BZPEERReading, trust and collaboration for research
Menu

Discover

GraphFollow connections around a paper, topic or saved view.

Workspaces

HomePick up where your research flow left off.InboxHandle requests, replies and notifications from one place.CollectionsCurate reading lists, evidence sets and shareable dossiers.ResearchSee your private provenance graph, trail and imports.CollaborationMove from discovery into focused discussion rooms.PublishDraft, preview and publish full-text research articles.

Network

ExpertsFind specialists worth following or asking for help.CommunitiesJoin research circles organized around shared work.PartnersSee external organizations active around the same topics.

Opportunities

ListingsBrowse roles, calls and collaborations with clearer fit signals.

Account

Log inReturn to your reading and collaboration workspace.Create accountStart saving work, following people and joining teams.
Log inCreate account

Researcher profile

Jian Zhao

Jian Zhao contributes to research discovery and scholarly infrastructure.

ResearcherAffiliation not importedOpen to collaborate
Computer VisionMachine LearningArtificial IntelligenceHuman-Computer Interactionphysics.opticsphysics.atom-pheess.IVMultiagent SystemsMultimediaSocial and Information Networksastro-ph.SRBiological Physicseess.ASGraphicsquant-phRoboticsSound

Trust snapshot

Quick read

Trust 21 - EmergingVerification L1Unclaimed author
44works
0followers
17topics
4close collaborators

Actions

Decide how to stay connected

Follow researcher0

Identity and collaboration

How to connect with this researcher

Claiming links this public author record to a researcher profile and unlocks direct collaboration workflows.

Log in to claim

Direct collaboration

Open a focused conversation when the fit is right

Claim this author entity first to unlock direct invitations.

Research graph

See the researcher in context

Open full explorer

Inspect adjacent work, topics, institutions and collaborators without jumping out to a separate graph page.

Building this graph slice

BZPEER is loading the nearby papers, people, topics and institutions for this page.

Published work

44 published item(s)

preprint2026arXiv

AffineLens: Capturing the Continuous Piecewise Affine Functions of Neural Networks

Piecewise affine neural networks (PANNs) provide a principled geometric perspective on neural network expressivity by characterizing the input--output map as a continuous piecewise affine (CPA) function whose complexity is governed by the number, arrangement, and shapes of its affine regions. However, existing interpretability and expressivity analyses often rely on indirect proxies (e.g., activation statistics or theoretical upper bounds) and rarely offer practical, accurate tools for enumerating and visualizing the induced region partition under realistic architectures and bounded input domains. In this work, we present AffineLens, a unified framework for computing the hyperplane arrangements and polyhedral structures underlying PANNs. Given a calibrated (bounded) input polytope, AffineLens identifies the subset of neuron-induced hyperplanes that intersect the domain, enumerates the resulting affine sub-regions in a layer-wise manner, and returns provably non-empty maximal CPA regions together with interior representatives. The framework further provides visualizations of region partitioning and decision boundaries, enabling qualitative inspection alongside quantitative region counts. By exploiting the affine restriction property of CPA networks under fixed activation patterns, AffineLens supports a broad class of modern components, including batch normalization, pooling, residual connections, multilayer perceptrons, and convolutional layers. Finally, we use AffineLens to perform a systematic empirical study of architectural expressivity, comparing networks through region complexity metrics and revealing how design choices influence the geometry of learned functions.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Beyond Accuracy: Evaluating Grounded Visual Evidence in Thinking with Images

Despite the remarkable progress of Vision-Language Models (VLMs) in adopting "Thinking-with-Images" capabilities, accurately evaluating the authenticity of their reasoning process remains a critical challenge. Existing benchmarks mainly rely on outcome-oriented accuracy, lacking the capability to assess whether models can accurately leverage fine-grained visual cues for multi-step reasoning. To address these limitations, we propose ViEBench, a process-verifiable benchmark designed to evaluate faithful visual reasoning. Comprising 200 multi-scenario high-resolution images with expert-annotated visual evidence, ViEBench uniquely categorizes tasks by difficulty into perception and reasoning dimensions, where reasoning tasks require utilizing localized visual details with prior knowledge. To establish comprehensive evaluation criteria, we introduce a dual-axis matrix that provides fine-grained metrics through four diagnostic quadrants, enabling transparent diagnosis of model behavior across varying task complexities. Our experiments yield several interesting observations: (1) VLMs can sometimes produce correct final answers despite grounding on irrelevant regions, and (2) they may successfully locate the correct evidence but still fail to utilize it to reach accurate conclusions. Our findings demonstrate that ViEBench can serve as a more explainable and practical benchmark for comprehensively evaluating the effectiveness agentic VLMs. The codes will be released at: https://github.com/Xuchen-Li/ViEBench.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

ChipLingo: A Systematic Training Framework for Large Language Models in EDA

With the rapid advancement of semiconductor technology, Electronic Design Automation (EDA) has become an increasingly knowledge-intensive and document-driven engineering domain. Although large language models (LLMs) have shown strong general capabilities, applying them directly to EDA remains challenging due to limited domain expertise, cross-tool knowledge confusion, and degraded retrieval-augmented generation (RAG) performance after domain training. To address these issues, this paper presents ChipLingo, a systematic training pipeline for domain-adapted LLMs tailored to EDA scenarios. ChipLingo consists of three stages: domain corpus construction with multi-source data curation and QA augmentation, domain-adaptive pretraining with comparisons of different parameter training strategies, and instruction alignment with RAG scenario training under diverse retrieval conditions. We also curate an internal benchmark, EDA-Bench, covering representative EDA tool scenarios, with plans for public release. Experiments show that ChipLingo-8B achieves 59.7% accuracy on EDA-Bench, outperforming the same-scale base model and some larger general-purpose models. ChipLingo-32B reaches 70.02%, approaching leading closed-source commercial models. Further analysis shows that QA augmentation improves domain performance, Partial FT offers a better balance between adaptation and general capability retention than LoRA, and explicit RAG scenario training mitigates the decline in retrieval utilization after domain training. These results demonstrate the practical value of systematic domain training for knowledge-intensive EDA tasks and provide a foundation for future EDA agents and external-knowledge-driven systems.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Incantation: Natural Language as the Action Interface for Multi-Entity Video World Models

Modern interactive video world models have achieved impressive visual fidelity, yet lack fine-grained multi-entity control and cross-entity, cross-world generalization. We trace this gap to the action interface: standard control protocols (e.g. animation IDs, device inputs, scene-level captions) bind action semantics to specific entities or engines at design time. We propose natural language as the interface to unlock expressiveness that no prior interface can achieve, and we present Incantation, the first interactive video world model with per-latent-frame (0.25 s) natural-language conditioning that supports simultaneous multi-entity control and concept-level cross-entity transfer beyond any fixed rendering pipeline. We pair a pretrained bidirectional video backbone with frame-local text cross-attention, and enable real-time long-horizon streaming through ODE-initialized Self-Forcing distillation with a RoPE-decoupled sliding KV-cache. We surpass the Action-Index baseline on cross-entity transfer (89% vs. 43%) and out-of-vocabulary prompts (90% vs. 0%), and our 2-step student sustains 19.7 FPS at 480p with stable FVD over 2-hour rollouts. We further apply the same architecture and training recipe to The King of Fighters, changing only the per-entity action vocabulary slots. We have released a preview subset of the Incantation dataset at https://huggingface.co/datasets/zhush/incantation-elden-ring-scenes, containing manually collected Elden Ring player-boss combat clips with structured action-oriented metadata. Larger-scale Elden Ring and KOF data will be released with the full project.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Learning How to Remember: A Meta-Cognitive Management Method for Structured and Transferable Agent Memory

Large language model (LLM) agents increasingly rely on accumulated memory to solve long-horizon decision-making tasks. However, most existing approaches store memory in fixed representations and reuse it at a single or implicit level of abstraction, which limits generalization and often leads to negative transfer when distribution shift. This paper proposes the Meta-Cognitive Memory Abstraction method (MCMA), which treats memory abstraction as a learnable cognitive skill rather than a fixed design choice. MCMA decouples task execution from memory management by combining a frozen task model with a learned memory copilot. The memory copilot is trained using direct preference optimization, it determines how memories should be structured, abstracted, and reused. Memories are further organized into a hierarchy of abstraction levels, enabling selective reuse based on task similarity. When no memory is transferable, MCMA transfers the ability to abstract and manage memory by transferring the memory copilot. Experiments on ALFWorld, ScienceWorld, and BabyAI demonstrate substantial improvements in performance, out-of-distribution generalization, and cross-task transfer over several baselines.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Loupe: A Generalizable and Adaptive Framework for Image Forgery Detection

The proliferation of generative models has raised serious concerns about visual content forgery. Existing deepfake detection methods primarily target either image-level classification or pixel-wise localization. While some achieve high accuracy, they often suffer from limited generalization across manipulation types or rely on complex architectures. In this paper, we propose Loupe, a lightweight yet effective framework for joint deepfake detection and localization. Loupe integrates a patch-aware classifier and a segmentation module with conditional queries, allowing simultaneous global authenticity classification and fine-grained mask prediction. To enhance robustness against distribution shifts of test set, Loupe introduces a pseudo-label-guided test-time adaptation mechanism by leveraging patch-level predictions to supervise the segmentation head. Extensive experiments on the DDL dataset demonstrate that Loupe achieves state-of-the-art performance, securing the first place in the IJCAI 2025 Deepfake Detection and Localization Challenge with an overall score of 0.846. Our results validate the effectiveness of the proposed patch-level fusion and conditional query design in improving both classification accuracy and spatial localization under diverse forgery patterns. The code is available at https://github.com/Kamichanw/Loupe.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Metis: Learning to Jailbreak LLMs via Self-Evolving Metacognitive Policy Optimization

Red teaming is critical for uncovering vulnerabilities in Large Language Models (LLMs). While automated methods have improved scalability, existing approaches often rely on static heuristics or stochastic search, rendering them brittle against advanced safety alignment. To address this, we introduce Metis, a framework that reformulates jailbreaking as inference-time policy optimization within an adversarial Partially Observable Markov Decision Process (POMDP). Metis employs a self-evolving metacognitive loop to perform causal diagnosis of a target's defense logic and leverages structured feedback as a semantic gradient to refine its policy, offering enhanced interpretability through transparent reasoning traces. Extensive evaluations across 10 diverse models demonstrate that Metis achieves the strongest average Attack Success Rate (ASR) among compared methods at 89.2%, maintaining high efficacy on resilient frontier models (e.g., 76.0% on O1 and 78.0% on GPT-5-chat) where traditional baselines exhibit substantial performance degradation. By replacing redundant exploration with directed optimization, Metis reduces token costs by an average of 8.2x and up to 11.4x. Our analysis reveals that current defenses remain vulnerable to internally-steered, closed-loop reasoning trajectories under the tested settings, highlighting a critical need for next-generation defenses capable of reasoning about safety dynamically during inference.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

The RoboSense Challenge: Sense Anything, Navigate Anywhere, Adapt Across Platforms

Autonomous systems are increasingly deployed in open and dynamic environments -- from city streets to aerial and indoor spaces -- where perception models must remain reliable under sensor noise, environmental variation, and platform shifts. However, even state-of-the-art methods often degrade under unseen conditions, highlighting the need for robust and generalizable robot sensing. The RoboSense 2025 Challenge is designed to advance robustness and adaptability in robot perception across diverse sensing scenarios. It unifies five complementary research tracks spanning language-grounded decision making, socially compliant navigation, sensor configuration generalization, cross-view and cross-modal correspondence, and cross-platform 3D perception. Together, these tasks form a comprehensive benchmark for evaluating real-world sensing reliability under domain shifts, sensor failures, and platform discrepancies. RoboSense 2025 provides standardized datasets, baseline models, and unified evaluation protocols, enabling large-scale and reproducible comparison of robust perception methods. The challenge attracted 143 teams from 85 institutions across 16 countries, reflecting broad community engagement. By consolidating insights from 23 winning solutions, this report highlights emerging methodological trends, shared design principles, and open challenges across all tracks, marking a step toward building robots that can sense reliably, act robustly, and adapt across platforms in real-world environments.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

TIE: Time Interval Encoding for Video Generation over Events

Director-style prompting, robotic action prediction, and interactive video agents demand temporal grounding over concurrent events -- a regime in which 68% of general clips and over 99% of robotics/gameplay clips contain overlapping events, yet existing multi-event generators rest on a single-active-prompt assumption. However, modern video generators, such as Diffusion Transformers (DiT), represent time as discrete points through point-wise positional encodings. This formulation creates a fundamental dimension mismatch: temporally extended intervals and overlapping events are mathematically unrepresentable to the attention mechanism. In this paper, we propose Time Interval Encoding (TIE), a principled, plug-and-play interval-aware generalization of rotary embeddings that elevates time intervals to first-class primitives inside DiT cross-attention. Rather than introducing another heuristic interval embedding, we show that, within RoPE-compatible bilinear attention, TIE is characterized by two basic principles: Temporal Integrability, which requires an event to aggregate positional evidence over its full duration, and Duration Invariance, which removes the trivial bias toward longer intervals. Under a uniform kernel, this characterization yields an efficient closed-form sinc-based solution that preserves the standard attention interface and naturally attenuates boundary noise through interval integration. Empirically, TIE preserves the visual quality of the base DiT model while substantially improving temporal controllability. In our experiments on the OmniEvents dataset, it improves human-verified Temporal Constraint Satisfaction Rate from 77.34% to 96.03% and reduces temporal boundary error from 0.261s to 0.073s, while also improving trajectory-level temporal alignment metrics. The code and dataset are available at https://github.com/MatrixTeam-AI/TIE.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

X-Voice: Enabling Everyone to Speak 30 Languages via Zero-Shot Cross-Lingual Voice Cloning

In this paper, we present X-Voice, a 0.4B multilingual zero-shot voice cloning model that clones arbitrary voices and enables everyone to speak 30 languages. X-Voice is trained on a 420K-hour multilingual corpus using the International Phonetic Alphabet (IPA) as a unified representation. To eliminate the reliance on prompt text without complex preprocessing like forced alignment, we design a two-stage training paradigm. In Stage 1, we establish X-Voice$_{\text{s1}}$ through standard conditional flow-matching training and use it to synthesize 10K hours of speaker-consistent segments as audio prompts. In Stage 2, we fine-tune on these audio pairs with prompt text masked to derive X-Voice$_{\text{s2}}$, which enables zero-shot voice cloning without requiring transcripts of audio prompts. Architecturally, we extend F5-TTS by implementing a dual-level injection of language identifiers and decoupling and scheduling of Classifier-Free Guidance to facilitate multilingual speech synthesis. Subjective and objective evaluation results demonstrate that X-Voice outperforms existing flow-matching based multilingual systems like LEMAS-TTS and achieves zero-shot cross-lingual cloning capabilities comparable to billion-scale models such as Qwen3-TTS. To facilitate research transparency and community advancement, we open-source all related resources.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

AugRmixAT: A Data Processing and Training Method for Improving Multiple Robustness and Generalization Performance

Deep neural networks are powerful, but they also have shortcomings such as their sensitivity to adversarial examples, noise, blur, occlusion, etc. Moreover, ensuring the reliability and robustness of deep neural network models is crucial for their application in safety-critical areas. Much previous work has been proposed to improve specific robustness. However, we find that the specific robustness is often improved at the sacrifice of the additional robustness or generalization ability of the neural network model. In particular, adversarial training methods significantly hurt the generalization performance on unperturbed data when improving adversarial robustness. In this paper, we propose a new data processing and training method, called AugRmixAT, which can simultaneously improve the generalization ability and multiple robustness of neural network models. Finally, we validate the effectiveness of AugRmixAT on the CIFAR-10/100 and Tiny-ImageNet datasets. The experiments demonstrate that AugRmixAT can improve the model's generalization performance while enhancing the white-box robustness, black-box robustness, common corruption robustness, and partial occlusion robustness.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

AutoAdversary: A Pixel Pruning Method for Sparse Adversarial Attack

Deep neural networks (DNNs) have been proven to be vulnerable to adversarial examples. A special branch of adversarial examples, namely sparse adversarial examples, can fool the target DNNs by perturbing only a few pixels. However, many existing sparse adversarial attacks use heuristic methods to select the pixels to be perturbed, and regard the pixel selection and the adversarial attack as two separate steps. From the perspective of neural network pruning, we propose a novel end-to-end sparse adversarial attack method, namely AutoAdversary, which can find the most important pixels automatically by integrating the pixel selection into the adversarial attack. Specifically, our method utilizes a trainable neural network to generate a binary mask for the pixel selection. After jointly optimizing the adversarial perturbation and the neural network, only the pixels corresponding to the value 1 in the mask are perturbed. Experiments demonstrate the superiority of our proposed method over several state-of-the-art methods. Furthermore, since AutoAdversary does not require a heuristic pixel selection process, it does not slow down excessively as other methods when the image size increases.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Bond-Selective Intensity Diffraction Tomography

Recovering molecular information remains a grand challenge in the widely used holographic and computational imaging technologies. To address this challenge, we developed a computational mid-infrared photothermal microscope, termed Bond-selective Intensity Diffraction Tomography (BS-IDT). Based on a low-cost brightfield microscope with an add-on pulsed light source, BS-IDT recovers both infrared spectra and bond-selective 3D refractive index maps from intensity-only measurements. High-fidelity infrared fingerprint spectra extraction is validated. Volumetric chemical imaging of biological cells is demonstrated at a speed of ~20 seconds per volume, with a lateral and axial resolution of ~350 nm and ~1.1 micron, respectively. BS-IDT's application potential is investigated by chemically quantifying lipids stored in cancer cells and volumetric chemical imaging on Caenorhabditis elegans with a large field of view (~100 micron X 100 micron).

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Coach-assisted Multi-Agent Reinforcement Learning Framework for Unexpected Crashed Agents

Multi-agent reinforcement learning is difficult to be applied in practice, which is partially due to the gap between the simulated and real-world scenarios. One reason for the gap is that the simulated systems always assume that the agents can work normally all the time, while in practice, one or more agents may unexpectedly "crash" during the coordination process due to inevitable hardware or software failures. Such crashes will destroy the cooperation among agents, leading to performance degradation. In this work, we present a formal formulation of a cooperative multi-agent reinforcement learning system with unexpected crashes. To enhance the robustness of the system to crashes, we propose a coach-assisted multi-agent reinforcement learning framework, which introduces a virtual coach agent to adjust the crash rate during training. We design three coaching strategies and the re-sampling strategy for our coach agent. To the best of our knowledge, this work is the first to study the unexpected crashes in the multi-agent system. Extensive experiments on grid-world and StarCraft II micromanagement tasks demonstrate the efficacy of adaptive strategy compared with the fixed crash rate strategy and curriculum learning strategy. The ablation study further illustrates the effectiveness of our re-sampling strategy.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

CodeToon: Story Ideation, Auto Comic Generation, and Structure Mapping for Code-Driven Storytelling

Recent work demonstrated how we can design and use coding strips, a form of comic strips with corresponding code, to enhance teaching and learning in programming. However, creating coding strips is a creative, time-consuming process. Creators have to generate stories from code (code->story) and design comics from stories (story->comic). We contribute CodeToon, a comic authoring tool that facilitates this code-driven storytelling process with two mechanisms: (1) story ideation from code using metaphor and (2) automatic comic generation from the story. We conducted a two-part user study that evaluates the tool and the comics generated by participants to test whether CodeToon facilitates the authoring process and helps generate quality comics. Our results show that CodeToon helps users create accurate, informative, and useful coding strips in a significantly shorter time. Overall, this work contributes methods and design guidelines for code-driven storytelling and opens up opportunities for using art to support computer science education.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Coordinate-Aligned Multi-Camera Collaboration for Active Multi-Object Tracking

Active Multi-Object Tracking (AMOT) is a task where cameras are controlled by a centralized system to adjust their poses automatically and collaboratively so as to maximize the coverage of targets in their shared visual field. In AMOT, each camera only receives partial information from its observation, which may mislead cameras to take locally optimal action. Besides, the global goal, i.e., maximum coverage of objects, is hard to be directly optimized. To address the above issues, we propose a coordinate-aligned multi-camera collaboration system for AMOT. In our approach, we regard each camera as an agent and address AMOT with a multi-agent reinforcement learning solution. To represent the observation of each agent, we first identify the targets in the camera view with an image detector, and then align the coordinates of the targets in 3D environment. We define the reward of each agent based on both global coverage as well as four individual reward terms. The action policy of the agents is derived with a value-based Q-network. To the best of our knowledge, we are the first to study the AMOT task. To train and evaluate the efficacy of our system, we build a virtual yet credible 3D environment, named "Soccer Court", to mimic the real-world AMOT scenario. The experimental results show that our system achieves a coverage of 71.88%, outperforming the baseline method by 8.9%.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

CTDS: Centralized Teacher with Decentralized Student for Multi-Agent Reinforcement Learning

Due to the partial observability and communication constraints in many multi-agent reinforcement learning (MARL) tasks, centralized training with decentralized execution (CTDE) has become one of the most widely used MARL paradigms. In CTDE, centralized information is dedicated to learning the allocation of the team reward with a mixing network, while the learning of individual Q-values is usually based on local observations. The insufficient utility of global observation will degrade performance in challenging environments. To this end, this work proposes a novel Centralized Teacher with Decentralized Student (CTDS) framework, which consists of a teacher model and a student model. Specifically, the teacher model allocates the team reward by learning individual Q-values conditioned on global observation, while the student model utilizes the partial observations to approximate the Q-values estimated by the teacher model. In this way, CTDS balances the full utilization of global observation during training and the feasibility of decentralized execution for online inference. Our CTDS framework is generic which is ready to be applied upon existing CTDE methods to boost their performance. We conduct experiments on a challenging set of StarCraft II micromanagement tasks to test the effectiveness of our method and the results show that CTDS outperforms the existing value-based MARL methods.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

DouZero+: Improving DouDizhu AI by Opponent Modeling and Coach-guided Learning

Recent years have witnessed the great breakthrough of deep reinforcement learning (DRL) in various perfect and imperfect information games. Among these games, DouDizhu, a popular card game in China, is very challenging due to the imperfect information, large state space, elements of collaboration and a massive number of possible moves from turn to turn. Recently, a DouDizhu AI system called DouZero has been proposed. Trained using traditional Monte Carlo method with deep neural networks and self-play procedure without the abstraction of human prior knowledge, DouZero has outperformed all the existing DouDizhu AI programs. In this work, we propose to enhance DouZero by introducing opponent modeling into DouZero. Besides, we propose a novel coach network to further boost the performance of DouZero and accelerate its training process. With the integration of the above two techniques into DouZero, our DouDizhu AI system achieves better performance and ranks top in the Botzone leaderboard among more than 400 AI agents, including DouZero.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Face.evoLVe: A High-Performance Face Recognition Library

In this paper, we develop face.evoLVe -- a comprehensive library that collects and implements a wide range of popular deep learning-based methods for face recognition. First of all, face.evoLVe is composed of key components that cover the full process of face analytics, including face alignment, data processing, various backbones, losses, and alternatives with bags of tricks for improving performance. Later, face.evoLVe supports multi-GPU training on top of different deep learning platforms, such as PyTorch and PaddlePaddle, which facilitates researchers to work on both large-scale datasets with millions of images and low-shot counterparts with limited well-annotated data. More importantly, along with face.evoLVe, images before & after alignment in the common benchmark datasets are released with source codes and trained models provided. All these efforts lower the technical burdens in reproducing the existing methods for comparison, while users of our library could focus on developing advanced approaches more efficiently. Last but not least, face.evoLVe is well designed and vibrantly evolving, so that new face recognition approaches can be easily plugged into our framework. Note that we have used face.evoLVe to participate in a number of face recognition competitions and secured the first place. The version that supports PyTorch is publicly available at https://github.com/ZhaoJ9014/face.evoLVe.PyTorch and the PaddlePaddle version is available at https://github.com/ZhaoJ9014/face.evoLVe.PyTorch/tree/master/paddle. Face.evoLVe has been widely used for face analytics, receiving 2.4K stars and 622 forks.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Imaging moving atoms by holographically reconstructing the dragged slow light

The propagation of light in moving media is dragged by atomic motion. The light-drag effect can be dramatically enhanced by reducing the group velocity with electro-magnetically induced transparency (EIT). We develop a systematic procedure to accurately reconstruct the complex wavefront of the slow light with single-shot measurements, enabling precise, photon shot-noise limited spectroscopic measurements of atomic response across EIT even in presence of generic atomic number fluctuations. Applying the technique to an expanding cloud of cold atoms, we demonstrate simultaneous inference of the atomic density distribution and the velocity field from the complex imaging data. This inline imaging technique may assist a wide range of cold atom experiments to access spectroscopic and phase space information with in situ and minimally destructive measurements.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Infographics Wizard: Flexible Infographics Authoring and Design Exploration

Infographics are an aesthetic visual representation of information following specific design principles of human perception. Designing infographics can be a tedious process for non-experts and time-consuming, even for professional designers. With the help of designers, we propose a semi-automated infographic framework for general structured and flow-based infographic design generation. For novice designers, our framework automatically creates and ranks infographic designs for a user-provided text with no requirement for design input. However, expert designers can still provide custom design inputs to customize the infographics. We will also contribute an individual visual group (VG) designs dataset (in SVG), along with a 1k complete infographic image dataset with segmented VGs in this work. Evaluation results confirm that by using our framework, designers from all expertise levels can generate generic infographic designs faster than existing methods while maintaining the same quality as hand-designed infographics templates.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

MCMARL: Parameterizing Value Function via Mixture of Categorical Distributions for Multi-Agent Reinforcement Learning

In cooperative multi-agent tasks, a team of agents jointly interact with an environment by taking actions, receiving a team reward and observing the next state. During the interactions, the uncertainty of environment and reward will inevitably induce stochasticity in the long-term returns and the randomness can be exacerbated with the increasing number of agents. However, such randomness is ignored by most of the existing value-based multi-agent reinforcement learning (MARL) methods, which only model the expectation of Q-value for both individual agents and the team. Compared to using the expectations of the long-term returns, it is preferable to directly model the stochasticity by estimating the returns through distributions. With this motivation, this work proposes a novel value-based MARL framework from a distributional perspective, \emph{i.e.}, parameterizing value function via \underline{M}ixture of \underline{C}ategorical distributions for MARL. Specifically, we model both individual Q-values and global Q-value with categorical distribution. To integrate categorical distributions, we define five basic operations on the distribution, which allow the generalization of expected value function factorization methods (\emph{e.g.}, VDN and QMIX) to their MCMARL variants. We further prove that our MCMARL framework satisfies \emph{Distributional-Individual-Global-Max} (DIGM) principle with respect to the expectation of distribution, which guarantees the consistency between joint and individual greedy action selections in the global Q-value and individual Q-values. Empirically, we evaluate MCMARL on both a stochastic matrix game and a challenging set of StarCraft II micromanagement tasks, showing the efficacy of our framework.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

MSDN: Mutually Semantic Distillation Network for Zero-Shot Learning

The key challenge of zero-shot learning (ZSL) is how to infer the latent semantic knowledge between visual and attribute features on seen classes, and thus achieving a desirable knowledge transfer to unseen classes. Prior works either simply align the global features of an image with its associated class semantic vector or utilize unidirectional attention to learn the limited latent semantic representations, which could not effectively discover the intrinsic semantic knowledge e.g., attribute semantics) between visual and attribute features. To solve the above dilemma, we propose a Mutually Semantic Distillation Network (MSDN), which progressively distills the intrinsic semantic representations between visual and attribute features for ZSL. MSDN incorporates an attribute$\rightarrow$visual attention sub-net that learns attribute-based visual features, and a visual$\rightarrow$attribute attention sub-net that learns visual-based attribute features. By further introducing a semantic distillation loss, the two mutual attention sub-nets are capable of learning collaboratively and teaching each other throughout the training process. The proposed MSDN yields significant improvements over the strong baselines, leading to new state-of-the-art performances on three popular challenging benchmarks, i.e., CUB, SUN, and AWA2. Our codes have been available at: \url{https://github.com/shiming-chen/MSDN}.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Multi-Target Active Object Tracking with Monte Carlo Tree Search and Target Motion Modeling

In this work, we are dedicated to multi-target active object tracking (AOT), where there are multiple targets as well as multiple cameras in the environment. The goal is maximize the overall target coverage of all cameras. Previous work makes a strong assumption that each camera is fixed in a location and only allowed to rotate, which limits its application. In this work, we relax the setting by allowing all cameras to both move along the boundary lines and rotate. In our setting, the action space becomes much larger, which leads to much higher computational complexity to identify the optimal action. To this end, we propose to leverage the action selection from multi-agent reinforcement learning (MARL) network to prune the search tree of Monte Carlo Tree Search (MCTS) method, so as to find the optimal action more efficiently. Besides, we model the motion of the targets to predict the future position of the targets, which makes a better estimation of the future environment state in the MCTS process. We establish a multi-target 2D environment to simulate the sports games, and experimental results demonstrate that our method can effectively improve the target coverage.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Network Comparison with Interpretable Contrastive Network Representation Learning

Identifying unique characteristics in a network through comparison with another network is an essential network analysis task. For example, with networks of protein interactions obtained from normal and cancer tissues, we can discover unique types of interactions in cancer tissues. This analysis task could be greatly assisted by contrastive learning, which is an emerging analysis approach to discover salient patterns in one dataset relative to another. However, existing contrastive learning methods cannot be directly applied to networks as they are designed only for high-dimensional data analysis. To address this problem, we introduce a new analysis approach called contrastive network representation learning (cNRL). By integrating two machine learning schemes, network representation learning and contrastive learning, cNRL enables embedding of network nodes into a low-dimensional representation that reveals the uniqueness of one network compared to another. Within this approach, we also design a method, named i-cNRL, which offers interpretability in the learned results, allowing for understanding which specific patterns are only found in one network. We demonstrate the effectiveness of i-cNRL for network comparison with multiple network models and real-world datasets. Furthermore, we compare i-cNRL and other potential cNRL algorithm designs through quantitative and qualitative evaluations.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Review Neural Networks about Image Transformation Based on IGC Learning Framework with Annotated Information

Image transformation, a class of vision and graphics problems whose goal is to learn the mapping between an input image and an output image, develops rapidly in the context of deep neural networks. In Computer Vision (CV), many problems can be regarded as the image transformation task, e.g., semantic segmentation and style transfer. These works have different topics and motivations, making the image transformation task flourishing. Some surveys only review the research on style transfer or image-to-image translation, all of which are just a branch of image transformation. However, none of the surveys summarize those works together in a unified framework to our best knowledge. This paper proposes a novel learning framework including Independent learning, Guided learning, and Cooperative learning, called the IGC learning framework. The image transformation we discuss mainly involves the general image-to-image translation and style transfer about deep neural networks. From the perspective of this framework, we review those subtasks and give a unified interpretation of various scenarios. We categorize related subtasks about the image transformation according to similar development trends. Furthermore, experiments have been performed to verify the effectiveness of IGC learning. Finally, new research directions and open problems are discussed for future research.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Revisiting QMIX: Discriminative Credit Assignment by Gradient Entropy Regularization

In cooperative multi-agent systems, agents jointly take actions and receive a team reward instead of individual rewards. In the absence of individual reward signals, credit assignment mechanisms are usually introduced to discriminate the contributions of different agents so as to achieve effective cooperation. Recently, the value decomposition paradigm has been widely adopted to realize credit assignment, and QMIX has become the state-of-the-art solution. In this paper, we revisit QMIX from two aspects. First, we propose a new perspective on credit assignment measurement and empirically show that QMIX suffers limited discriminability on the assignment of credits to agents. Second, we propose a gradient entropy regularization with QMIX to realize a discriminative credit assignment, thereby improving the overall performance. The experiments demonstrate that our approach can comparatively improve learning efficiency and achieve better performance.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

RSTAM: An Effective Black-Box Impersonation Attack on Face Recognition using a Mobile and Compact Printer

Face recognition has achieved considerable progress in recent years thanks to the development of deep neural networks, but it has recently been discovered that deep neural networks are vulnerable to adversarial examples. This means that face recognition models or systems based on deep neural networks are also susceptible to adversarial examples. However, the existing methods of attacking face recognition models or systems with adversarial examples can effectively complete white-box attacks but not black-box impersonation attacks, physical attacks, or convenient attacks, particularly on commercial face recognition systems. In this paper, we propose a new method to attack face recognition models or systems called RSTAM, which enables an effective black-box impersonation attack using an adversarial mask printed by a mobile and compact printer. First, RSTAM enhances the transferability of the adversarial masks through our proposed random similarity transformation strategy. Furthermore, we propose a random meta-optimization strategy for ensembling several pre-trained face models to generate more general adversarial masks. Finally, we conduct experiments on the CelebA-HQ, LFW, Makeup Transfer (MT), and CASIA-FaceV5 datasets. The performance of the attacks is also evaluated on state-of-the-art commercial face recognition systems: Face++, Baidu, Aliyun, Tencent, and Microsoft. Extensive experiments show that RSTAM can effectively perform black-box impersonation attacks on face recognition models or systems.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

The Chinese Hα Solar Explorer (CHASE) mission: An overview

The Chinese Hα Solar Explorer (CHASE), dubbed "Xihe" - Goddess of the Sun, was launched on October 14, 2021 as the first solar space mission of China National Space Administration (CNSA). The CHASE mission is designed to test a newly developed satellite platform and to acquire the spectroscopic observations in the Hα waveband. The Hα Imaging Spectrograph (HIS) is the scientific payload of the CHASE satellite. It consists of two observational modes: raster scanning mode and continuum imaging mode. The raster scanning mode obtains full-Sun or region-of-interest spectral images from 6559.7 to 6565.9 Å and from 6567.8 to 6570.6 Å with 0.024 Å pixel spectral resolution and 1 minute temporal resolution. The continuum imaging mode obtains photospheric images in continuum around 6689 Å with the full width at half maximum of 13.4 Å. The CHASE mission will advance our understanding of the dynamics of solar activity in the photosphere and chromosphere. In this paper, we present an overview of the CHASE mission including the scientific objectives, HIS instrument overview, data calibration flow, and first results of on-orbit observations.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Thin-Plate Spline Motion Model for Image Animation

Image animation brings life to the static object in the source image according to the driving video. Recent works attempt to perform motion transfer on arbitrary objects through unsupervised methods without using a priori knowledge. However, it remains a significant challenge for current unsupervised methods when there is a large pose gap between the objects in the source and driving images. In this paper, a new end-to-end unsupervised motion transfer framework is proposed to overcome such issue. Firstly, we propose thin-plate spline motion estimation to produce a more flexible optical flow, which warps the feature maps of the source image to the feature domain of the driving image. Secondly, in order to restore the missing regions more realistically, we leverage multi-resolution occlusion masks to achieve more effective feature fusion. Finally, additional auxiliary loss functions are designed to ensure that there is a clear division of labor in the network modules, encouraging the network to generate high-quality images. Our method can animate a variety of objects, including talking faces, human bodies, and pixel animations. Experiments demonstrate that our method performs better on most benchmarks than the state of the art with visible improvements in pose-related metrics.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Toward Systematic Considerations of Missingness in Visual Analytics

Data-driven decision making has been a common task in today's big data era, from simple choices such as finding a fast way to drive home, to complex decisions on medical treatment. It is often supported by visual analytics. For various reasons (e.g., system failure, interrupted network, intentional information hiding, or bias), visual analytics for sensemaking of data involves missingness (e.g., data loss and incomplete analysis), which impacts human decisions. For example, missing data can cost a business millions of dollars, and failing to recognize key evidence can put an innocent person in jail. Being aware of missingness is critical to avoid such catastrophes. To fulfill this, as an initial step, we consider missingness in visual analytics from two aspects: data-centric and human-centric. The former emphasizes missingness in three data-related categories: data composition, data relationship, and data usage. The latter focuses on the human-perceived missingness at three levels: observed-level, inferred-level, and ignored-level. Based on them, we discuss possible roles of visualizations for handling missingness, and conclude our discussion with future research opportunities.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

Anti-UAV: A Large Multi-Modal Benchmark for UAV Tracking

Unmanned Aerial Vehicle (UAV) offers lots of applications in both commerce and recreation. With this, monitoring the operation status of UAVs is crucially important. In this work, we consider the task of tracking UAVs, providing rich information such as location and trajectory. To facilitate research on this topic, we propose a dataset, Anti-UAV, with more than 300 video pairs containing over 580k manually annotated bounding boxes. The releasing of such a large-scale dataset could be a useful initial step in research of tracking UAVs. Furthermore, the advancement of addressing research challenges in Anti-UAV can help the design of anti-UAV systems, leading to better surveillance of UAVs. Besides, a novel approach named dual-flow semantic consistency (DFSC) is proposed for UAV tracking. Modulated by the semantic flow across video sequences, the tracker learns more robust class-level semantic information and obtains more discriminative instance-level features. Experimental results demonstrate that Anti-UAV is very challenging, and the proposed method can effectively improve the tracker's performance. The Anti-UAV benchmark and the code of the proposed approach will be publicly available at https://github.com/ucas-vg/Anti-UAV.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

IC Networks: Remodeling the Basic Unit for Convolutional Neural Networks

Convolutional neural network (CNN) is a class of artificial neural networks widely used in computer vision tasks. Most CNNs achieve excellent performance by stacking certain types of basic units. In addition to increasing the depth and width of the network, designing more effective basic units has become an important research topic. Inspired by the elastic collision model in physics, we present a general structure which can be integrated into the existing CNNs to improve their performance. We term it the "Inter-layer Collision" (IC) structure. Compared to the traditional convolution structure, the IC structure introduces nonlinearity and feature recalibration in the linear convolution operation, which can capture more fine-grained features. In addition, a new training method, namely weak logit distillation (WLD), is proposed to speed up the training of IC networks by extracting knowledge from pre-trained basic models. In the ImageNet experiment, we integrate the IC structure into ResNet-50 and reduce the top-1 error from 22.38% to 21.75%, which also catches up the top-1 error of ResNet-100 (21.75%) with nearly half of FLOPs.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

InfoColorizer: Interactive Recommendation of Color Palettes for Infographics

When designing infographics, general users usually struggle with getting desired color palettes using existing infographic authoring tools, which sometimes sacrifice customizability, require design expertise, or neglect the influence of elements' spatial arrangement. We propose a data-driven method that provides flexibility by considering users' preferences, lowers the expertise barrier via automation, and tailors suggested palettes to the spatial layout of elements. We build a recommendation engine by utilizing deep learning techniques to characterize good color design practices from data, and further develop InfoColorizer, a tool that allows users to obtain color palettes for their infographics in an interactive and dynamic manner. To validate our method, we conducted a comprehensive four-part evaluation, including case studies, a controlled user study, a survey study, and an interview study. The results indicate that InfoColorizer can provide compelling palette recommendations with adequate flexibility, allowing users to effectively obtain high-quality color design for input infographics with low effort.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

NBSearch: Semantic Search and Visual Exploration of Computational Notebooks

Code search is an important and frequent activity for developers using computational notebooks (e.g., Jupyter). The flexibility of notebooks brings challenges for effective code search, where classic search interfaces for traditional software code may be limited. In this paper, we propose, NBSearch, a novel system that supports semantic code search in notebook collections and interactive visual exploration of search results. NBSearch leverages advanced machine learning models to enable natural language search queries and intuitive visualizations to present complicated intra- and inter-notebook relationships in the returned results. We developed NBSearch through an iterative participatory design process with two experts from a large software company. We evaluated the models with a series of experiments and the whole system with a controlled user study. The results indicate the feasibility of our analytical pipeline and the effectiveness of NBSearch to support code search in large notebook collections.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

Quantum error correction with the color-Gottesman-Kitaev-Preskill code

The Gottesman-Kitaev-Preskill (GKP) code is an important type of bosonic quantum error-correcting code. Since the GKP code only protects against small shift errors in $\hat{p}$ and $\hat{q}$ quadratures, it is necessary to concatenate the GKP code with a stabilizer code for the larger error correction. In this paper, we consider the concatenation of the single-mode GKP code with the two-dimension (2D) color code (color-GKP code) on the square-octagon lattice. We use the Steane type scheme with a maximum-likelihood estimation (ME-Steane scheme) for GKP error correction and show its advantage for the concatenation. In our main work, the minimum-weight perfect matching (MWPM) algorithm is applied to decode the color-GKP code. Complemented with the continuous-variable information from the GKP code, the threshold of 2D color code is improved. If only data GKP qubits are noisy, the threshold reaches $σ\approx 0.59$ $(\bar{p}\approx13.3\%)$ compared with $\bar{p}=10.2\%$ of the normal 2D color code. If measurements are also noisy, we introduce the generalized Restriction Decoder on the three-dimension space-time graph for decoding. The threshold reaches $σ\approx 0.46$ when measurements in the GKP error correction are noiseless, and $σ\approx 0.24$ when all measurements are noisy. Lastly, the good performance of the generalized Restriction Decoder is also shown on the normal 2D color code giving the threshold at $3.1\%$ under the phenomenological error model.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

3D Face Reconstruction from A Single Image Assisted by 2D Face Images in the Wild

3D face reconstruction from a single 2D image is a challenging problem with broad applications. Recent methods typically aim to learn a CNN-based 3D face model that regresses coefficients of 3D Morphable Model (3DMM) from 2D images to render 3D face reconstruction or dense face alignment. However, the shortage of training data with 3D annotations considerably limits performance of those methods. To alleviate this issue, we propose a novel 2D-assisted self-supervised learning (2DASL) method that can effectively use "in-the-wild" 2D face images with noisy landmark information to substantially improve 3D face model learning. Specifically, taking the sparse 2D facial landmarks as additional information, 2DSAL introduces four novel self-supervision schemes that view the 2D landmark and 3D landmark prediction as a self-mapping process, including the 2D and 3D landmark self-prediction consistency, cycle-consistency over the 2D landmark prediction and self-critic over the predicted 3DMM coefficients based on landmark predictions. Using these four self-supervision schemes, the 2DASL method significantly relieves demands on the the conventional paired 2D-to-3D annotations and gives much higher-quality 3D face models without requiring any additional 3D annotations. Experiments on multiple challenging datasets show that our method outperforms state-of-the-arts for both 3D face reconstruction and dense face alignment by a large margin.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

A Visual Analytics Framework for Contrastive Network Analysis

A common network analysis task is comparison of two networks to identify unique characteristics in one network with respect to the other. For example, when comparing protein interaction networks derived from normal and cancer tissues, one essential task is to discover protein-protein interactions unique to cancer tissues. However, this task is challenging when the networks contain complex structural (and semantic) relations. To address this problem, we design ContraNA, a visual analytics framework leveraging both the power of machine learning for uncovering unique characteristics in networks and also the effectiveness of visualization for understanding such uniqueness. The basis of ContraNA is cNRL, which integrates two machine learning schemes, network representation learning (NRL) and contrastive learning (CL), to generate a low-dimensional embedding that reveals the uniqueness of one network when compared to another. ContraNA provides an interactive visualization interface to help analyze the uniqueness by relating embedding results and network structures as well as explaining the learned features by cNRL. We demonstrate the usefulness of ContraNA with two case studies using real-world datasets. We also evaluate through a controlled user study with 12 participants on network comparison tasks. The results show that participants were able to both effectively identify unique characteristics from complex networks and interpret the results obtained from cNRL.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Atomic spin-wave control and spin-dependent kicks with shaped subnanosecond pulses

The absorption of traveling photons resonant with electric dipole transitions of an atomic gas naturally leads to electric dipole spin wave excitations. For a number of applications, it would be highly desirable to shape and coherently control the spatial waveform of the spin waves before spontaneous emission can occur. This paper details a recently developed optical control technique to achieve this goal, where counter-propagating, shaped sub-nanosecond pulses impart sub-wavelength geometric phases to the spin waves by cyclically driving an auxiliary transition. In particular, we apply this technique to reversibly shift the wave vector of a spin wave on the $D2$ line of laser-cooled $^{87}$Rb atoms, by driving an auxiliary $D1$ transition with shape-optimized pulses, so as to shut off and recall superradiance on demand. We investigate a spin-dependent momentum transfer during the spin-wave control process, which leads to a transient optical force as large as $\sim 1\hbar k$/ns, and study the limitations to the achieved $70\sim 75\%$ spin wave control efficiency by jointly characterizing the spin-wave control and matterwave acceleration. Aided by numerical modeling, we project potential future improvements of the control fidelity to the $99\%$ level when the atomic states are better prepared and by equipping a faster and more powerful pulse shaper. Our technique also enables a background-free measurement of the superradiant emission to unveil the precise scaling of the emission intensity and decay rate with optical depth.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

IC-Network: Efficient Structure for Convolutional Neural Networks

Neural networks have been widely used, and most networks achieve excellent performance by stacking certain types of basic units. Compared to increasing the depth and width of the network, designing more effective basic units has become an important research topic. Inspired by the elastic collision model in physics, we present a universal structure that could be integrated into the existing network structures to speed up the training process and increase their generalization abilities. We term this structure the "Inter-layer Collision" (IC) structure. We built two kinds of basic computational units (IC layer and IC block) that compose the convolutional neural networks (CNNs) by combining the IC structure with the convolution operation. Compared to traditional convolutions, both of the proposed computational units have a stronger non-linear representation ability and can filter features useful for a given task. Using these computational units to build networks, we bring significant improvements in performance for existing state-of-the-art CNNs. On the imagenet experiment, we integrate the IC block into ResNet-50 and reduce the top-1 error from 22.85% to 21.49%, which also exceeds the top-1 error of ResNet-100 (21.75%).

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

ICE: Identify and Compare Event Sequence Sets through Multi-Scale Matrix and Unit Visualizations

Comparative analysis of event sequence data is essential in many application domains, such as website design and medical care. However, analysts often face two challenges: they may not always know which sets of event sequences in the data are useful to compare, and the comparison needs to be achieved at different granularity, due to the volume and complexity of the data. This paper presents, ICE, an interactive visualization that allows analysts to explore an event sequence dataset, and identify promising sets of event sequences to compare at both the pattern and sequence levels. More specifically, ICE incorporates a multi-level matrix-based visualization for browsing the entire dataset based on the prefixes and suffixes of sequences. To support comparison at multiple levels, ICE employs the unit visualization technique, and we further explore the design space of unit visualizations for event sequence comparison tasks. Finally, we demonstrate the effectiveness of ICE with three real-world datasets from different domains.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Learning to Detect Head Movement in Unconstrained Remote Gaze Estimation in the Wild

Unconstrained remote gaze estimation remains challenging mostly due to its vulnerability to the large variability in head-pose. Prior solutions struggle to maintain reliable accuracy in unconstrained remote gaze tracking. Among them, appearance-based solutions demonstrate tremendous potential in improving gaze accuracy. However, existing works still suffer from head movement and are not robust enough to handle real-world scenarios. Especially most of them study gaze estimation under controlled scenarios where the collected datasets often cover limited ranges of both head-pose and gaze which introduces further bias. In this paper, we propose novel end-to-end appearance-based gaze estimation methods that could more robustly incorporate different levels of head-pose representations into gaze estimation. Our method could generalize to real-world scenarios with low image quality, different lightings and scenarios where direct head-pose information is not available. To better demonstrate the advantage of our methods, we further propose a new benchmark dataset with the most rich distribution of head-gaze combination reflecting real-world scenarios. Extensive evaluations on several public datasets and our own dataset demonstrate that our method consistently outperforms the state-of-the-art by a significant margin.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Precise pulse shaping for quantum control of strong optical transitions

Advances of quantum control technology have led to nearly perfect single-qubit control of nuclear spins and atomic hyperfine ground states. In contrast, quantum control of strong optical transitions, even for free atoms, are far from being perfect. Developments of such quantum control appears to be bottlenecked by available laser technology for generating isolated, sub-nanosecond optical waveforms with sub-THz programming bandwidth. Here we propose a simple and robust method for the desired pulse shaping, based on precisely stacking multiple delayed picosecond pulses. Our proof-of-principal demonstration leads to arbitrarily shapeable optical waveforms with 30~GHz bandwidth and $100~$ps duration. We confirm the stability of the waveforms by interfacing the pulses with laser-cooled atoms, resulting in ``super-resolved'' spectroscopic signals. This pulse shaping method may open exciting perspectives in quantum optics, and for fast laser cooling and atom interferometry with mode-locked lasers.

0 citations0 reviewsNo code linkedOpen access
preprint2019arXiv

Deep Learning Cell Imaging through Anderson Localizing Optical Fibre

We demonstrate a deep-learning-based fibre imaging system which can transfer real-time artifact-free cell images through a meter-long Anderson localizing optical fibre. The cell samples are illuminated by an incoherent LED light source. A deep convolutional neural network is applied to the image reconstruction process. The network training uses data generated by a set-up with straight fibre at room temperature (~20 °C) but can be utilized directly for high fidelity reconstruction of cell images that are transported through fibre with a few degrees bend and/or fibre with segments heated up to 50 °C. In addition, cell images located several millimeters away from the bare fibre end can be transported and recovered successfully without the assistance of any distal optics. We further evidence that the trained neural network is able to reconstruct the images of cells which are never used in the training process and feature very different morphology.

0 citations0 reviewsNo code linkedOpen access