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

Yan Lu

Yan Lu contributes to research discovery and scholarly infrastructure.

ResearcherAffiliation not importedOpen to collaborate
Computer VisionMachine Learningeess.ASSoundMultimediaastro-ph.SRcond-mat.mes-halleess.IVArtificial Intelligencecond-mat.mtrl-sciDistributed, Parallel, and Cluster Computingeess.SYmath.OCNetworking and Internet Architecturephysics.app-phphysics.chem-phphysics.comp-phSystems and Control

Trust snapshot

Quick read

Trust 21 - EmergingVerification L1Unclaimed author
32works
0followers
18topics
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

32 published item(s)

preprint2026arXiv

Scaling Video Understanding via Compact Latent Multi-Agent Collaboration

Multi-modal large language models (MLLMs) advance vision language understanding but face inherent limitations in long-video tasks due to bounded perception context budgets. Existing agentic methods mitigate this via rule-based preprocessing, yet often suffer from information loss, high cost, and reliance on textual intermediates. We propose MACF, an end-to-end Multi-Agent Collaboration Framework that decouples per-agent perception budgets from global video complexity, enabling scalable video understanding while preserving visual fidelity. MACF partitions videos into segments for locally budgeted agents and enables holistic reasoning via an agent-native latent communication protocol. Each agent encodes partial observations into compact, task-sufficient tokens in a shared embedding space, allowing efficient and information-preserving collaboration by a central coordinator. We introduce a curriculum training strategy that progressively enforces semantic alignment, evidence summarization, and cross-agent coordination. Extensive experiments on diverse video understanding benchmarks show that MACF consistently outperforms state-of-the-art MLLMs and multi-agent systems under identical budget constraints, demonstrating the effectiveness of our latent collaboration for scalable video understanding.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

A Comprehensive Review of Digital Twin -- Part 2: Roles of Uncertainty Quantification and Optimization, a Battery Digital Twin, and Perspectives

As an emerging technology in the era of Industry 4.0, digital twin is gaining unprecedented attention because of its promise to further optimize process design, quality control, health monitoring, decision and policy making, and more, by comprehensively modeling the physical world as a group of interconnected digital models. In a two-part series of papers, we examine the fundamental role of different modeling techniques, twinning enabling technologies, and uncertainty quantification and optimization methods commonly used in digital twins. This second paper presents a literature review of key enabling technologies of digital twins, with an emphasis on uncertainty quantification, optimization methods, open source datasets and tools, major findings, challenges, and future directions. Discussions focus on current methods of uncertainty quantification and optimization and how they are applied in different dimensions of a digital twin. Additionally, this paper presents a case study where a battery digital twin is constructed and tested to illustrate some of the modeling and twinning methods reviewed in this two-part review. Code and preprocessed data for generating all the results and figures presented in the case study are available on GitHub.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Alignment-guided Temporal Attention for Video Action Recognition

Temporal modeling is crucial for various video learning tasks. Most recent approaches employ either factorized (2D+1D) or joint (3D) spatial-temporal operations to extract temporal contexts from the input frames. While the former is more efficient in computation, the latter often obtains better performance. In this paper, we attribute this to a dilemma between the sufficiency and the efficiency of interactions among various positions in different frames. These interactions affect the extraction of task-relevant information shared among frames. To resolve this issue, we prove that frame-by-frame alignments have the potential to increase the mutual information between frame representations, thereby including more task-relevant information to boost effectiveness. Then we propose Alignment-guided Temporal Attention (ATA) to extend 1-dimensional temporal attention with parameter-free patch-level alignments between neighboring frames. It can act as a general plug-in for image backbones to conduct the action recognition task without any model-specific design. Extensive experiments on multiple benchmarks demonstrate the superiority and generality of our module.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Cross-Scale Vector Quantization for Scalable Neural Speech Coding

Bitrate scalability is a desirable feature for audio coding in real-time communications. Existing neural audio codecs usually enforce a specific bitrate during training, so different models need to be trained for each target bitrate, which increases the memory footprint at the sender and the receiver side and transcoding is often needed to support multiple receivers. In this paper, we introduce a cross-scale scalable vector quantization scheme (CSVQ), in which multi-scale features are encoded progressively with stepwise feature fusion and refinement. In this way, a coarse-level signal is reconstructed if only a portion of the bitstream is received, and progressively improves the quality as more bits are available. The proposed CSVQ scheme can be flexibly applied to any neural audio coding network with a mirrored auto-encoder structure to achieve bitrate scalability. Subjective results show that the proposed scheme outperforms the classical residual VQ (RVQ) with scalability. Moreover, the proposed CSVQ at 3 kbps outperforms Opus at 9 kbps and Lyra at 3kbps and it could provide a graceful quality boost with bitrate increase.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

End-to-End Neural Speech Coding for Real-Time Communications

Deep-learning based methods have shown their advantages in audio coding over traditional ones but limited attention has been paid on real-time communications (RTC). This paper proposes the TFNet, an end-to-end neural speech codec with low latency for RTC. It takes an encoder-temporal filtering-decoder paradigm that has seldom been investigated in audio coding. An interleaved structure is proposed for temporal filtering to capture both short-term and long-term temporal dependencies. Furthermore, with end-to-end optimization, the TFNet is jointly optimized with speech enhancement and packet loss concealment, yielding a one-for-all network for three tasks. Both subjective and objective results demonstrate the efficiency of the proposed TFNet.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Hybrid Instance-aware Temporal Fusion for Online Video Instance Segmentation

Recently, transformer-based image segmentation methods have achieved notable success against previous solutions. While for video domains, how to effectively model temporal context with the attention of object instances across frames remains an open problem. In this paper, we propose an online video instance segmentation framework with a novel instance-aware temporal fusion method. We first leverages the representation, i.e., a latent code in the global context (instance code) and CNN feature maps to represent instance- and pixel-level features. Based on this representation, we introduce a cropping-free temporal fusion approach to model the temporal consistency between video frames. Specifically, we encode global instance-specific information in the instance code and build up inter-frame contextual fusion with hybrid attentions between the instance codes and CNN feature maps. Inter-frame consistency between the instance codes are further enforced with order constraints. By leveraging the learned hybrid temporal consistency, we are able to directly retrieve and maintain instance identities across frames, eliminating the complicated frame-wise instance matching in prior methods. Extensive experiments have been conducted on popular VIS datasets, i.e. Youtube-VIS-19/21. Our model achieves the best performance among all online VIS methods. Notably, our model also eclipses all offline methods when using the ResNet-50 backbone.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Hybrid Spatial-Temporal Entropy Modelling for Neural Video Compression

For neural video codec, it is critical, yet challenging, to design an efficient entropy model which can accurately predict the probability distribution of the quantized latent representation. However, most existing video codecs directly use the ready-made entropy model from image codec to encode the residual or motion, and do not fully leverage the spatial-temporal characteristics in video. To this end, this paper proposes a powerful entropy model which efficiently captures both spatial and temporal dependencies. In particular, we introduce the latent prior which exploits the correlation among the latent representation to squeeze the temporal redundancy. Meanwhile, the dual spatial prior is proposed to reduce the spatial redundancy in a parallel-friendly manner. In addition, our entropy model is also versatile. Besides estimating the probability distribution, our entropy model also generates the quantization step at spatial-channel-wise. This content-adaptive quantization mechanism not only helps our codec achieve the smooth rate adjustment in single model but also improves the final rate-distortion performance by dynamic bit allocation. Experimental results show that, powered by the proposed entropy model, our neural codec can achieve 18.2% bitrate saving on UVG dataset when compared with H.266 (VTM) using the highest compression ratio configuration. It makes a new milestone in the development of neural video codec. The codes are at https://github.com/microsoft/DCVC.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Multi-Modal Multi-Correlation Learning for Audio-Visual Speech Separation

In this paper we propose a multi-modal multi-correlation learning framework targeting at the task of audio-visual speech separation. Although previous efforts have been extensively put on combining audio and visual modalities, most of them solely adopt a straightforward concatenation of audio and visual features. To exploit the real useful information behind these two modalities, we define two key correlations which are: (1) identity correlation (between timbre and facial attributes); (2) phonetic correlation (between phoneme and lip motion). These two correlations together comprise the complete information, which shows a certain superiority in separating target speaker's voice especially in some hard cases, such as the same gender or similar content. For implementation, contrastive learning or adversarial training approach is applied to maximize these two correlations. Both of them work well, while adversarial training shows its advantage by avoiding some limitations of contrastive learning. Compared with previous research, our solution demonstrates clear improvement on experimental metrics without additional complexity. Further analysis reveals the validity of the proposed architecture and its good potential for future extension.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Neighbor Correspondence Matching for Flow-based Video Frame Synthesis

Video frame synthesis, which consists of interpolation and extrapolation, is an essential video processing technique that can be applied to various scenarios. However, most existing methods cannot handle small objects or large motion well, especially in high-resolution videos such as 4K videos. To eliminate such limitations, we introduce a neighbor correspondence matching (NCM) algorithm for flow-based frame synthesis. Since the current frame is not available in video frame synthesis, NCM is performed in a current-frame-agnostic fashion to establish multi-scale correspondences in the spatial-temporal neighborhoods of each pixel. Based on the powerful motion representation capability of NCM, we further propose to estimate intermediate flows for frame synthesis in a heterogeneous coarse-to-fine scheme. Specifically, the coarse-scale module is designed to leverage neighbor correspondences to capture large motion, while the fine-scale module is more computationally efficient to speed up the estimation process. Both modules are trained progressively to eliminate the resolution gap between training dataset and real-world videos. Experimental results show that NCM achieves state-of-the-art performance on several benchmarks. In addition, NCM can be applied to various practical scenarios such as video compression to achieve better performance.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Neural Capture of Animatable 3D Human from Monocular Video

We present a novel paradigm of building an animatable 3D human representation from a monocular video input, such that it can be rendered in any unseen poses and views. Our method is based on a dynamic Neural Radiance Field (NeRF) rigged by a mesh-based parametric 3D human model serving as a geometry proxy. Previous methods usually rely on multi-view videos or accurate 3D geometry information as additional inputs; besides, most methods suffer from degraded quality when generalized to unseen poses. We identify that the key to generalization is a good input embedding for querying dynamic NeRF: A good input embedding should define an injective mapping in the full volumetric space, guided by surface mesh deformation under pose variation. Based on this observation, we propose to embed the input query with its relationship to local surface regions spanned by a set of geodesic nearest neighbors on mesh vertices. By including both position and relative distance information, our embedding defines a distance-preserved deformation mapping and generalizes well to unseen poses. To reduce the dependency on additional inputs, we first initialize per-frame 3D meshes using off-the-shelf tools and then propose a pipeline to jointly optimize NeRF and refine the initial mesh. Extensive experiments show our method can synthesize plausible human rendering results under unseen poses and views.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Neural Compression-Based Feature Learning for Video Restoration

How to efficiently utilize the temporal features is crucial, yet challenging, for video restoration. The temporal features usually contain various noisy and uncorrelated information, and they may interfere with the restoration of the current frame. This paper proposes learning noise-robust feature representations to help video restoration. We are inspired by that the neural codec is a natural denoiser. In neural codec, the noisy and uncorrelated contents which are hard to predict but cost lots of bits are more inclined to be discarded for bitrate saving. Therefore, we design a neural compression module to filter the noise and keep the most useful information in features for video restoration. To achieve robustness to noise, our compression module adopts a spatial channel-wise quantization mechanism to adaptively determine the quantization step size for each position in the latent. Experiments show that our method can significantly boost the performance on video denoising, where we obtain 0.13 dB improvement over BasicVSR++ with only 0.23x FLOPs. Meanwhile, our method also obtains SOTA results on video deraining and dehazing.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Online Video Instance Segmentation via Robust Context Fusion

Video instance segmentation (VIS) aims at classifying, segmenting and tracking object instances in video sequences. Recent transformer-based neural networks have demonstrated their powerful capability of modeling spatio-temporal correlations for the VIS task. Relying on video- or clip-level input, they suffer from high latency and computational cost. We propose a robust context fusion network to tackle VIS in an online fashion, which predicts instance segmentation frame-by-frame with a few preceding frames. To acquire the precise and temporal-consistent prediction for each frame efficiently, the key idea is to fuse effective and compact context from reference frames into the target frame. Considering the different effects of reference and target frames on the target prediction, we first summarize contextual features through importance-aware compression. A transformer encoder is adopted to fuse the compressed context. Then, we leverage an order-preserving instance embedding to convey the identity-aware information and correspond the identities to predicted instance masks. We demonstrate that our robust fusion network achieves the best performance among existing online VIS methods and is even better than previously published clip-level methods on the Youtube-VIS 2019 and 2021 benchmarks. In addition, visual objects often have acoustic signatures that are naturally synchronized with them in audio-bearing video recordings. By leveraging the flexibility of our context fusion network on multi-modal data, we further investigate the influence of audios on the video-dense prediction task, which has never been discussed in existing works. We build up an Audio-Visual Instance Segmentation dataset, and demonstrate that acoustic signals in the wild scenarios could benefit the VIS task.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Recursive Least-Squares Estimator-Aided Online Learning for Visual Tracking

Tracking visual objects from a single initial exemplar in the testing phase has been broadly cast as a one-/few-shot problem, i.e., one-shot learning for initial adaptation and few-shot learning for online adaptation. The recent few-shot online adaptation methods incorporate the prior knowledge from large amounts of annotated training data via complex meta-learning optimization in the offline phase. This helps the online deep trackers to achieve fast adaptation and reduce overfitting risk in tracking. In this paper, we propose a simple yet effective recursive least-squares estimator-aided online learning approach for few-shot online adaptation without requiring offline training. It allows an in-built memory retention mechanism for the model to remember the knowledge about the object seen before, and thus the seen data can be safely removed from training. This also bears certain similarities to the emerging continual learning field in preventing catastrophic forgetting. This mechanism enables us to unveil the power of modern online deep trackers without incurring too much extra computational cost. We evaluate our approach based on two networks in the online learning families for tracking, i.e., multi-layer perceptrons in RT-MDNet and convolutional neural networks in DiMP. The consistent improvements on several challenging tracking benchmarks demonstrate its effectiveness and efficiency.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Rethinking Minimal Sufficient Representation in Contrastive Learning

Contrastive learning between different views of the data achieves outstanding success in the field of self-supervised representation learning and the learned representations are useful in broad downstream tasks. Since all supervision information for one view comes from the other view, contrastive learning approximately obtains the minimal sufficient representation which contains the shared information and eliminates the non-shared information between views. Considering the diversity of the downstream tasks, it cannot be guaranteed that all task-relevant information is shared between views. Therefore, we assume the non-shared task-relevant information cannot be ignored and theoretically prove that the minimal sufficient representation in contrastive learning is not sufficient for the downstream tasks, which causes performance degradation. This reveals a new problem that the contrastive learning models have the risk of over-fitting to the shared information between views. To alleviate this problem, we propose to increase the mutual information between the representation and input as regularization to approximately introduce more task-relevant information, since we cannot utilize any downstream task information during training. Extensive experiments verify the rationality of our analysis and the effectiveness of our method. It significantly improves the performance of several classic contrastive learning models in downstream tasks. Our code is available at https://github.com/Haoqing-Wang/InfoCL.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Robust Nonparametric Distribution Forecast with Backtest-based Bootstrap and Adaptive Residual Selection

Distribution forecast can quantify forecast uncertainty and provide various forecast scenarios with their corresponding estimated probabilities. Accurate distribution forecast is crucial for planning - for example when making production capacity or inventory allocation decisions. We propose a practical and robust distribution forecast framework that relies on backtest-based bootstrap and adaptive residual selection. The proposed approach is robust to the choice of the underlying forecasting model, accounts for uncertainty around the input covariates, and relaxes the independence between residuals and covariates assumption. It reduces the Absolute Coverage Error by more than 63% compared to the classic bootstrap approaches and by 2% - 32% compared to a variety of State-of-the-Art deep learning approaches on in-house product sales data and M4-hourly competition data.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Self-Supervised Image Representation Learning with Geometric Set Consistency

We propose a method for self-supervised image representation learning under the guidance of 3D geometric consistency. Our intuition is that 3D geometric consistency priors such as smooth regions and surface discontinuities may imply consistent semantics or object boundaries, and can act as strong cues to guide the learning of 2D image representations without semantic labels. Specifically, we introduce 3D geometric consistency into a contrastive learning framework to enforce the feature consistency within image views. We propose to use geometric consistency sets as constraints and adapt the InfoNCE loss accordingly. We show that our learned image representations are general. By fine-tuning our pre-trained representations for various 2D image-based downstream tasks, including semantic segmentation, object detection, and instance segmentation on real-world indoor scene datasets, we achieve superior performance compared with state-of-the-art methods.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Semantic-aligned Fusion Transformer for One-shot Object Detection

One-shot object detection aims at detecting novel objects according to merely one given instance. With extreme data scarcity, current approaches explore various feature fusions to obtain directly transferable meta-knowledge. Yet, their performances are often unsatisfactory. In this paper, we attribute this to inappropriate correlation methods that misalign query-support semantics by overlooking spatial structures and scale variances. Upon analysis, we leverage the attention mechanism and propose a simple but effective architecture named Semantic-aligned Fusion Transformer (SaFT) to resolve these issues. Specifically, we equip SaFT with a vertical fusion module (VFM) for cross-scale semantic enhancement and a horizontal fusion module (HFM) for cross-sample feature fusion. Together, they broaden the vision for each feature point from the support to a whole augmented feature pyramid from the query, facilitating semantic-aligned associations. Extensive experiments on multiple benchmarks demonstrate the superiority of our framework. Without fine-tuning on novel classes, it brings significant performance gains to one-stage baselines, lifting state-of-the-art results to a higher level.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Test-time Batch Normalization

Deep neural networks often suffer the data distribution shift between training and testing, and the batch statistics are observed to reflect the shift. In this paper, targeting of alleviating distribution shift in test time, we revisit the batch normalization (BN) in the training process and reveals two key insights benefiting test-time optimization: $(i)$ preserving the same gradient backpropagation form as training, and $(ii)$ using dataset-level statistics for robust optimization and inference. Based on the two insights, we propose a novel test-time BN layer design, GpreBN, which is optimized during testing by minimizing Entropy loss. We verify the effectiveness of our method on two typical settings with distribution shift, i.e., domain generalization and robustness tasks. Our GpreBN significantly improves the test-time performance and achieves the state of the art results.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Towards Error-Resilient Neural Speech Coding

Neural audio coding has shown very promising results recently in the literature to largely outperform traditional codecs but limited attention has been paid on its error resilience. Neural codecs trained considering only source coding tend to be extremely sensitive to channel noises, especially in wireless channels with high error rate. In this paper, we investigate how to elevate the error resilience of neural audio codecs for packet losses that often occur during real-time communications. We propose a feature-domain packet loss concealment algorithm (FD-PLC) for real-time neural speech coding. Specifically, we introduce a self-attention-based module on the received latent features to recover lost frames in the feature domain before the decoder. A hybrid segment-level and frame-level frequency-domain discriminator is employed to guide the network to focus on both the generative quality of lost frames and the continuity with neighbouring frames. Experimental results on several error patterns show that the proposed scheme can achieve better robustness compared with the corresponding error-free and error-resilient baselines. We also show that feature-domain concealment is superior to waveform-domain counterpart as post-processing.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Towards Robust Video Object Segmentation with Adaptive Object Calibration

In the booming video era, video segmentation attracts increasing research attention in the multimedia community. Semi-supervised video object segmentation (VOS) aims at segmenting objects in all target frames of a video, given annotated object masks of reference frames. Most existing methods build pixel-wise reference-target correlations and then perform pixel-wise tracking to obtain target masks. Due to neglecting object-level cues, pixel-level approaches make the tracking vulnerable to perturbations, and even indiscriminate among similar objects. Towards robust VOS, the key insight is to calibrate the representation and mask of each specific object to be expressive and discriminative. Accordingly, we propose a new deep network, which can adaptively construct object representations and calibrate object masks to achieve stronger robustness. First, we construct the object representations by applying an adaptive object proxy (AOP) aggregation method, where the proxies represent arbitrary-shaped segments at multi-levels for reference. Then, prototype masks are initially generated from the reference-target correlations based on AOP. Afterwards, such proto-masks are further calibrated through network modulation, conditioning on the object proxy representations. We consolidate this conditional mask calibration process in a progressive manner, where the object representations and proto-masks evolve to be discriminative iteratively. Extensive experiments are conducted on the standard VOS benchmarks, YouTube-VOS-18/19 and DAVIS-17. Our model achieves the state-of-the-art performance among existing published works, and also exhibits superior robustness against perturbations. Our project repo is at https://github.com/JerryX1110/Robust-Video-Object-Segmentation

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Turbo: Opportunistic Enhancement for Edge Video Analytics

Edge computing is being widely used for video analytics. To alleviate the inherent tension between accuracy and cost, various video analytics pipelines have been proposed to optimize the usage of GPU on edge nodes. Nonetheless, we find that GPU compute resources provisioned for edge nodes are commonly under-utilized due to video content variations, subsampling and filtering at different places of a pipeline. As opposed to model and pipeline optimization, in this work, we study the problem of opportunistic data enhancement using the non-deterministic and fragmented idle GPU resources. In specific, we propose a task-specific discrimination and enhancement module and a model-aware adversarial training mechanism, providing a way to identify and transform low-quality images that are specific to a video pipeline in an accurate and efficient manner. A multi-exit model structure and a resource-aware scheduler is further developed to make online enhancement decisions and fine-grained inference execution under latency and GPU resource constraints. Experiments across multiple video analytics pipelines and datasets reveal that by judiciously allocating a small amount of idle resources on frames that tend to yield greater marginal benefits from enhancement, our system boosts DNN object detection accuracy by $7.3-11.3\%$ without incurring any latency costs.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

A catalog of early-type Hα emission line stars and 58 newly confirmed Herbig Ae/Bes from LAMOST DR7

We derive a catalog of early-type emission-line stars including 30,048 spectra of 25,886 stars from LAMOST DR7, in which 3,922 have Simbad records. The sample is obtained using K-Nearest Neighbor and Random Forest methods and visually inspected. The spectra are classified into 3 morphological types (10 subtypes) based on H$α$ emission line profiles. Some spectra contaminated by nebula emission lines such as from HII regions are flagged in the catalog. We also provide a specific sub-catalog of 101 stars with the stellar wind by calculating stellar wind or accretion flow velocities based on P Cygni or inverse P Cygni profiles, in which 74\% of them having velocities below 400km/s. More important, with two color-color diagrams (H-K, K- W1) and (H-K, J-H) of a collection of known Herbig Ae/Be stars (HAeBes) and classical Ae/Be stars (CAeBes), we propose an updated criterion to separate HAeBes from CAeBes. By the criterion, we select 201 HAeBes candidates and 5,547 CAeBes candidates from the sample. We confirmed 66 of the 201 HAeBes by using both WISE images and LAMOST spectra and present a specific HAeBe sub-catalog, in which 58 are newly identified. In addition, the WISE colors (W1-W2, W1- W3, and W1-W4) show the distribution consistency between our confirmed HAeBes and that of the known HAeBes. Most of the 66 confirmed HAeBes locate in the lower edge of the main sequence of hot end in the HR diagram, while the distances of about 77\% exceed 1Kpc, which enlarges the number of far distant known HAeBes.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

Custom Object Detection via Multi-Camera Self-Supervised Learning

This paper proposes MCSSL, a self-supervised learning approach for building custom object detection models in multi-camera networks. MCSSL associates bounding boxes between cameras with overlapping fields of view by leveraging epipolar geometry and state-of-the-art tracking and reID algorithms, and prudently generates two sets of pseudo-labels to fine-tune backbone and detection networks respectively in an object detection model. To train effectively on pseudo-labels,a powerful reID-like pretext task with consistency loss is constructed for model customization. Our evaluation shows that compared with legacy selftraining methods, MCSSL improves average mAP by 5.44% and 6.76% on WildTrack and CityFlow dataset, respectively.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Artificial Multiferroics and Enhanced Magnetoelectric Effect in van der Waals Heterostructures

Multiferroic materials with coupled ferroelectric and ferromagnetic properties are important for multifunctional devices due to their potential ability of controlling magnetism via electric field, and vice versa. The recent discoveries of two-dimensional ferromagnetic and ferroelectric materials have ignited tremendous research interest and aroused hope to search for two-dimensional multiferroics. However, intrinsic two-dimensional multiferroic materials and, particularly, those with strong magnetoelectric couplings are still rare to date. In this paper, using first-principles simulations, we propose artificial two-dimensional multiferroics via a van der Waals heterostructure formed by ferromagnetic bilayer chromium triiodide (CrI3) and ferroelectric monolayer Sc2CO2. In addition to the coexistence of ferromagnetism and ferroelectricity, our calculations show that, by switching the electric polarization of Sc2CO2, we can tune the interlayer magnetic couplings of bilayer CrI3 between ferromagnetic and antiferromagnetic states. We further reveal that such a strong magnetoelectric effect is from a dramatic change of the band alignment induced by the strong build-in electric polarization in Sc2CO2 and the subsequent change of the interlayer magnetic coupling of bilayer CrI3. These artificial multiferroics and enhanced magnetoelectric effect give rise to realizing multifunctional nanoelectronics by van der Waals heterostructures.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Cross-modality Person re-identification with Shared-Specific Feature Transfer

Cross-modality person re-identification (cm-ReID) is a challenging but key technology for intelligent video analysis. Existing works mainly focus on learning common representation by embedding different modalities into a same feature space. However, only learning the common characteristics means great information loss, lowering the upper bound of feature distinctiveness. In this paper, we tackle the above limitation by proposing a novel cross-modality shared-specific feature transfer algorithm (termed cm-SSFT) to explore the potential of both the modality-shared information and the modality-specific characteristics to boost the re-identification performance. We model the affinities of different modality samples according to the shared features and then transfer both shared and specific features among and across modalities. We also propose a complementary feature learning strategy including modality adaption, project adversarial learning and reconstruction enhancement to learn discriminative and complementary shared and specific features of each modality, respectively. The entire cm-SSFT algorithm can be trained in an end-to-end manner. We conducted comprehensive experiments to validate the superiority of the overall algorithm and the effectiveness of each component. The proposed algorithm significantly outperforms state-of-the-arts by 22.5% and 19.3% mAP on the two mainstream benchmark datasets SYSU-MM01 and RegDB, respectively.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Double Dirac Cones and Topologically Non-Trivial Phonons for Continuous, Square Symmetric (C$_{4v}$ and C$_{2v}$) Unit Cells

Because phononic topological insulators have primarily been studied in discrete, graphene-like structures with C$_{6}$ or C$_{3}$ hexagonal symmetry, an open question is how to systematically achieve double Dirac cones and topologically non-trivial structures using continuous, non-hexagonal unit cells. Here, we address this challenge by presenting a novel computational methodology for the inverse design of continuous two-dimensional square phononic metamaterials exhibiting C$_{4v}$ and C$_{2v}$ symmetry. This leads to the systematic design of square unit cell topologies exhibiting a double Dirac degeneracy, which enables topologically-protected interface propagation based on the quantum spin Hall effect (QSHE). Numerical simulations prove that helical edge states emerge at the interface between two topologically distinct square phononic metamaterials, which opens the possibility of QSHE-based pseudospin-dependent transport beyond hexagonal lattices.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Enhanced Catalytic Activity of Gold@Polydopamine Nanoreactors with Multi-compartment Structure Under NIR Irradiation

Photothermal conversion (PTC) nanostructures have great potential for applications in many fields, and therefore, they have attracted tremendous attention. However, the construction of a PTC nanoreactor with multi-compartment structure to achieve the combination of unique chemical properties and structural feature is still challenging due to the synthetic difficulties. Herein, we designed and synthesized a catalytically active, PTC gold (Au)@polydopamine (PDA) nanoreactor driven by infrared irradiation using assembled PS-b-P2VP nanosphere as soft template. The particles exhibit multi-compartment structure which is revealed by 3D electron tomography characterization technique. They feature permeable shells with tunable shell thickness. Full kinetics for the reduction reaction of 4-nitrophenol has been investigated using these particles as nanoreactors and compared with other reported systems. Notably, a remarkable acceleration of the catalytic reaction upon near-infrared irradiation is demonstrated, which reveals for the first time the importance of the synergistic effect of photothermal conversion and complex inner structure to the kinetics of the catalytic reduction. The ease of synthesis and fresh insights into catalysis will promote a new platform for novel nanoreactor studies.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

M Subdwarf Research. II. Atmospheric Parameters and Kinematics

Applying the revised M subdwarf classification criteria discussed in Paper I to LAMOST DR7, combining the M subdwarf sample from Savcheva et al, a new M subdwarf sample was constructed for further study. The atmospheric parameters for each object were derived fitting with the PHOENIX grid, combining with Gaia DR2, the relationship between the gravity and metallicity were explored according to the locus both in the color-absolute magnitude diagram and the reduced proper motion diagram. Objects that have both the largest gravity and the lowest metallicity are located away from the main-sequence cloud and may be considered as the intrinsic M subdwarfs, which can be classified as luminosity class VI. Another group of objects whose spectra show typical M subdwarf characters have lower gravity and relatively moderate metal deficiency and occupy part of the ordinary M dwarf region in both diagrams. The Galactic U , V , W space velocity components and their dispersion show that the local Galactic halo population sampled in the solar neighborhood is represented by objects of high gravity and an inconspicuous bimodal metallicity distribution, with a fraction of prograde orbits. The other M subdwarfs seem to partly belong to the thick disk component with a significant fraction of thin disk moderately metal-poor objects intricately mixed with them. However, the selection effects, especially the favored anti-center direction of investigation in the LAMOST sub-sample, but also contamination by multiplicity and parameter coupling could play important roles and need to be further investigated.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

MonoGRNet: A Geometric Reasoning Network for Monocular 3D Object Localization

Detecting and localizing objects in the real 3D space, which plays a crucial role in scene understanding, is particularly challenging given only a single RGB image due to the geometric information loss during imagery projection. We propose MonoGRNet for the amodal 3D object detection from a monocular RGB image via geometric reasoning in both the observed 2D projection and the unobserved depth dimension. MonoGRNet is a single, unified network composed of four task-specific subnetworks, responsible for 2D object detection, instance depth estimation (IDE), 3D localization and local corner regression. Unlike the pixel-level depth estimation that needs per-pixel annotations, we propose a novel IDE method that directly predicts the depth of the targeting 3D bounding box's center using sparse supervision. The 3D localization is further achieved by estimating the position in the horizontal and vertical dimensions. Finally, MonoGRNet is jointly learned by optimizing the locations and poses of the 3D bounding boxes in the global context. We demonstrate that MonoGRNet achieves state-of-the-art performance on challenging datasets.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Scattering under Linear Non Self-Adjoint Operators: Case of in-Plane Elastic Waves

In this paper, we consider the problem of the scattering of in-plane waves at an interface between a homogeneous medium and a metamaterial. The relevant eigenmodes in the two regions are calculated by solving a recently described non self-adjoint eigenvalue problem particularly suited to scattering studies. The method efficiently produces all propagating and evanescent modes consistent with the application of Snell's law and is applicable to very general scattering problems. In a model composite, we elucidate the emergence of a rich spectrum of eigenvalue degeneracies. These degeneracies appear in both the complex and real domains of the wave-vector. However, since this problem is non self-adjoint, these degeneracies generally represent a coalescing of both the eigenvalues and eigenvectors (exceptional points). Through explicit calculations of Poynting vector, we point out an intriguing phenomenon: there always appears to be an abrupt change in the sign of the refraction angle of the wave on two sides of an exceptional point. Furthermore, the presence of these degeneracies, in some cases, hints at fast changes in the scattered field as the incident angle is changed by small amounts. We calculate these scattered fields through a novel application of the Betti-Rayleigh reciprocity theorem. We present several numerical examples showing a rich scattering spectrum. In one particularly intriguing example, we point out wave behavior which may be related to the phenomenon of resonance trapping. We also show that there exists a deep connection between energy flux conservation and the biorthogonality relationship of the non self-adjoint problem. The proof applies to the general class of scattering problems involving elastic waves (under self-adjoint or non self-adjoint operators).

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

WatchDog: Real-time Vehicle Tracking on Geo-distributed Edge Nodes

Vehicle tracking, a core application to smart city video analytics, is becoming more widely deployed than ever before thanks to the increasing number of traffic cameras and recent advances of computer vision and machine learning. Due to the constraints of bandwidth, latency, and privacy concerns, tracking tasks are more preferable to run on edge devices sitting close to the cameras. However, edge devices are provisioned with a fixed amount of compute budget, making them incompetent to adapt to time-varying tracking workloads caused by traffic dynamics. In coping with this challenge, we propose WatchDog, a real-time vehicle tracking system fully utilizes edge nodes across the road network. WatchDog leverages computer vision tasks with different resource-accuracy trade-offs, and decompose and schedule tracking tasks judiciously across edge devices based on the current workload to maximize the number of tasks while ensuring a provable response time bound at each edge device. Extensive evaluations have been conducted using real-world city-wide vehicle trajectory datasets, showing a 100% tracking coverage with real-time guarantee.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Weakly Supervised 3D Object Detection from Point Clouds

A crucial task in scene understanding is 3D object detection, which aims to detect and localize the 3D bounding boxes of objects belonging to specific classes. Existing 3D object detectors heavily rely on annotated 3D bounding boxes during training, while these annotations could be expensive to obtain and only accessible in limited scenarios. Weakly supervised learning is a promising approach to reducing the annotation requirement, but existing weakly supervised object detectors are mostly for 2D detection rather than 3D. In this work, we propose VS3D, a framework for weakly supervised 3D object detection from point clouds without using any ground truth 3D bounding box for training. First, we introduce an unsupervised 3D proposal module that generates object proposals by leveraging normalized point cloud densities. Second, we present a cross-modal knowledge distillation strategy, where a convolutional neural network learns to predict the final results from the 3D object proposals by querying a teacher network pretrained on image datasets. Comprehensive experiments on the challenging KITTI dataset demonstrate the superior performance of our VS3D in diverse evaluation settings. The source code and pretrained models are publicly available at https://github.com/Zengyi-Qin/Weakly-Supervised-3D-Object-Detection.

0 citations0 reviewsNo code linkedOpen access