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

Zhenyu Wu

Zhenyu Wu contributes to research discovery and scholarly infrastructure.

ResearcherAffiliation not importedOpen to collaborate
Computer VisionMachine LearningInformation RetrievalSocial and Information NetworksArtificial Intelligenceastro-ph.GAastro-ph.HEComputation and LanguageHuman-Computer InteractionMultiagent SystemsMultimediaRobotics

Trust snapshot

Quick read

Trust 21 - EmergingVerification L1Unclaimed author
16works
0followers
12topics
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

16 published item(s)

preprint2026arXiv

DINORANKCLIP: DINOv3 Distillation and Injection for Vision-Language Pretraining with High-Order Ranking Consistency

Contrastive language-image pretraining (CLIP) suffers from two structural weaknesses: the symmetric InfoNCE loss discards the relative ordering among unmatched in-batch pairs, and global pooling collapses the visual representation into a semantic bottleneck that is poorly sensitive to fine-grained local structure. RANKCLIP partially addresses the first issue with a list-wise Plackett-Luce ranking-consistency loss, but its model is strictly first-order and inherits the second weakness untouched. We propose DINORANKCLIP, a pretraining framework that addresses both jointly. Our principal contribution is injecting a frozen DINOv3 teacher into the contrastive trunk through a dual-branch lightweight student and a multi-scale fusion module with channel-spatial attention, a self-attention refiner, and a conflict-aware gate that preserves the cross-modal alignment up to first order. Complementarily, we introduce a high-order Plackett-Luce ranking model in which the per-position utility is augmented with attention-parameterised pairwise and tuple-wise transition terms; the family contains CLIP and RANKCLIP as nested zero-order and first-order special cases, and the optimal order on every benchmark is $R^*=3$. The full empirical study -- order sweep, Fine-grained Probe on five datasets, four-node Modality-Gap analysis, six-variant Fusion ablation -- fits in 72 hours on a single eight-GPU H100 node and trains entirely on Conceptual Captions 3M. DINORANKCLIP consistently outperforms CLIP, CyCLIP, ALIP, and RANKCLIP under matched compute, with the largest relative gains on the fine-grained and out-of-distribution evaluations that most directly stress local structural reasoning.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

EditEmoTalk: Controllable Speech-Driven 3D Facial Animation with Continuous Expression Editing

Speech-driven 3D facial animation aims to generate realistic and expressive facial motions directly from audio. While recent methods achieve high-quality lip synchronization, they often rely on discrete emotion categories, limiting continuous and fine-grained emotional control. We present EditEmoTalk, a controllable speech-driven 3D facial animation framework with continuous emotion editing. The key idea is a boundary-aware semantic embedding that learns the normal directions of inter-emotion decision boundaries, enabling a continuous expression manifold for smooth emotion manipulation. Moreover, we introduce an emotional consistency loss that enforces semantic alignment between the generated motion dynamics and the target emotion embedding through a mapping network, ensuring faithful emotional expression. Extensive experiments demonstrate that EditEmoTalk achieves superior controllability, expressiveness, and generalization while maintaining accurate lip synchronization. Code and pretrained models will be released.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

GenCAMO: Scene-Graph Contextual Decoupling for Environment-aware and Mask-free Camouflage Image-Dense Annotation Generation

Conceal dense prediction (CDP), especially RGB-D camouflage object detection and open-vocabulary camouflage object segmentation, plays a crucial role in advancing the understanding and reasoning of complex camouflage scenes. However, high-quality and large-scale camouflage datasets with dense annotation remain scarce due to expensive data collection and labeling costs. To address this challenge, we explore leveraging generative models to synthesize realistic camouflage image-dense data for training CDP models with fine-grained representations, prior knowledge, and auxiliary reasoning. Concretely, our contributions are threefold: (i) we introduce GenCAMO-DB, a large-scale camouflage dataset with multi-modal annotations, including depth maps, scene graphs, attribute descriptions, and text prompts; (ii) we present GenCAMO, an environment-aware and mask-free generative framework that produces high-fidelity camouflage image-dense annotations; (iii) extensive experiments across multiple modalities demonstrate that GenCAMO significantly improves dense prediction performance on complex camouflage scenes by providing high-quality synthetic data. The code and datasets will be released after paper acceptance.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

OS-Symphony: A Holistic Framework for Robust and Generalist Computer-Using Agent

While Vision-Language Models (VLMs) have significantly advanced Computer-Using Agents (CUAs), current frameworks struggle with robustness in long-horizon workflows and generalization in novel domains. These limitations stem from a lack of granular control over historical visual context curation and the absence of visual-aware tutorial retrieval. To bridge these gaps, we introduce OS-Symphony, a holistic framework that comprises an Orchestrator coordinating two key innovations for robust automation: (1) a Reflection-Memory Agent that utilizes milestone-driven long-term memory to enable trajectory-level self-correction, effectively mitigating visual context loss in long-horizon tasks; (2) Versatile Tool Agents featuring a Multimodal Searcher that adopts a SeeAct paradigm to navigate a browser-based sandbox to synthesize live, visually aligned tutorials, thereby resolving fidelity issues in unseen scenarios. Experimental results demonstrate that OS-Symphony delivers substantial performance gains across varying model scales, establishing new state-of-the-art results on three online benchmarks, notably achieving 65.84% on OSWorld.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

E^2VTS: Energy-Efficient Video Text Spotting from Unmanned Aerial Vehicles

Unmanned Aerial Vehicles (UAVs) based video text spotting has been extensively used in civil and military domains. UAV's limited battery capacity motivates us to develop an energy-efficient video text spotting solution. In this paper, we first revisit RCNN's crop & resize training strategy and empirically find that it outperforms aligned RoI sampling on a real-world video text dataset captured by UAV. To reduce energy consumption, we further propose a multi-stage image processor that takes videos' redundancy, continuity, and mixed degradation into account. Lastly, the model is pruned and quantized before deployed on Raspberry Pi. Our proposed energy-efficient video text spotting solution, dubbed as E^2VTS, outperforms all previous methods by achieving a competitive tradeoff between energy efficiency and performance. All our codes and pre-trained models are available at https://github.com/wuzhenyusjtu/LPCVC20-VideoTextSpotting.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Radiation hydrodynamics modeling of kilonovae with SNEC

We develop a method to compute synthetic kilonova light curves that combines numerical relativity simulations of neutron star mergers and the $\texttt{SNEC}$ radiation-hydrodynamics code. We describe our implementation of initial and boundary conditions, r-process heating, and opacities for kilonova simulations. We validate our approach by carefully checking that energy conservation is satisfied and by comparing the $\texttt{SNEC}$ results with those of two semi-analytic light curve models. We apply our code to the calculation of color light curves for three binaries having different mass ratios (equal and unequal mass) and different merger outcome (short-lived and long-lived remnants). We study the sensitivity of our results to hydrodynamic effects, nuclear physics uncertainties in the heating rates, and duration of the merger simulations. We find that hydrodynamics effects are typically negligible and that homologous expansion is a good approximation in most cases. However, pressure forces can amplify the impact of uncertainties in the radioactive heating rates. We also study the impact of shocks possibly launched into the outflows by a relativistic jet. None of our models match AT2017gfo, the kilonova in GW170817. This points to possible deficiencies in our merger simulations and kilonova models which neglect non-LTE effects and possible additional energy injection from the merger remnant, and to the need to go beyond the assumption of spherical symmetry adopted in this work.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Searching Extra-tidal Features around the Globular Cluster Whiting 1

Whiting 1 is a faint and young globular cluster in the halo of the Milky Way, and was suggested to have originated in the Sagittarius spherical dwarf galaxy (Sgr dSph). In this paper, we use the deep DESI Legacy Imaging Surveys to explore tentative spatial connection between Whiting 1 and the Sgr dSph. We redetermine the fundamental parameters of Whiting 1 and use the best-fitting isochrone (age $τ$=6.5 Gyr, metalicity Z=0.005 and $\rm d_{\odot}$=26.9 kpc) to construct a theoretical matched filter for the extra-tidal features searching. Without any smooth technique to the matched filter density map, we detect a round-shape feature with possible leading and trailing tails on either side of the cluster. This raw image is not totally new compared to old discoveries, but confirms that no more large-scale features can be detected under a depth of r<=22.5 mag. In our results, the whole feature stretches 0.1-0.2 degree along the orbit of Whiting 1, which gives a much larger area than the cluster core. The tails on both sides of the cluster align along the orbital direction of the Sgr dSph as well as the cluster itself, which implies that these debris are probably stripped remnants of Whiting 1 by the Milky Way.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Smart Explorer: Recognizing Objects in Dense Clutter via Interactive Exploration

Recognizing objects in dense clutter accurately plays an important role to a wide variety of robotic manipulation tasks including grasping, packing, rearranging and many others. However, conventional visual recognition models usually miss objects because of the significant occlusion among instances and causes incorrect prediction due to the visual ambiguity with the high object crowdedness. In this paper, we propose an interactive exploration framework called Smart Explorer for recognizing all objects in dense clutters. Our Smart Explorer physically interacts with the clutter to maximize the recognition performance while minimize the number of motions, where the false positives and negatives can be alleviated effectively with the optimal accuracy-efficiency trade-offs. Specifically, we first collect the multi-view RGB-D images of the clutter and reconstruct the corresponding point cloud. By aggregating the instance segmentation of RGB images across views, we acquire the instance-wise point cloud partition of the clutter through which the existed classes and the number of objects for each class are predicted. The pushing actions for effective physical interaction are generated to sizably reduce the recognition uncertainty that consists of the instance segmentation entropy and multi-view object disagreement. Therefore, the optimal accuracy-efficiency trade-off of object recognition in dense clutter is achieved via iterative instance prediction and physical interaction. Extensive experiments demonstrate that our Smart Explorer acquires promising recognition accuracy with only a few actions, which also outperforms the random pushing by a large margin.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

A Deeper Look at Salient Object Detection: Bi-stream Network with a Small Training Dataset

Compared with the conventional hand-crafted approaches, the deep learning based methods have achieved tremendous performance improvements by training exquisitely crafted fancy networks over large-scale training sets. However, do we really need large-scale training set for salient object detection (SOD)? In this paper, we provide a deeper insight into the interrelationship between the SOD performances and the training sets. To alleviate the conventional demands for large-scale training data, we provide a feasible way to construct a novel small-scale training set, which only contains 4K images. Moreover, we propose a novel bi-stream network to take full advantage of our proposed small training set, which is consisted of two feature backbones with different structures, achieving complementary semantical saliency fusion via the proposed gate control unit. To our best knowledge, this is the first attempt to use a small-scale training set to outperform state-of-the-art models which are trained on large-scale training sets; nevertheless, our method can still achieve the leading state-of-the-art performance on five benchmark datasets.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

A Heterogeneous Information Network based Cross Domain Insurance Recommendation System for Cold Start Users

Internet is changing the world, adapting to the trend of internet sales will bring revenue to traditional insurance companies. Online insurance is still in its early stages of development, where cold start problem (prospective customer) is one of the greatest challenges. In traditional e-commerce field, several cross-domain recommendation (CDR) methods have been studied to infer preferences of cold start users based on their preferences in other domains. However, these CDR methods could not be applied to insurance domain directly due to the domain specific properties. In this paper, we propose a novel framework called a Heterogeneous information network based Cross Domain Insurance Recommendation (HCDIR) system for cold start users. Specifically, we first try to learn more effective user and item latent features in both source and target domains. In source domain, we employ gated recurrent unit (GRU) to module user dynamic interests. In target domain, given the complexity of insurance products and the data sparsity problem, we construct an insurance heterogeneous information network (IHIN) based on data from PingAn Jinguanjia, the IHIN connects users, agents, insurance products and insurance product properties together, giving us richer information. Then we employ three-level (relational, node, and semantic) attention aggregations to get user and insurance product representations. After obtaining latent features of overlapping users, a feature mapping between the two domains is learned by multi-layer perceptron (MLP). We apply HCDIR on Jinguanjia dataset, and show HCDIR significantly outperforms the state-of-the-art solutions.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

DCDIR: A Deep Cross-Domain Recommendation System for Cold Start Users in Insurance Domain

Internet insurance products are apparently different from traditional e-commerce goods for their complexity, low purchasing frequency, etc.So, cold start problem is even worse. In traditional e-commerce field, several cross-domain recommendation (CDR) methods have been studied to infer preferences of cold start users based on their preferences in other domains. However, these CDR methods could not be applied into insurance domain directly due to product complexity. In this paper, we propose a Deep Cross Domain Insurance Recommendation System (DCDIR) for cold start users. Specifically, we first learn more effective user and item latent features in both domains. In target domain, given the complexity of insurance products, we design meta path based method over insurance product knowledge graph. In source domain, we employ GRU to model user dynamic interests. Then we learn a feature mapping function by multi-layer perceptions. We apply DCDIR on our company datasets, and show DCDIR significantly outperforms the state-of-the-art solutions.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

DREAM: A Dynamic Relational-Aware Model for Social Recommendation

Social connections play a vital role in improving the performance of recommendation systems (RS). However, incorporating social information into RS is challenging. Most existing models usually consider social influences in a given session, ignoring that both users preferences and their friends influences are evolving. Moreover, in real world, social relations are sparse. Modeling dynamic influences and alleviating data sparsity is of great importance. In this paper, we propose a unified framework named Dynamic RElation Aware Model (DREAM) for social recommendation, which tries to model both users dynamic interests and their friends temporal influences. Specifically, we design temporal information encoding modules, because of which user representations are updated in each session. The updated user representations are transferred to relational-GAT modules, subsequently influence the operations on social networks. In each session, to solve social relation sparsity, we utilize glove-based method to complete social network with virtual friends. Then we employ relational-GAT module over completed social networks to update users representations. In the extensive experiments on the public datasets, DREAM significantly outperforms the state-of-the-art solutions.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Recursive Multi-model Complementary Deep Fusion forRobust Salient Object Detection via Parallel Sub Networks

Fully convolutional networks have shown outstanding performance in the salient object detection (SOD) field. The state-of-the-art (SOTA) methods have a tendency to become deeper and more complex, which easily homogenize their learned deep features, resulting in a clear performance bottleneck. In sharp contrast to the conventional ``deeper&#39;&#39; schemes, this paper proposes a ``wider&#39;&#39; network architecture which consists of parallel sub networks with totally different network architectures. In this way, those deep features obtained via these two sub networks will exhibit large diversity, which will have large potential to be able to complement with each other. However, a large diversity may easily lead to the feature conflictions, thus we use the dense short-connections to enable a recursively interaction between the parallel sub networks, pursuing an optimal complementary status between multi-model deep features. Finally, all these complementary multi-model deep features will be selectively fused to make high-performance salient object detections. Extensive experiments on several famous benchmarks clearly demonstrate the superior performance, good generalization, and powerful learning ability of the proposed wider framework.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Rethinking of the Image Salient Object Detection: Object-level Semantic Saliency Re-ranking First, Pixel-wise Saliency Refinement Latter

The real human attention is an interactive activity between our visual system and our brain, using both low-level visual stimulus and high-level semantic information. Previous image salient object detection (SOD) works conduct their saliency predictions in a multi-task manner, i.e., performing pixel-wise saliency regression and segmentation-like saliency refinement at the same time, which degenerates their feature backbones in revealing semantic information. However, given an image, we tend to pay more attention to those regions which are semantically salient even in the case that these regions are perceptually not the most salient ones at first glance. In this paper, we divide the SOD problem into two sequential tasks: 1) we propose a lightweight, weakly supervised deep network to coarsely locate those semantically salient regions first; 2) then, as a post-processing procedure, we selectively fuse multiple off-the-shelf deep models on these semantically salient regions as the pixel-wise saliency refinement. In sharp contrast to the state-of-the-art (SOTA) methods that focus on learning pixel-wise saliency in &#34;single image&#34; using perceptual clues mainly, our method has investigated the &#34;object-level semantic ranks between multiple images&#34;, of which the methodology is more consistent with the real human attention mechanism. Our method is simple yet effective, which is the first attempt to consider the salient object detection mainly as an object-level semantic re-ranking problem.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Self-Supervised Joint Learning Framework of Depth Estimation via Implicit Cues

In self-supervised monocular depth estimation, the depth discontinuity and motion objects&#39; artifacts are still challenging problems. Existing self-supervised methods usually utilize a single view to train the depth estimation network. Compared with static views, abundant dynamic properties between video frames are beneficial to refined depth estimation, especially for dynamic objects. In this work, we propose a novel self-supervised joint learning framework for depth estimation using consecutive frames from monocular and stereo videos. The main idea is using an implicit depth cue extractor which leverages dynamic and static cues to generate useful depth proposals. These cues can predict distinguishable motion contours and geometric scene structures. Furthermore, a new high-dimensional attention module is introduced to extract clear global transformation, which effectively suppresses uncertainty of local descriptors in high-dimensional space, resulting in a more reliable optimization in learning framework. Experiments demonstrate that the proposed framework outperforms the state-of-the-art(SOTA) on KITTI and Make3D datasets.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

UBER-GNN: A User-Based Embeddings Recommendation based on Graph Neural Networks

The problem of session-based recommendation aims to predict user next actions based on session histories. Previous methods models session histories into sequences and estimate user latent features by RNN and GNN methods to make recommendations. However under massive-scale and complicated financial recommendation scenarios with both virtual and real commodities , such methods are not sufficient to represent accurate user latent features and neglect the long-term characteristics of users. To take long-term preference and dynamic interests into account, we propose a novel method, i.e. User-Based Embeddings Recommendation with Graph Neural Network, UBER-GNN for brevity. UBER-GNN takes advantage of structured data to generate longterm user preferences, and transfers session sequences into graphs to generate graph-based dynamic interests. The final user latent feature is then represented as the composition of the long-term preferences and the dynamic interests using attention mechanism. Extensive experiments conducted on real Ping An scenario show that UBER-GNN outperforms the state-of-the-art session-based recommendation methods.

0 citations0 reviewsNo code linkedOpen access