Wenjun Zeng

Proactive Agents for Multi-Turn Text-to-Image Generation Under Uncertainty ICML 2025 UniScene: Unified Occupancy-centric Driving Scene Generation CVPR 2025 Open-World Reinforcement Learning over Long Short-Term Imagination ICLR 2025 RLLTE: Long-Term Evolution Project of Reinforcement Learning AAAI 2025 Hybrid-grained Feature Aggregation with Coarse-to-fine Language Guidance for Self-supervised Monocular Depth Estimation ICCV 2025 Perceiving and Acting in First-Person: A Dataset and Benchmark for Egocentric Human-Object-Human Interactions ICCV 2025 Disentangled World Models: Learning to Transfer Semantic Knowledge from Distracting Videos for Reinforcement Learning ICCV 2025 ULTHO: Ultra-Lightweight yet Efficient Hyperparameter Optimization in Deep Reinforcement Learning ICCV 2025 MultiConIR: Towards Multi-Condition Information Retrieval EMNLP 2025 Closed-Loop Unsupervised Representation Disentanglement with $\\beta$-VAE Distillation and Diffusion Probabilistic Feedback ECCV 2024 Making Offline RL Online: Collaborative World Models for Offline Visual Reinforcement Learning NIPS 2024 Scene Graph Disentanglement and Composition for Generalizable Complex Image Generation NIPS 2024 One at a Time: Progressive Multi-Step Volumetric Probability Learning for Reliable 3D Scene Perception AAAI 2024 HIMO: A New Benchmark for Full-Body Human Interacting with Multiple Objects ECCV 2024 Hierarchical Temporal Context Learning for Camera-based Semantic Scene Completion ECCV 2024 Graph-based Unsupervised Disentangled Representation Learning via Multimodal Large Language Models NIPS 2024 Bridging Stereo Geometry and BEV Representation with Reliable Mutual Interaction for Semantic Scene Completion IJCAI 2024 ReGenNet: Towards Human Action-Reaction Synthesis CVPR 2024 Inter-X: Towards Versatile Human-Human Interaction Analysis CVPR 2024 Rate-Distortion-Cognition Controllable Versatile Neural Image Compression ECCV 2024 ActFormer: A GAN-based Transformer towards General Action-Conditioned 3D Human Motion Generation ICCV 2023 Automatic Intrinsic Reward Shaping for Exploration in Deep Reinforcement Learning ICML 2023 NaviNeRF: NeRF-based 3D Representation Disentanglement by Latent Semantic Navigation ICCV 2023 Sparse MLP for Image Recognition: Is Self-Attention Really Necessary? AAAI 2022 When Shift Operation Meets Vision Transformer: An Extremely Simple Alternative to Attention Mechanism AAAI 2022 Lifelong Unsupervised Domain Adaptive Person Re-Identification With Coordinated Anti-Forgetting and Adaptation CVPR 2022 Correlation-Aware Deep Tracking CVPR 2022 Retriever: Learning Content-Style Representation as a Token-Level Bipartite Graph ICLR 2022 ReSTR: Convolution-Free Referring Image Segmentation Using Transformers CVPR 2022 VirtualPose: Learning Generalizable 3D Human Pose Models from Virtual Data ECCV 2022 Robust Multi-Object Tracking by Marginal Inference ECCV 2022 Towards Building A Group-based Unsupervised Representation Disentanglement Framework ICLR 2022 Learning Disentangled Representation by Exploiting Pretrained Generative Models: A Contrastive Learning View ICLR 2022 Zero-Shot Text-to-Speech for Text-Based Insertion in Audio Narration INTERSPEECH 2021 ToAlign: Task-Oriented Alignment for Unsupervised Domain Adaptation NIPS 2021 Very Important Person Localization in Unconstrained Conditions: A New Benchmark AAAI 2021 Exploiting Sample Uncertainty for Domain Adaptive Person Re-Identification AAAI 2021 S2R-DepthNet: Learning a Generalizable Depth-Specific Structural Representation CVPR 2021 Unsupervised Visual Representation Learning by Tracking Patches in Video CVPR 2021 MetaAlign: Coordinating Domain Alignment and Classification for Unsupervised Domain Adaptation CVPR 2021 An Empirical Study of the Collapsing Problem in Semi-Supervised 2D Human Pose Estimation ICCV 2021 Re-Energizing Domain Discriminator With Sample Relabeling for Adversarial Domain Adaptation ICCV 2021 Self-Supervised Visual Representations Learning by Contrastive Mask Prediction ICCV 2021 Uncertainty-Aware Few-Shot Image Classification IJCAI 2021 PlayVirtual: Augmenting Cycle-Consistent Virtual Trajectories for Reinforcement Learning NIPS 2021 Multi-Granularity Reference-Aided Attentive Feature Aggregation for Video-Based Person Re-Identification CVPR 2020 Tracking by Instance Detection: A Meta-Learning Approach CVPR 2020 Fusing Wearable IMUs With Multi-View Images for Human Pose Estimation: A Geometric Approach CVPR 2020 Relation-Aware Global Attention for Person Re-Identification CVPR 2020 Semantics-Guided Neural Networks for Efficient Skeleton-Based Human Action Recognition CVPR 2020 Style Normalization and Restitution for Generalizable Person Re-Identification CVPR 2020 Joint Time-Frequency and Time Domain Learning for Speech Enhancement IJCAI 2020 Beyond Intra-modality: A Survey of Heterogeneous Person Re-identification IJCAI 2020 Semantics-Aligned Representation Learning for Person Re-Identification AAAI 2020 Uncertainty-Aware Multi-Shot Knowledge Distillation for Image-Based Object Re-Identification AAAI 2020 PHASEN: A Phase-and-Harmonics-Aware Speech Enhancement Network AAAI 2020 Posterior-Guided Neural Architecture Search AAAI 2020 Multi-Scale Group Transformer for Long Sequence Modeling in Speech Separation IJCAI 2020 VoxelPose: Towards Multi-Camera 3D Human Pose Estimation in Wild Environment ECCV 2020 Global Distance-distributions Separation for Unsupervised Person Re-identification ECCV 2020 Spatiotemporal Fusion in 3D CNNs: A Probabilistic View CVPR 2020 SPM-Tracker: Series-Parallel Matching for Real-Time Visual Object Tracking CVPR 2019 Cross View Fusion for 3D Human Pose Estimation ICCV 2019 Unsupervised High-Resolution Depth Learning From Videos With Dual Networks ICCV 2019 Moving Indoor: Unsupervised Video Depth Learning in Challenging Environments ICCV 2019 Learning Basis Representation to Refine 3D Human Pose Estimations AAAI 2019 Detect or Track: Towards Cost-Effective Video Object Detection/Tracking AAAI 2019 Context-Reinforced Semantic Segmentation CVPR 2019 Densely Semantically Aligned Person Re-Identification CVPR 2019 Adding Attentiveness to the Neurons in Recurrent Neural Networks ECCV 2018 A Twofold Siamese Network for Real-Time Object Tracking CVPR 2018 MiCT: Mixed 3D/2D Convolutional Tube for Human Action Recognition CVPR 2018 Online Dictionary Learning for Approximate Archetypal Analysis ECCV 2018 Human Pose Estimation Using Global and Local Normalization ICCV 2017 View Adaptive Recurrent Neural Networks for High Performance Human Action Recognition From Skeleton Data ICCV 2017 High-Speed Hyperspectral Video Acquisition With a Dual-Camera Architecture CVPR 2015 A Computational Cognitive Model for Semantic Sub-Network Extraction from Natural Language Queries COLING 2012