Wei Wu

Diffusion Guided Chain-of-Vision for Large Autoregressive Vision Models CVPR 2026 Benchmarking Large Vision-Language Models via Directed Scene Graph for Comprehensive Image Captioning CVPR 2025 DriveScape: High-Resolution Driving Video Generation by Multi-View Feature Fusion CVPR 2025 FreqPDE: Rethinking Positional Depth Embedding for Multi-View 3D Object Detection Transformers ICCV 2025 GeoFormer: Geometry Point Encoder for 3D Object Detection with Graph-based Transformer ICCV 2025 InstaDrive: Instance-Aware Driving World Models for Realistic and Consistent Video Generation ICCV 2025 Learning Visual Generative Priors without Text CVPR 2025 RoboSense: Large-scale Dataset and Benchmark for Egocentric Robot Perception and Navigation in Crowded and Unstructured Environments CVPR 2025 UniMamba: Unified Spatial-Channel Representation Learning with Group-Efficient Mamba for LiDAR-based 3D Object Detection CVPR 2025 HoloVIC: Large-scale Dataset and Benchmark for Multi-Sensor Holographic Intersection and Vehicle-Infrastructure Cooperative CVPR 2024 Language-Image Pre-training with Long Captions ECCV 2024 LoTLIP: Improving Language-Image Pre-training for Long Text Understanding NeurIPS 2024 SMART: Scalable Multi-agent Real-time Motion Generation via Next-token Prediction NeurIPS 2024 SwiftPillars: High-Efficiency Pillar Encoder for Lidar-Based 3D Detection AAAI 2024 ActFormer: A GAN-based Transformer towards General Action-Conditioned 3D Human Motion Generation ICCV 2023 Regularized Mask Tuning: Uncovering Hidden Knowledge in Pre-Trained Vision-Language Models ICCV 2023 Backbone Is All Your Need: A Simplified Architecture for Visual Object Tracking ECCV 2022 Cross Domain Object Detection by Target-Perceived Dual Branch Distillation CVPR 2022 L-Tracing: Fast Light Visibility Estimation on Neural Surfaces by Sphere Tracing ECCV 2022 Learning Video Representations of Human Motion From Synthetic Data CVPR 2022 Target-Relevant Knowledge Preservation for Multi-Source Domain Adaptive Object Detection CVPR 2022 Temporal Complementarity-Guided Reinforcement Learning for Image-to-Video Person Re-Identification CVPR 2022 Unsupervised Learning of Accurate Siamese Tracking CVPR 2022 BSN++: Complementary Boundary Regressor with Scale-Balanced Relation Modeling for Temporal Action Proposal Generation AAAI 2021 Context-Aware Graph Convolution Network for Target Re-identification AAAI 2021 Learning Statistical Texture for Semantic Segmentation CVPR 2021 Spatial-Temporal Correlation and Topology Learning for Person Re-Identification in Videos CVPR 2021 Temporal Context Aggregation Network for Temporal Action Proposal Refinement CVPR 2021 Adaptive Dilated Network With Self-Correction Supervision for Counting CVPR 2020 Class-wise Dynamic Graph Convolution for Semantic Segmentation ECCV 2020 Computation Reallocation for Object Detection ICLR 2020 Hierarchical Feature Embedding for Attribute Recognition CVPR 2020 Improving One-Shot NAS by Suppressing the Posterior Fading CVPR 2020 AM-LFS: AutoML for Loss Function Search ICCV 2019 Dynamic Curriculum Learning for Imbalanced Data Classification ICCV 2019 IRLAS: Inverse Reinforcement Learning for Architecture Search CVPR 2019 Online Hyper-Parameter Learning for Auto-Augmentation Strategy ICCV 2019 STM: SpatioTemporal and Motion Encoding for Action Recognition ICCV 2019 SiamRPN++: Evolution of Siamese Visual Tracking With Very Deep Networks CVPR 2019 Distractor-aware Siamese Networks for Visual Object Tracking ECCV 2018 End-to-End Flow Correlation Tracking With Spatial-Temporal Attention CVPR 2018 High Performance Visual Tracking With Siamese Region Proposal Network CVPR 2018 Practical Block-Wise Neural Network Architecture Generation CVPR 2018