Gaoang Wang

papers

986

total citations

papers (15)

MovieChat: From Dense Token to Sparse Memory for Long Video Understanding

CVPR 2024arXiv

471

citations

StableVideo: Text-driven Consistency-aware Diffusion Video Editing

ICCV 2023arXiv

207

citations

Track Without Appearance: Learn Box and Tracklet Embedding With Local and Global Motion Patterns for Vehicle Tracking

ICCV 2021arXiv

citations

Language Adaptive Weight Generation for Multi-Task Visual Grounding

CVPR 2023arXiv

citations

Bridging Cross-task Protocol Inconsistency for Distillation in Dense Object Detection

ICCV 2023arXiv

citations

MedM2G: Unifying Medical Multi-Modal Generation via Cross-Guided Diffusion with Visual Invariant

CVPR 2024arXiv

citations

Global Adaptation Meets Local Generalization: Unsupervised Domain Adaptation for 3D Human Pose Estimation

ICCV 2023arXiv

citations

BEVSpread: Spread Voxel Pooling for Bird’s-Eye-View Representation in Vision-based Roadside 3D Object Detection

CVPR 2024arXiv

citations

Hierarchical Semi-Supervised Contrastive Learning for Contamination-Resistant Anomaly Detection

ECCV 2022arXiv

citations

Multi-Step Denoising Scheduled Sampling: Towards Alleviating Exposure Bias for Diffusion Models

AAAI 2024

citations

Frame Order Matters: A Temporal Sequence-Aware Model for Few-Shot Action Recognition

AAAI 2025arXiv

citations

Efficient Logit-based Knowledge Distillation of Deep Spiking Neural Networks for Full-Range Timestep Deployment

ICML 2025arXiv

citations

Gaoang Wang

papers (15)

MovieChat: From Dense Token to Sparse Memory for Long Video Understanding

StableVideo: Text-driven Consistency-aware Diffusion Video Editing

Track Without Appearance: Learn Box and Tracklet Embedding With Local and Global Motion Patterns for Vehicle Tracking

Language Adaptive Weight Generation for Multi-Task Visual Grounding

Bridging Cross-task Protocol Inconsistency for Distillation in Dense Object Detection

MedM2G: Unifying Medical Multi-Modal Generation via Cross-Guided Diffusion with Visual Invariant

Global Adaptation Meets Local Generalization: Unsupervised Domain Adaptation for 3D Human Pose Estimation

BEVSpread: Spread Voxel Pooling for Bird’s-Eye-View Representation in Vision-based Roadside 3D Object Detection

Hierarchical Semi-Supervised Contrastive Learning for Contamination-Resistant Anomaly Detection

Multi-Step Denoising Scheduled Sampling: Towards Alleviating Exposure Bias for Diffusion Models

Frame Order Matters: A Temporal Sequence-Aware Model for Few-Shot Action Recognition

UniAP: Towards Universal Animal Perception in Vision via Few-Shot Learning

Bringing RNNs Back to Efficient Open-Ended Video Understanding

AniMo: Species-Aware Model for Text-Driven Animal Motion Generation

Efficient Logit-based Knowledge Distillation of Deep Spiking Neural Networks for Full-Range Timestep Deployment

papers (15)

MovieChat: From Dense Token to Sparse Memory for Long Video Understanding

StableVideo: Text-driven Consistency-aware Diffusion Video Editing

Track Without Appearance: Learn Box and Tracklet Embedding With Local and Global Motion Patterns for Vehicle Tracking

Language Adaptive Weight Generation for Multi-Task Visual Grounding

Bridging Cross-task Protocol Inconsistency for Distillation in Dense Object Detection

MedM2G: Unifying Medical Multi-Modal Generation via Cross-Guided Diffusion with Visual Invariant

Global Adaptation Meets Local Generalization: Unsupervised Domain Adaptation for 3D Human Pose Estimation

BEVSpread: Spread Voxel Pooling for Bird’s-Eye-View Representation in Vision-based Roadside 3D Object Detection

Hierarchical Semi-Supervised Contrastive Learning for Contamination-Resistant Anomaly Detection

Multi-Step Denoising Scheduled Sampling: Towards Alleviating Exposure Bias for Diffusion Models

Frame Order Matters: A Temporal Sequence-Aware Model for Few-Shot Action Recognition

UniAP: Towards Universal Animal Perception in Vision via Few-Shot Learning

Bringing RNNs Back to Efficient Open-Ended Video Understanding

AniMo: Species-Aware Model for Text-Driven Animal Motion Generation

Efficient Logit-based Knowledge Distillation of Deep Spiking Neural Networks for Full-Range Timestep Deployment