Zhaoyu Chen

papers

628

total citations

papers (18)

OneTracker: Unifying Visual Object Tracking with Foundation Models and Efficient Tuning

CVPR 2024arXiv

123

citations

AIDE: A Vision-Driven Multi-View, Multi-Modal, Multi-Tasking Dataset for Assistive Driving Perception

ICCV 2023arXiv

citations

Improving Generalization in Visual Reinforcement Learning via Conflict-aware Gradient Agreement Augmentation

ICCV 2023arXiv

citations

Efficient Decision-based Black-box Patch Attacks on Video Recognition

ICCV 2023arXiv

citations

De-confounded Data-free Knowledge Distillation for Handling Distribution Shifts

CVPR 2024arXiv

citations

Improving Factuality in Large Language Models via Decoding-Time Hallucinatory and Truthful Comparators

AAAI 2025arXiv

citations

Debiased Multimodal Understanding for Human Language Sequences

AAAI 2025arXiv

citations

Out of Thin Air: Exploring Data-Free Adversarial Robustness Distillation

AAAI 2024arXiv

citations

dFLMoE: Decentralized Federated Learning via Mixture of Experts for Medical Data Analysis

CVPR 2025arXiv

citations

General Compression Framework for Efficient Transformer Object Tracking

ICCV 2025arXiv

citations

Synthesizing Near-Boundary OOD Samples for Out-of-Distribution Detection

ICCV 2025arXiv

citations

Boosting Adversarial Transferability with Spatial Adversarial Alignment

NEURIPS 2025arXiv

citations

Shape Matters: Deformable Patch Attack

ECCV 2022

citations

Dynamic Semantic-Aware Correlation Modeling for UAV Tracking

NEURIPS 2025arXiv

citations

Zhaoyu Chen

papers (18)

OneTracker: Unifying Visual Object Tracking with Foundation Models and Efficient Tuning

Content-based Unrestricted Adversarial Attack

LVOS: A Benchmark for Long-term Video Object Segmentation

Towards Practical Certifiable Patch Defense With Vision Transformer

Context De-Confounded Emotion Recognition

AIDE: A Vision-Driven Multi-View, Multi-Modal, Multi-Tasking Dataset for Assistive Driving Perception

Improving Generalization in Visual Reinforcement Learning via Conflict-aware Gradient Agreement Augmentation

Efficient Decision-based Black-box Patch Attacks on Video Recognition

De-confounded Data-free Knowledge Distillation for Handling Distribution Shifts

Improving Factuality in Large Language Models via Decoding-Time Hallucinatory and Truthful Comparators

Debiased Multimodal Understanding for Human Language Sequences

Out of Thin Air: Exploring Data-Free Adversarial Robustness Distillation

dFLMoE: Decentralized Federated Learning via Mixture of Experts for Medical Data Analysis

General Compression Framework for Efficient Transformer Object Tracking

Synthesizing Near-Boundary OOD Samples for Out-of-Distribution Detection

Boosting Adversarial Transferability with Spatial Adversarial Alignment

Shape Matters: Deformable Patch Attack

Dynamic Semantic-Aware Correlation Modeling for UAV Tracking

papers (18)

OneTracker: Unifying Visual Object Tracking with Foundation Models and Efficient Tuning

Content-based Unrestricted Adversarial Attack

LVOS: A Benchmark for Long-term Video Object Segmentation

Towards Practical Certifiable Patch Defense With Vision Transformer

Context De-Confounded Emotion Recognition

AIDE: A Vision-Driven Multi-View, Multi-Modal, Multi-Tasking Dataset for Assistive Driving Perception

Improving Generalization in Visual Reinforcement Learning via Conflict-aware Gradient Agreement Augmentation

Efficient Decision-based Black-box Patch Attacks on Video Recognition

De-confounded Data-free Knowledge Distillation for Handling Distribution Shifts

Improving Factuality in Large Language Models via Decoding-Time Hallucinatory and Truthful Comparators

Debiased Multimodal Understanding for Human Language Sequences

Out of Thin Air: Exploring Data-Free Adversarial Robustness Distillation

dFLMoE: Decentralized Federated Learning via Mixture of Experts for Medical Data Analysis

General Compression Framework for Efficient Transformer Object Tracking

Synthesizing Near-Boundary OOD Samples for Out-of-Distribution Detection

Boosting Adversarial Transferability with Spatial Adversarial Alignment

Shape Matters: Deformable Patch Attack

Dynamic Semantic-Aware Correlation Modeling for UAV Tracking