Peng Wu

15

Papers

315

Total Citations

Papers (15)

VadCLIP: Adapting Vision-Language Models for Weakly Supervised Video Anomaly Detection

Text Prompt with Normality Guidance for Weakly Supervised Video Anomaly Detection

Open-Vocabulary Video Anomaly Detection

Unified Embedding Alignment for Open-Vocabulary Video Instance Segmentation

Out-of-Bounding-Box Triggers: A Stealthy Approach to Cheat Object Detectors

Learning Counterfactual Outcomes Under Rank Preservation

NeurIPS 2025arXiv

Guiding Cross-Modal Representations with MLLM Priors via Preference Alignment

A Conditional Probability Framework for Compositional Zero-shot Learning

Local Causal Structure Learning in the Presence of Latent Variables

LOGICZSL: Exploring Logic-induced Representation for Compositional Zero-shot Learning

Probabilistic Verification of Cybersickness in Virtual Reality Through Bayesian Networks

VarCMP: Adapting Cross-Modal Pre-Training Models for Video Anomaly Retrieval

Relaxing the Accurate Imputation Assumption in Doubly Robust Learning for Debiased Collaborative Filtering

Policy Learning for Balancing Short-Term and Long-Term Rewards

HVI: A New Color Space for Low-light Image Enhancement