Peng Wu

papers

1,031

total citations

papers (20)

Not only Look, but also Listen: Learning Multimodal Violence Detection under Weak Supervision

ECCV 2020arXiv

439

citations

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

AAAI 2024arXiv

163

citations

Video Event Restoration Based on Keyframes for Video Anomaly Detection

CVPR 2023arXiv

102

citations

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

CVPR 2025arXiv

citations

Text Prompt with Normality Guidance for Weakly Supervised Video Anomaly Detection

CVPR 2024arXiv

citations

Probabilistic Verification of Cybersickness in Virtual Reality Through Bayesian Networks

ISMAR 2025

citations

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

ECCV 2024arXiv

citations

A Conditional Probability Framework for Compositional Zero-shot Learning

ICCV 2025arXiv

citations

Guiding Cross-Modal Representations with MLLM Priors via Preference Alignment

NEURIPS 2025arXiv

citations

Removing Hidden Confounding in Recommendation: A Unified Multi-Task Learning Approach

NEURIPS 2023

citations

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

ICML 2024

citations

Fairly Recommending with Social Attributes: A Flexible and Controllable Optimization Approach

NEURIPS 2023

citations

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

CVPR 2025

citations

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

AAAI 2025

citations

Peng Wu

papers (20)

Not only Look, but also Listen: Learning Multimodal Violence Detection under Weak Supervision

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

Video Event Restoration Based on Keyframes for Video Anomaly Detection

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

Text Prompt with Normality Guidance for Weakly Supervised Video Anomaly Detection

Open-Vocabulary Video Anomaly Detection

Dynamic Local Aggregation Network with Adaptive Clusterer for Anomaly Detection

Unified Embedding Alignment for Open-Vocabulary Video Instance Segmentation

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

Local Causal Structure Learning in the Presence of Latent Variables

Learning Counterfactual Outcomes Under Rank Preservation

Probabilistic Verification of Cybersickness in Virtual Reality Through Bayesian Networks

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

A Conditional Probability Framework for Compositional Zero-shot Learning

Guiding Cross-Modal Representations with MLLM Priors via Preference Alignment

Removing Hidden Confounding in Recommendation: A Unified Multi-Task Learning Approach

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

Fairly Recommending with Social Attributes: A Flexible and Controllable Optimization Approach

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

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

papers (20)

Not only Look, but also Listen: Learning Multimodal Violence Detection under Weak Supervision

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

Video Event Restoration Based on Keyframes for Video Anomaly Detection

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

Text Prompt with Normality Guidance for Weakly Supervised Video Anomaly Detection

Open-Vocabulary Video Anomaly Detection

Dynamic Local Aggregation Network with Adaptive Clusterer for Anomaly Detection

Unified Embedding Alignment for Open-Vocabulary Video Instance Segmentation

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

Local Causal Structure Learning in the Presence of Latent Variables

Learning Counterfactual Outcomes Under Rank Preservation

Probabilistic Verification of Cybersickness in Virtual Reality Through Bayesian Networks

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

A Conditional Probability Framework for Compositional Zero-shot Learning

Guiding Cross-Modal Representations with MLLM Priors via Preference Alignment

Removing Hidden Confounding in Recommendation: A Unified Multi-Task Learning Approach

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

Fairly Recommending with Social Attributes: A Flexible and Controllable Optimization Approach

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

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