collaborators

7 papers

cs.CV2026

CRISP: Pre-LLM Yet Text-Driven Visual Token Pruning for Efficient LVLM Inference

Xu Li, Yi Zheng, Mengyang Zhao +7

Large Vision-Language Models (LVLMs) typically require processing hundreds to thousands of visual tokens, leading to substantial inference overhead. Existing visual token pruning m…

cs.CV2026

Robust Embodied Perception in Dynamic Environments via Disentangled Weight Fusion

Juncen Guo, Xiaoguang Zhu, Jingyi Wu +4

Embodied perception systems face severe challenges of dynamic environment distribution drift when they continuously interact in open physical spaces. However, the existing domain i…

cs.CV2025

CalFuse: Multi-Modal Continual Learning via Feature Calibration and Parameter Fusion

Juncen Guo, Siao Liu, Xiaoguang Zhu +8

With the proliferation of multi-modal data in large-scale visual recognition systems, enabling models to continuously acquire knowledge from evolving data streams while preserving…

cs.CV2025

Privacy-Preserving Video Anomaly Detection: A Survey

Yang Liu, Siao Liu, Xiaoguang Zhu +7

Video Anomaly Detection (VAD) aims to automatically analyze spatiotemporal patterns in surveillance videos collected from open spaces to detect anomalous events that may cause harm…

cs.CV2025

Cross-channel Perception Learning for H&E-to-IHC Virtual Staining

Hao Yang, JianYu Wu, Run Fang +7

With the rapid development of digital pathology, virtual staining has become a key technology in multimedia medical information systems, offering new possibilities for the analysis…

cs.NI2025

A Survey on Video Analytics in Cloud-Edge-Terminal Collaborative Systems

Linxiao Gong, Hao Yang, Gaoyun Fang +7

The explosive growth of video data has driven the development of distributed video analytics in cloud-edge-terminal collaborative (CETC) systems, enabling efficient video processin…