8 papers
Closing the Estimation Gap: Training-Free Transductive Inference for Cross-Domain Few-Shot Action Recognition
Changyi Li, Zeyu Yang, Yu Xiao
Cross-domain few-shot action recognition (CD-FSAR) aims to recognise unseen action classes in a target domain from a handful of labelled videos. Despite advances in representation…
Compressed LLM Reprogramming for Vision-Aided Beam Prediction in Vehicular Networks
Kai Dong, Lei Wang, Changyi Li +2
Large Language Model (LLM) reprogramming-based beam prediction demonstrates strong data efficiency by adapting pretrained language models for vehicle-to-infrastructure (V2I) beam p…
Reachability Is Not Generalization: Understanding Verb--Noun Decomposition in Assembly Action Recognition
Changyi Li, Yu Xiao
Assembly actions are compositional: they combine a manipulation with a part or tool. In deployment, systems routinely encounter novel combinations of familiar components, yet an at…
Training-Free Logical and Structural Anomaly Detection via Calibrated Fusion
Changyi Li, Miao Yu, Kai Dong +1
Industrial anomaly detection must handle two distinct defect families: structural anomalies, which manifest as local texture corruptions, and logical anomalies, which violate globa…
Adaptive Multi-Granularity Temporal Modeling for Weakly Supervised Video Anomaly Detection
Changyi Li, Yu Xiao
As the scale of video surveillance data outpaces manual annotation capacities, weakly supervised video anomaly detection (WSVAD) has emerged as a critical research frontier. Most e…
Pre-Decoding Acoustic Triage for Budgeted Vision-Language Captioning of Untrimmed Egocentric Video
Masoud Jalayer, Changyi Li, Yu Xiao
Automatically analyzing hours-long egocentric video is increasingly essential for progress monitoring, quality control, and safety in logistics, construction, and manufacturing. Ye…
UniSLAD: A Unified Framework for Structural and Logical Industrial Visual Anomaly Detection
Changyi Li, Chao Yang, Yu Xiao +1
Visual anomaly detection is a fundamental task in industrial automation. While existing approaches have achieved notable progress in identifying structural defects, the detection o…
Exploring Human-AI Collaboration in E-Textile Design: A Case Study on Flex Sensor Placement for Shoulder Motion Detection
Zhuchenyang Liu, Yao Zhang, Yalan He +4
Flex sensors are widely used in e-textiles for detecting joint motions and, subsequently, full-body movements. A critical initial step in utilizing these sensors is determining the…