5 papers
Metacognition as Reward: Reinforcing LLM Reasoning via Knowledge and Regulation Signals
Sirui Chen, Lei Xu, Yuying Zhao +6
Recent RL methods have substantially improved the reasoning abilities of LLMs. Existing reward designs mainly follow two paradigms: (1) Reinforcement learning with verifiable rewar…
STAR: Semantic-Temporal Adaptive Representation Learning for Few-Shot Action Recognition
Hongli Liu, Yu Wang, Shengjie Zhao
Few-shot action recognition (FSAR) requires models to generalize to novel action categories from only a handful of annotated samples. Despite progress with vision-language models,…
GenCape: Structure-Inductive Generative Modeling for Category-Agnostic Pose Estimation
Jiyong Rao, Yu Wang, Shengjie Zhao
Category-agnostic pose estimation (CAPE) aims to localize keypoints on query images from arbitrary categories, using only a few annotated support examples for guidance. Recent appr…
Unify the Views: View-Consistent Prototype Learning for Few-Shot Segmentation
Hongli Liu, Yu Wang, Shengjie Zhao
Few-shot segmentation (FSS) has gained significant attention for its ability to generalize to novel classes with limited supervision, yet remains challenged by structural misalignm…
Weakly Supervised Video Anomaly Detection with Anomaly-Connected Components and Intention Reasoning
Yu Wang, Shengjie Zhao
Weakly supervised video anomaly detection (WS-VAD) involves identifying the temporal intervals that contain anomalous events in untrimmed videos, where only video-level annotations…