8 papers
Temporal Feature Distillation for Label-Efficient Precise Event Spotting in Sports Videos
Hao Xu, Xinyu Wei, Sam Wells +1
The paper introduces a semi-supervised Temporal Feature Distillation method and a Transformer Gate Shift module to improve precise event spotting in sports videos with limited labe…
INHerit-SG: Incremental Hierarchical Semantic Scene Graphs with RAG-Style Retrieval
YukTungSamuel Fang, Zhikang Shi, Jiabin Qiu +5
Driven by recent advancements in foundation models, semantic scene graphs have emerged as a promising paradigm for high-level 3D environmental abstraction in robot navigation. Howe…
EgoHandICL: Egocentric 3D Hand Reconstruction with In-Context Learning
Binzhu Xie, Shi Qiu, Sicheng Zhang +5
Robust 3D hand reconstruction in egocentric vision is challenging due to depth ambiguity, self-occlusion, and complex hand-object interactions. Prior methods mitigate these issues…
Multi-Focus Temporal Shifting for Precise Event Spotting in Sports Videos
Hao Xu, Xinyu Wei, Sam Wells +1
Precise Event Spotting (PES) in sports videos requires frame-level recognition of fine-grained actions from single-camera footage. Existing PES models typically incorporate lightwe…
Deep Learning for Sports Video Event Detection: Tasks, Datasets, Methods, and Challenges
Hao Xu, Arbind Agrahari Baniya, Sam Well +3
Video event detection has become a cornerstone of modern sports analytics, powering automated performance evaluation, content generation, and tactical decision-making. Recent advan…
Embodied Representation Alignment with Mirror Neurons
Wentao Zhu, Zhining Zhang, Yuwei Ren +3
Mirror neurons are a class of neurons that activate both when an individual observes an action and when they perform the same action. This mechanism reveals a fundamental interplay…