ACM Multimedia 2025 · Demo
CReLeRI: Explainable, Concept-centric, Representation, Learning, Reasoning, and Interaction Video Analysis System
Michael Francis Perez, Yichi Yang, Yuheng Zha, Enze Ma, Danish Tamboli, Haodi Ma, Reza Shahriari, Vyom Pathak, Dzmitry Kasinets, Rohith Venkatakrishnan, Daisy (Zhe) Wang, Jaime Ruiz, Eric D. Ragan, Zhiting Hu, Eric Xing, Jun-Yan Zhu
Overview
CReLeRI makes action recognition in untrimmed videos easier to inspect. It divides videos at scene and action transitions, identifies actions and their participants, and checks their spatial grounding in 3D. An interactive interface connects the results to video segments and visual evidence.
Resources