IEEE

Unveiling Context-Related Anomalies: Knowledge Graph Empowered Decoupling of Scene and Action for Human-Related Video Anomaly Detection

Abstract: Video anomaly detection methods are mainly classified into two categories based on their primary feature types: appearance-based and action-based. Appearance-based methods rely on low-level ...
IEEE

CDC: Enhancing Scene Graph Generation for IoST-Driven Social Behavioral Modeling With Cooperative Dual Classifier

Abstract: Scene graph generation (SGG) plays an important role in the intelligence of social things (IoST) framework by extracting structured semantic representations from social device data, thereby ...
GitHub

LASER: A Neuro-Symbolic Framework for Learning Spatial-Temporal Scene Graphs with Weak Supervision

This follow-up work demonstrates applying LASER for scene-graph generation in embodied agent environments. Answer: Ensure your CUDA Tool kit and your pytorch has the same version. Take 12.4 as an ...
abc13

ABC13's 'Countdown to Kickoff' gets Texans fans exclusive pregame coverage all season long

HOUSTON, Texas (KTRK) -- Each week, join ABC13's "Countdown to Kickoff," airing before games this season, for a breakdown of what happened and what to look ahead to next. The pregame show with Greg ...
GitHub

Collaborative Dynamic 3D Scene Graphs for Open-Vocabulary Urban Scene Understanding

@inproceedings{steinke2025curbosg, author={Steinke, Tim and Büchner, Martin and Vödisch, Niclas and Valada, Abhinav}, booktitle={2025 IEEE/RSJ International Conference on Intelligent Robots and ...