All news
4 articles- paperarXiv (systems, data, ML)·22 Oct 20263.9Motion-guided VLM picks frames for efficient video anomaly detection instead of dense per-frame inference.
- paperarXiv (systems, data, ML)·22 Oct 20263.7Benchmark for agents writing video-centered deep research reports.
- paperarXiv (systems, data, ML)·22 Oct 20263.3Step-sequence reasoning to recognize mistakes in procedural videos.
- paperACM Digital Library·24 Oct 20263.2Text-query-guided video summarization with a self-attentive conv network.