real-time video analysis

2 papers across 2 sessions

Poster Session 5

Friday, December 5, 2025 · 11:00 AM → 2:00 PM

Aha! - Predicting What Matters Next: Online Highlight Detection Without Looking Ahead

#4609 · Aiden Chang, Celso de Melo, Stephanie Lukin

Aha! enables real-time, autoregressive highlight detection in continuous video using language tasks. Using a VLM and a Dynamic SinkCache for constant memory, it achieves SOTA on benchmarks & shows robotics potential.

Poster Session 6

1 paper

Friday, December 5, 2025 · 4:30 PM → 7:30 PM

Exhibit Hall C,D,E

RTV-Bench: Benchmarking MLLM Continuous Perception, Understanding and Reasoning through Real-Time Video

#4412 · ShuHang Xun, Sicheng Tao, Jungang Li, Yibo Shi, Zhixin Lin, Zhanhui Zhu, Yibo Yan, Hanqian Li, LingHao Zhang, Shikang Wang, Yixin Liu, Hanbo Zhang, Ying Ma, Xuming Hu