Shot-Aware Frame Sampling for Video Understanding
Published in arXiv preprint, 2026
This work introduces InfoShot, a task-agnostic frame sampler for efficient long-video understanding. It partitions videos into semantically consistent shots and selects complementary representative and high-deviation frames to retain both broad context and short-lived critical events.
Recommended citation: Mengyu Zhao, Di Fu, Yongyu Xie, Jiaxing Zhang, Zhigang Yuan, Shirin Jalali, Yong Cao. 2026. Shot-Aware Frame Sampling for Video Understanding. arXiv:2603.17374.
Recommended citation: Mengyu Zhao, Di Fu, Yongyu Xie, Jiaxing Zhang, Zhigang Yuan, Shirin Jalali, Yong Cao. 2026. Shot-Aware Frame Sampling for Video Understanding. arXiv:2603.17374. https://arxiv.org/abs/2603.17374