Tencent AVS: A Holistic Ads Video Dataset for Multi-modal Scene Segmentation

no code implementations • 9 Dec 2022 • Jie Jiang, Zhimin Li, Jiangfeng Xiong, Rongwei Quan, Qinglin Lu, Wei Liu

Therefore, TAVS is distinguished from previous temporal segmentation datasets due to its multi-modal information, holistic view of categories, and hierarchical granularities.

Multi-Label Classification Scene Segmentation +3