Papers with Code · CC BY-SA 4.0

Action Segmentation

Action Localization › Action Segmentation 153 평가 기록 15 datasets

Action Segmentation is a challenging problem in high-level video understanding. In its simplest form, Action Segmentation aims to segment a temporally untrimmed video by time and label each segmented part with one of pre-defined action labels. The results of Action Segmentation can be further used as input to various applications, such as video-to-text and action localization.

<span class="description-source">Source: TricorNet: A Hybrid Temporal Convolutional and Recurrent Network for Video Action Segmentation </span>

하위 태스크

UA Unsupervised Action Segmentation 4 데이터셋 · 24 rows WS Weakly Supervised Action Segmentation (Transcript) 1 데이터셋 · 7 rows WS Weakly Supervised Action Segmentation (Action Set)) 1 데이터셋 · 2 rows SB Skeleton Based Action Segmentation 0 데이터셋 · 0 rows