TSRN: two-stage refinement network for temporal action segmentation

• Published in: Pattern analysis and applications : PAA Vol. 26; no. 3; pp. 1375 - 1393
• Main Authors: Tian, Xiaoyan, Jin, Ye, Tang, Xianglong
• Format: Journal Article
• Language: English
• Published: London Springer London 01.08.2023; Springer Nature B.V
• Subjects: Computer Science; Labels; Pattern Recognition; Segmentation; Segments; Semantics; Theoretical Advances; Temporal action segmentation; Refinement network; Over-segmentation; Video semantic understanding; Self-attention

In high-level video semantic understanding, continuous action segmentation is a challenging task aimed at segmenting an untrimmed video and labeling each segment with predefined labels over time. However, the accuracy of segment predictions is limited by confusing information in video sequences, suc...