Temporal Segment Transformer for Action Segmentation
원문 초록
Recognizing human actions from untrimmed videos is an important task in activity understanding, and poses unique challenges in modeling long-range temporal relations. Recent works adopt a predict-and-refine strategy which converts an initial prediction to action segments for global context modeling. However, the generated segment representations are often noisy and exhibit inaccurate segment boundaries, over-segmentation and other problems. To deal with these issues, we propose an attention based approach which we call \textit{temporal segment transformer}, for joint segment relation modeling and denoising. The main idea is to denoise segment representations using attention between segment and frame representations, and also use inter-segment attention to capture temporal correlations between segments. The refined segment representations are used to predict action labels and adjust segment boundaries, and a final action segmentation is produced based on voting from segment masks. We show that this novel architecture achieves state-of-the-art accuracy on the popular 50Salads, GTEA and Breakfast benchmarks. We also conduct extensive ablations to demonstrate the effectiveness of different components of our design.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
ASQuery: A Query-based Model for Action Segmentation
Is Weakly-supervised Action Segmentation Ready For Human-Robot Interaction? No, Let's Improve It With Action-union Learning
Alleviating Textual Reliance in Medical Language-guided Segmentation via Prototype-driven Semantic Approximation
A New Dataset and Performance Benchmark for Real-time Spacecraft Segmentation in Onboard Flight Computers
Seg-Wild: Interactive Segmentation based on 3D Gaussian Splatting for Unconstrained Image Collections
PSAT: Pediatric Segmentation Approaches via Adult Augmentations and Transfer Learning
토론
이 논문과 연결된 포럼 글이 아직 없습니다.