arXiv:2008.08977
Generating Adjacency Matrix for Video Relocalization
원문 초록
In this paper, we continue our work on video relocalization task. Based on using graph convolution to extract intra-video and inter-video frame features, we improve the method by using similarity-metric based graph convolution, whose weighted adjacency matrix is achieved by calculating similarity metric between features of any two different time steps in the graph. Experiments on ActivityNet v1.2 and Thumos14 dataset show the effectiveness of this improvement, and it outperforms the state-of-the-art methods.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
TimeLoc: A Unified End-to-End Framework for Precise Timestamp Localization in Long Videos
Moment of Untruth: Dealing with Negative Queries in Video Moment Retrieval
LD-DETR: Loop Decoder DEtection TRansformer for Video Moment Retrieval and Highlight Detection
A Flexible and Scalable Framework for Video Moment Search
Watch Video, Catch Keyword: Context-aware Keyword Attention for Moment Retrieval and Highlight Detection
Length-Aware DETR for Robust Moment Retrieval
토론
이 논문과 연결된 포럼 글이 아직 없습니다.