Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations
text-to-video Mean Rank: 9.3 text-to-video R@1: 62.9text-to-video R@5: 84.5text-to-video R@10: 90.8
Papers with Code · CC BY-SA 4.0
Video Retrieval
The objective of video retrieval is as follows: given a text query and a pool of candidate videos, select the video which corresponds to the text query. Typically, the videos are returned as a ranked list of candidates and scored via document retrieval metrics.
개요는 각 항목의 일부입니다. 위 탭에서 전체 기록을 페이지별로 탐색할 수 있습니다.
벤치마크
Papers with Code 아카이브의 데이터셋별 기록 예시입니다. 평가 조건과 지표 방향이 검증되지 않아 순위를 의미하지 않습니다.
Dataset기록된 모델 예시MetricPaperCode
HunYuan_tvr (huge)
text-to-video Mean Rank: 9.3 text-to-video R@1: 62.9text-to-video R@5: 84.5text-to-video R@10: 90.8
논문
-
GRAM
text-to-video R@1: 64text-to-video R@10: 89.3video-to-text R@1: 64.8video-to-text R@10: 91.5
논문
코드
데이터셋
33개논문
text-to-video R@1: 57.7text-to-video R@5: 80.5text-to-video R@10: 88.2text-to-video Median Rank: 1.0
text-to-video Mean Rank: 10.0text-to-video R@1: 55.5text-to-video R@5: 79.4text-to-video R@10: 87.1
text-to-video R@1: 13.6text-to-video R@5: 32.5text-to-video R@10: 41.8
text-to-video R@1: 54.7text-to-video R@5: 77.7text-to-video R@10: 86.0
text-to-video Mean Rank: 10.7text-to-video R@1: 55.9text-to-video R@5: 79.8text-to-video R@10: 87.6
text-to-video R@1: 54.1text-to-video R@5: 79.5text-to-video R@10: 87.8text-to-video Median Rank: 1
text-to-video R@1: 24.9text-to-video R@5: 46.5text-to-video R@10: 55.1
text-to-video R@1: 54.1text-to-video R@5: 78.8text-to-video R@10: 86.9
text-to-video R@1: 54.0text-to-video R@5: 79.3text-to-video R@10: 87.4
text-to-video R@1: 18.4text-to-video R@5: 36.4 text-to-video R@10: 44.3
라이브러리
Papers with Code 리더보드 row에 연결된 구현 저장소입니다.