S-Measure: 0.755max F-Measure: 0.659max E-Measure: 0.806Average MAE: 0.084
Papers with Code · CC BY-SA 4.0
Video Salient Object Detection
Video salient object detection (VSOD) is significantly essential for understanding the underlying mechanism behind HVS during free-viewing in general and instrumental to a wide range of real-world applications, e.g., video segmentation, video captioning, video compression, autonomous driving, robotic interaction, weakly supervised attention. Besides its academic value and practical significance, VSOD presents great difficulties due to the challenges carried by video data (diverse motion patterns, occlusions, blur, large object deformations, etc.) and the inherent complexity of human visual attention behavior (i.e., selective attention allocation, attention shift) during dynamic scenes. Online benchmark: http://dpfan.net/davsod.
<span style="color:grey; opacity: 0.6">( Image credit: Shifting More Attention to Video Salient Object Detection, CVPR2019-Best Paper Finalist )</span>
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
데이터셋
10개논문
S-Measure: 0.803max F-Measure: 0.732Average MAE: 0.066
S-Measure: 0.894AVERAGE MAE: 0.028MAX F-MEASURE: 0.890
S-Measure: 0.701max F-Measure: 0.589max E-Measure: 0.765Average MAE: 0.095
S-Measure: 0.536max E-Measure: 0.624Average MAE: 0.231
S-Measure: 0.706max F-Measure: 0.591max E-Measure: 0.749Average MAE: 0.114
S-Measure: 0.530max E-Measure: 0.632Average MAE: 0.214
S-Measure: 0.564max E-Measure: 0.640Average MAE: 0.187
S-Measure: 0.534max E-Measure: 0.582Average MAE: 0.206
S-Measure: 0.646max F-Measure: 0.506max E-Measure: 0.694Average MAE: 0.109
라이브러리
Papers with Code 리더보드 row에 연결된 구현 저장소입니다.