태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
Human-Object Interaction (HOI) Anticipation is the task of predicting "a set of interactions" in a video that will happen in the future, which involves the i) localization of the subject (i.e., humans) and target (i.e., objects) of interaction, and ii) the classification of the interaction labels.
출처에 같은 태스크 이름으로 연결된 데이터셋입니다. 동명 태스크가 포함될 수 있으므로, 비교할 때는 평가 결과의 조건도 확인하세요.
VidHOI is a video-based human-object interaction detection benchmark. VidHOI is based on VidOR which is densely annotated with all humans and predefined objects showing up in each frame. VidOR is also more challenging as the videos are non-volunteering user-generated and thus jittery at times. Image source: https://xdshang.github.io/docs/vidor.html
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.