Papers with Code 아카이브

Live Video Captioning

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

하위 태스크: 0
평가표: 1
보존된 평가 기록: 1

Live video captioning (LVC) involves detecting and describing dense events within video streams. Traditional dense video captioning approaches typically focus on offline solutions where the entire video is available for analysis by the captioning model. In contrast, the LVC paradigm requires models to generate captions for video streams in an online manner. This imposes significant constraints, such as working with incomplete observations of the video and the need for temporal anticipation.

데이터셋

출처에 같은 태스크 이름으로 연결된 데이터셋입니다. 동명 태스크가 포함될 수 있으므로, 비교할 때는 평가 결과의 조건도 확인하세요.

ActivityNet Captions

The ActivityNet Captions dataset is built on ActivityNet v1.3 which includes 20k YouTube untrimmed videos with 100k caption annotations. The videos are 120 seconds long on average. Most of the videos contain over 3 annotated events with corresponding start/end time and human-written sentences, which contain 13.5 words on average. The number of videos in train/validation/test split is 10024/4926/5044, respectively. Source: Bidirectional Attentive Fusion with Context Gating for Dense Video Captioning Image Source: https://cs.stanford.edu/people/ranjaykrishna/densevid/

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.