태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
The benchmark evaluates a generative Video Conversational Model with respect to Detail Orientation.
We curate a test set based on the ActivityNet-200 dataset, featuring videos with rich, dense descriptive captions and associated question-answer pairs from human annotations. We develop an evaluation pipeline using the GPT-3.5 model that assigns a relative score to the generated predictions on a scale of 1-5.
출처에 같은 태스크 이름으로 연결된 데이터셋입니다. 동명 태스크가 포함될 수 있으므로, 비교할 때는 평가 결과의 조건도 확인하세요.
Video Instruction Dataset is used to train Video-ChatGPT. It consists of 100,000 high-quality video instruction pairs. employs a combination of human-assisted and semi-automatic annotation techniques, aiming to produce high-quality video instruction data. These methods create question-answer pairs related to 1. Video summarization 2. Description-based question-answers (exploring spatial, temporal, relationships, and reasoning concepts) 3. Creative/generative question-answers
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.