VCGBench-Diverse
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 1
- 보존된 평가 기록
- 6
Recognizing the limited diversity in existing video conversation benchmarks, we introduce VCGBench-Diverse to comprehensively evaluate the generalization ability of video LMMs. While VCG-Bench provides an extensive evaluation protocol, it is limited to videos from the ActivityNet200 dataset. Our benchmark comprises a total of 877 videos, 18 broad video categories and 4,354 QA pairs, ensuring a robust evaluation framework.
The evaluation is computed over five different aspects:
Correctness of information
Detail orientation
Contextual understanding
Temporal understanding
Consistency.
Additionally, VCGBench-Diverse provides a breakdown of performance across three key aspects:
Dense video captioning, which assesses the ability to generate detailed and accurate descriptions of the video content,
Spatial understanding, which evaluates the capability to understand and describe the spatial relationships and settings within the video
Reasoning, which tests the adeptness in inferring and explaining causal relationships and actions within the video.
하위 태스크
해결할 문제를 선택하세요. 같은 이름의 태스크는 상위 분야와 평가 조건으로 구분합니다.
더 세분화된 태스크가 없습니다.
관련 논문 살펴보기 →출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.