← VCGBench-Diverse

Papers with Code · CC BY-SA 4.0

VideoInstruct

아카이브 평가 6건 · 마지막 적재/변경 2026-10-30

원본 데이터셋 링크 1

평가 기록

과거 수집 기록이며 최신 순위가 아닙니다. 데이터셋 버전·split·실험 조건과 지표 방향이 검증되지 않은 결과는 직접 비교할 수 없습니다. 날짜는 논문 날짜이며 최신 평가일을 뜻하지 않습니다.

표가 화면보다 넓으면 좌우로 스크롤하여 논문과 구현 링크를 확인하세요.

원본 기록 순서 · 순위 미부여
모델	원본 지표·값	논문	구현
VideoGPT+	mean 2.47 Correctness of Information 2.46 Detail Orientation 2.73 Contextual Understanding 2.81 Temporal Understanding 1.78 Consistency 2.59 Dense Captioning 1.38 Spatial Understanding 2.80 Reasoning 3.63	VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding 2024-06-13	코드 1
Chat-UniVi	mean 2.29 Correctness of Information 2.29 Detail Orientation 2.56 Contextual Understanding 2.66 Temporal Understanding 1.56 Consistency 2.36 Dense Captioning 1.33 Spatial Understanding 2.36 Reasoning 3.59	Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding 2023-11-14	코드 1 · 코드 2 · 코드 3 · 코드 4
VideoChat2	mean 2.20 Correctness of Information 2.13 Detail Orientation 2.42 Contextual Understanding 2.51 Temporal Understanding 1.66 Consistency 2.27 Dense Captioning 1.26 Spatial Understanding 2.43 Reasoning 3.13	MVBench: A Comprehensive Multi-modal Video Understanding Benchmark 2023-11-28	코드 1 · 코드 2 · 코드 3
BT-Adapter	mean 2.19 Correctness of Information 2.20 Detail Orientation 2.62 Contextual Understanding 2.59 Temporal Understanding 1.29 Consistency 2.27 Dense Captioning 1.03 Spatial Understanding 2.35 Reasoning 3.62	BT-Adapter: Video Conversation is Feasible Without Video Instruction Tuning 2023-09-27	코드 1
VTimeLLM	mean 2.17 Correctness of Information 2.16 Detail Orientation 2.41 Contextual Understanding 2.48 Temporal Understanding 1.46 Consistency 2.35 Dense Captioning 1.13 Spatial Understanding 2.29 Reasoning 3.45	VTimeLLM: Empower LLM to Grasp Video Moments 2023-11-30	코드 1
Video-ChatGPT	mean 2.08 Correctness of Information 2.07 Detail Orientation 2.42 Contextual Understanding 2.46 Temporal Understanding 1.39 Consistency 2.06 Dense Captioning 0.89 Spatial Understanding 2.25 Reasoning 3.60	Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models 2023-06-08	코드 1 · 코드 2