Papers with Code · CC BY-SA 4.0

ActivityNet-QA

아카이브 평가 28건 · 마지막 적재/변경 2026-10-30

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
Tarsier (34B)	Confidence Score 3.7 Accuracy 61.6	Tarsier: Recipes for Training and Evaluating Large Video Description Models 2024-06-30	코드 1
PLLaVA (34B)	Confidence Score 3.7 Accuracy 60.9	PLLaVA : Parameter-free LLaVA Extension from Images to Videos for Video Dense Captioning 2024-04-25	코드 1
PPLLaVA-7B	Confidence Score 3.6 Accuracy 60.7	PPLLaVA: Varied Video Sequence Understanding With Prompt Guidance 2024-11-04	코드 1
LinVT-Qwen2-VL(7B)	Confidence Score 3.6 Accuracy 60.1	LinVT: Empower Your Image-level Large Language Model to Understand Videos 2024-12-06	코드 1
SlowFast-LLaVA-34B	Confidence Score 3.5 Accuracy 59.2	SlowFast-LLaVA: A Strong Training-Free Baseline for Video Large Language Models 2024-07-22	코드 1
TS-LLaVA-34B	Confidence Score 3.5 Accuracy 58.9	TS-LLaVA: Constructing Visual Tokens through Thumbnail-and-Sampling for Training-Free Video Large Language Models 2024-11-17	코드 1
IG-VLM	Confidence Score 3.5 Accuracy 58.4	An Image Grid Can Be Worth a Video: Zero-shot Video Question Answering Using a VLM 2024-03-27	코드 1
LLaVA-Mini	Confidence Score 3.5 Accuracy 53.5	LLaVA-Mini: Efficient Image and Video Large Multimodal Models with One Vision Token 2025-01-07	코드 1
Flash-VStream	Confidence Score 3.4 Accuracy 51.9	Flash-VStream: Memory-Based Real-Time Understanding for Long Video Streams 2024-06-12	코드 1
ST-LLM	Confidence Score 3.3 Accuracy 50.9	ST-LLM: Large Language Models Are Effective Temporal Learners 2024-03-30	코드 1
VideoGPT+	Confidence Score 3.6 Accuracy 50.6	VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding 2024-06-13	코드 1
CAT-7B	Confidence Score 3.5 Accuracy 50.2	CAT: Enhancing Multimodal Large Language Model to Answer Questions in Dynamic Audio-Visual Scenarios 2024-03-07	코드 1
Video-LaVIT	Confidence Score 3.3 Accuracy 50.1	Video-LaVIT: Unified Video-Language Pre-training with Decoupled Visual-Motional Tokenization 2024-02-05	코드 1
VideoChat2	Confidence Score 3.3 Accuracy 49.1	MVBench: A Comprehensive Multi-modal Video Understanding Benchmark 2023-11-28	코드 1 · 코드 2 · 코드 3
LLaMA-VID-13B (2 Token)	Confidence Score 3.3 Accuracy 47.5	LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models 2023-11-28	코드 1 · 코드 2
LLaMA-VID-7B (2 Token)	Confidence Score 3.3 Accuracy 47.4	LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models 2023-11-28	코드 1 · 코드 2
Chat-UniVi-13B	Confidence Score 3.6 Accuracy 46.4	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
MiniGPT4-video-7B	Accuracy 46.3	MiniGPT4-Video: Advancing Multimodal LLMs for Video Understanding with Interleaved Visual-Textual Tokens 2024-04-04	코드 1 · 코드 2
Chat-UniVi	Confidence Score 3.3 Accuracy 46.1	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
BT-Adapter (zero-shot)	Confidence Score 3.2 Accuracy 46.1	BT-Adapter: Video Conversation is Feasible Without Video Instruction Tuning 2023-09-27	코드 1
MovieChat	Confidence Score 3.1 Accuracy 45.7	MovieChat: From Dense Token to Sparse Memory for Long Video Understanding 2023-07-31	코드 1
Video-LLaVA	Confidence Score 3.3 Accuracy 45.3	Video-LLaVA: Learning United Visual Representation by Alignment Before Projection 2023-11-16	코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5 · 코드 6
Elysium	Confidence Score 2.9 Accuracy 43.4	Elysium: Exploring Object-level Perception in Videos via MLLM 2024-03-25	코드 1
Video-ChatGPT	Confidence Score 2.7 Accuracy 35.2	Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models 2023-06-08	코드 1 · 코드 2
LLaMA Adapter	Confidence Score 2.7 Accuracy 34.2	LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Model 2023-04-28	코드 1 · 코드 2 · 코드 3
Video Chat	Confidence Score 2.2 Accuracy 26.5	VideoChat: Chat-Centric Video Understanding 2023-05-10	코드 1
FrozenBiLM	Confidence Score - Accuracy 24.7	Zero-Shot Video Question Answering via Frozen Bidirectional Language Models 2022-06-16	코드 1 · 코드 2 · 코드 3
Video LLaMA	Confidence Score 1.1 Accuracy 12.4	Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding 2023-06-05	코드 1 · 코드 2 · 코드 3 · 코드 4