Question Answering on ActivityNet-QA

Metric: Accuracy (higher is better)

LeaderboardDataset

Loading chart...

Results

Sort:

#	Model↕	Accuracy▼	Extra Data	Paper	Date↕	Code
1	Tarsier (34B)	61.6	No	Tarsier: Recipes for Training and Evaluating Lar...	2024-06-30	Code
2	PLLaVA (34B)	60.9	No	PLLaVA : Parameter-free LLaVA Extension from Ima...	2024-04-25	Code
3	PPLLaVA-7B	60.7	No	PPLLaVA: Varied Video Sequence Understanding Wit...	2024-11-04	Code
4	LinVT-Qwen2-VL(7B)	60.1	No	LinVT: Empower Your Image-level Large Language M...	2024-12-06	Code
5	SlowFast-LLaVA-34B	59.2	No	SlowFast-LLaVA: A Strong Training-Free Baseline ...	2024-07-22	Code
6	TS-LLaVA-34B	58.9	No	TS-LLaVA: Constructing Visual Tokens through Thu...	2024-11-17	Code
7	IG-VLM	58.4	No	An Image Grid Can Be Worth a Video: Zero-shot Vi...	2024-03-27	Code
8	LLaVA-Mini	53.5	No	LLaVA-Mini: Efficient Image and Video Large Mult...	2025-01-07	Code
9	Flash-VStream	51.9	No	Flash-VStream: Memory-Based Real-Time Understand...	2024-06-12	Code
10	ST-LLM	50.9	No	ST-LLM: Large Language Models Are Effective Temp...	2024-03-30	Code
11	VideoGPT+	50.6	No	VideoGPT+: Integrating Image and Video Encoders ...	2024-06-13	Code
12	CAT-7B	50.2	No	CAT: Enhancing Multimodal Large Language Model t...	2024-03-07	Code
13	Video-LaVIT	50.1	No	Video-LaVIT: Unified Video-Language Pre-training...	2024-02-05	Code
14	VideoChat2	49.1	No	MVBench: A Comprehensive Multi-modal Video Under...	2023-11-28	Code
15	LLaMA-VID-13B (2 Token)	47.5	No	LLaMA-VID: An Image is Worth 2 Tokens in Large L...	2023-11-28	Code
16	LLaMA-VID-7B (2 Token)	47.4	No	LLaMA-VID: An Image is Worth 2 Tokens in Large L...	2023-11-28	Code
17	Chat-UniVi-13B	46.4	No	Chat-UniVi: Unified Visual Representation Empowe...	2023-11-14	Code
18	MiniGPT4-video-7B	46.3	No	MiniGPT4-Video: Advancing Multimodal LLMs for Vi...	2024-04-04	Code
19	Chat-UniVi	46.1	No	Chat-UniVi: Unified Visual Representation Empowe...	2023-11-14	Code
20	BT-Adapter (zero-shot)	46.1	No	BT-Adapter: Video Conversation is Feasible Witho...	2023-09-27	Code
21	MovieChat	45.7	No	MovieChat: From Dense Token to Sparse Memory for...	2023-07-31	Code
22	Video-LLaVA	45.3	No	Video-LLaVA: Learning United Visual Representati...	2023-11-16	Code
23	Elysium	43.4	No	Elysium: Exploring Object-level Perception in Vi...	2024-03-25	Code
24	Video-ChatGPT	35.2	No	Video-ChatGPT: Towards Detailed Video Understand...	2023-06-08	Code
25	LLaMA Adapter	34.2	No	LLaMA-Adapter V2: Parameter-Efficient Visual Ins...	2023-04-28	Code
26	Video Chat	26.5	No	VideoChat: Chat-Centric Video Understanding	2023-05-10	Code
27	FrozenBiLM	24.7	No	Zero-Shot Video Question Answering via Frozen Bi...	2022-06-16	Code
28	Video LLaMA	12.4	No	Video-LLaMA: An Instruction-tuned Audio-Visual L...	2023-06-05	Code

#1Tarsier (34B)SOTA
61.6
Accuracy· 2024-06-30
Tarsier: Recipes for Training and Evaluating Large Video Description Models Code
#2PLLaVA (34B)SOTA
60.9
Accuracy· 2024-04-25
PLLaVA : Parameter-free LLaVA Extension from Images to Videos for Video Dense Captioning Code
#3PPLLaVA-7B
60.7
Accuracy· 2024-11-04
PPLLaVA: Varied Video Sequence Understanding With Prompt Guidance Code
#4LinVT-Qwen2-VL(7B)
60.1
Accuracy· 2024-12-06
LinVT: Empower Your Image-level Large Language Model to Understand Videos Code
#5SlowFast-LLaVA-34B
59.2
Accuracy· 2024-07-22
SlowFast-LLaVA: A Strong Training-Free Baseline for Video Large Language Models Code
#6TS-LLaVA-34B
58.9
Accuracy· 2024-11-17
TS-LLaVA: Constructing Visual Tokens through Thumbnail-and-Sampling for Training-Free Video Large Language Models Code
#7IG-VLMSOTA
58.4
Accuracy· 2024-03-27
An Image Grid Can Be Worth a Video: Zero-shot Video Question Answering Using a VLM Code
#8LLaVA-Mini
53.5
Accuracy· 2025-01-07
LLaVA-Mini: Efficient Image and Video Large Multimodal Models with One Vision Token Code
#9Flash-VStream
51.9
Accuracy· 2024-06-12
Flash-VStream: Memory-Based Real-Time Understanding for Long Video Streams Code
#10ST-LLM
50.9
Accuracy· 2024-03-30
ST-LLM: Large Language Models Are Effective Temporal Learners Code
#11VideoGPT+
50.6
Accuracy· 2024-06-13
VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding Code
#12CAT-7BSOTA
50.2
Accuracy· 2024-03-07
CAT: Enhancing Multimodal Large Language Model to Answer Questions in Dynamic Audio-Visual Scenarios Code
#13Video-LaVITSOTA
50.1
Accuracy· 2024-02-05
Video-LaVIT: Unified Video-Language Pre-training with Decoupled Visual-Motional Tokenization Code
#14VideoChat2SOTA
49.1
Accuracy· 2023-11-28
MVBench: A Comprehensive Multi-modal Video Understanding Benchmark Code
#15LLaMA-VID-13B (2 Token)
47.5
Accuracy· 2023-11-28
LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models Code
#16LLaMA-VID-7B (2 Token)
47.4
Accuracy· 2023-11-28
LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models Code
#17Chat-UniVi-13BSOTA
46.4
Accuracy· 2023-11-14
Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding Code
#18MiniGPT4-video-7B
46.3
Accuracy· 2024-04-04
MiniGPT4-Video: Advancing Multimodal LLMs for Video Understanding with Interleaved Visual-Textual Tokens Code
#19Chat-UniVi
46.1
Accuracy· 2023-11-14
Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding Code
#20BT-Adapter (zero-shot)SOTA
46.1
Accuracy· 2023-09-27
BT-Adapter: Video Conversation is Feasible Without Video Instruction Tuning Code
#21MovieChatSOTA
45.7
Accuracy· 2023-07-31
MovieChat: From Dense Token to Sparse Memory for Long Video Understanding Code
#22Video-LLaVA
45.3
Accuracy· 2023-11-16
Video-LLaVA: Learning United Visual Representation by Alignment Before Projection Code
#23Elysium
43.4
Accuracy· 2024-03-25
Elysium: Exploring Object-level Perception in Videos via MLLM Code
#24Video-ChatGPTSOTA
35.2
Accuracy· 2023-06-08
Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models Code
#25LLaMA AdapterSOTA
34.2
Accuracy· 2023-04-28
LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Model Code
#26Video Chat
26.5
Accuracy· 2023-05-10
VideoChat: Chat-Centric Video Understanding Code
#27FrozenBiLMSOTA
24.7
Accuracy· 2022-06-16
Zero-Shot Video Question Answering via Frozen Bidirectional Language Models Code
#28Video LLaMA
12.4
Accuracy· 2023-06-05
Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding Code