Question Answering on ActivityNet-QA

Metric: Confidence Score (lower is better)

LeaderboardDataset

Loading chart...

Results

Sort:

#	Model↕	Confidence Score▲	Extra Data	Paper	Date↕	Code
1	Video LLaMA	1.1	No	Video-LLaMA: An Instruction-tuned Audio-Visual L...	2023-06-05	Code
2	Video Chat	2.2	No	VideoChat: Chat-Centric Video Understanding	2023-05-10	Code
3	Video-ChatGPT	2.7	No	Video-ChatGPT: Towards Detailed Video Understand...	2023-06-08	Code
4	LLaMA Adapter	2.7	No	LLaMA-Adapter V2: Parameter-Efficient Visual Ins...	2023-04-28	Code
5	Elysium	2.9	No	Elysium: Exploring Object-level Perception in Vi...	2024-03-25	Code
6	MovieChat	3.1	No	MovieChat: From Dense Token to Sparse Memory for...	2023-07-31	Code
7	BT-Adapter (zero-shot)	3.2	No	BT-Adapter: Video Conversation is Feasible Witho...	2023-09-27	Code
8	ST-LLM	3.3	No	ST-LLM: Large Language Models Are Effective Temp...	2024-03-30	Code
9	Video-LaVIT	3.3	No	Video-LaVIT: Unified Video-Language Pre-training...	2024-02-05	Code
10	VideoChat2	3.3	No	MVBench: A Comprehensive Multi-modal Video Under...	2023-11-28	Code
11	LLaMA-VID-13B (2 Token)	3.3	No	LLaMA-VID: An Image is Worth 2 Tokens in Large L...	2023-11-28	Code
12	LLaMA-VID-7B (2 Token)	3.3	No	LLaMA-VID: An Image is Worth 2 Tokens in Large L...	2023-11-28	Code
13	Chat-UniVi	3.3	No	Chat-UniVi: Unified Visual Representation Empowe...	2023-11-14	Code
14	Video-LLaVA	3.3	No	Video-LLaVA: Learning United Visual Representati...	2023-11-16	Code
15	Flash-VStream	3.4	No	Flash-VStream: Memory-Based Real-Time Understand...	2024-06-12	Code
16	SlowFast-LLaVA-34B	3.5	No	SlowFast-LLaVA: A Strong Training-Free Baseline ...	2024-07-22	Code
17	TS-LLaVA-34B	3.5	No	TS-LLaVA: Constructing Visual Tokens through Thu...	2024-11-17	Code
18	IG-VLM	3.5	No	An Image Grid Can Be Worth a Video: Zero-shot Vi...	2024-03-27	Code
19	LLaVA-Mini	3.5	No	LLaVA-Mini: Efficient Image and Video Large Mult...	2025-01-07	Code
20	CAT-7B	3.5	No	CAT: Enhancing Multimodal Large Language Model t...	2024-03-07	Code
21	PPLLaVA-7B	3.6	No	PPLLaVA: Varied Video Sequence Understanding Wit...	2024-11-04	Code
22	LinVT-Qwen2-VL(7B)	3.6	No	LinVT: Empower Your Image-level Large Language M...	2024-12-06	Code
23	VideoGPT+	3.6	No	VideoGPT+: Integrating Image and Video Encoders ...	2024-06-13	Code
24	Chat-UniVi-13B	3.6	No	Chat-UniVi: Unified Visual Representation Empowe...	2023-11-14	Code
25	Tarsier (34B)	3.7	No	Tarsier: Recipes for Training and Evaluating Lar...	2024-06-30	Code
26	PLLaVA (34B)	3.7	No	PLLaVA : Parameter-free LLaVA Extension from Ima...	2024-04-25	Code

#1Video LLaMASOTA
1.1
Confidence Score· 2023-06-05
Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding Code
#2Video ChatSOTA
2.2
Confidence Score· 2023-05-10
VideoChat: Chat-Centric Video Understanding Code
#3Video-ChatGPT
2.7
Confidence Score· 2023-06-08
Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models Code
#4LLaMA AdapterSOTA
2.7
Confidence Score· 2023-04-28
LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Model Code
#5Elysium
2.9
Confidence Score· 2024-03-25
Elysium: Exploring Object-level Perception in Videos via MLLM Code
#6MovieChat
3.1
Confidence Score· 2023-07-31
MovieChat: From Dense Token to Sparse Memory for Long Video Understanding Code
#7BT-Adapter (zero-shot)
3.2
Confidence Score· 2023-09-27
BT-Adapter: Video Conversation is Feasible Without Video Instruction Tuning Code
#8ST-LLM
3.3
Confidence Score· 2024-03-30
ST-LLM: Large Language Models Are Effective Temporal Learners Code
#9Video-LaVIT
3.3
Confidence Score· 2024-02-05
Video-LaVIT: Unified Video-Language Pre-training with Decoupled Visual-Motional Tokenization Code
#10VideoChat2
3.3
Confidence Score· 2023-11-28
MVBench: A Comprehensive Multi-modal Video Understanding Benchmark Code
#11LLaMA-VID-13B (2 Token)
3.3
Confidence Score· 2023-11-28
LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models Code
#12LLaMA-VID-7B (2 Token)
3.3
Confidence Score· 2023-11-28
LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models Code
#13Chat-UniVi
3.3
Confidence Score· 2023-11-14
Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding Code
#14Video-LLaVA
3.3
Confidence Score· 2023-11-16
Video-LLaVA: Learning United Visual Representation by Alignment Before Projection Code
#15Flash-VStream
3.4
Confidence Score· 2024-06-12
Flash-VStream: Memory-Based Real-Time Understanding for Long Video Streams Code
#16SlowFast-LLaVA-34B
3.5
Confidence Score· 2024-07-22
SlowFast-LLaVA: A Strong Training-Free Baseline for Video Large Language Models Code
#17TS-LLaVA-34B
3.5
Confidence Score· 2024-11-17
TS-LLaVA: Constructing Visual Tokens through Thumbnail-and-Sampling for Training-Free Video Large Language Models Code
#18IG-VLM
3.5
Confidence Score· 2024-03-27
An Image Grid Can Be Worth a Video: Zero-shot Video Question Answering Using a VLM Code
#19LLaVA-Mini
3.5
Confidence Score· 2025-01-07
LLaVA-Mini: Efficient Image and Video Large Multimodal Models with One Vision Token Code
#20CAT-7B
3.5
Confidence Score· 2024-03-07
CAT: Enhancing Multimodal Large Language Model to Answer Questions in Dynamic Audio-Visual Scenarios Code
#21PPLLaVA-7B
3.6
Confidence Score· 2024-11-04
PPLLaVA: Varied Video Sequence Understanding With Prompt Guidance Code
#22LinVT-Qwen2-VL(7B)
3.6
Confidence Score· 2024-12-06
LinVT: Empower Your Image-level Large Language Model to Understand Videos Code
#23VideoGPT+
3.6
Confidence Score· 2024-06-13
VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding Code
#24Chat-UniVi-13B
3.6
Confidence Score· 2023-11-14
Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding Code
#25Tarsier (34B)
3.7
Confidence Score· 2024-06-30
Tarsier: Recipes for Training and Evaluating Large Video Description Models Code
#26PLLaVA (34B)
3.7
Confidence Score· 2024-04-25
PLLaVA : Parameter-free LLaVA Extension from Images to Videos for Video Dense Captioning Code