Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/Video-ChatGPT

Video-ChatGPT

Reported on 39 benchmarks across 7 tasks · 1 paper · 29 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Reasoning27 results

Generative Visual Question AnsweringonVideoInstruct
Consistency· 2023-06-08
2.37
best: 3.81 (PPLLaVA-7B-dpo)
SOTA
Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models arXiv:2306.05424
Generative Visual Question AnsweringonVideoInstruct
Contextual Understanding· 2023-06-08
2.62
best: 4.21 (PPLLaVA-7B-dpo)
SOTA
Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models arXiv:2306.05424
Generative Visual Question AnsweringonVideoInstruct
Correctness of Information· 2023-06-08
2.4
best: 3.85 (PPLLaVA-7B-dpo)
SOTA
Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models arXiv:2306.05424
Generative Visual Question AnsweringonVideoInstruct
Detail Orientation· 2023-06-08
2.52
best: 3.56 (PPLLaVA-7B-dpo)
SOTA
Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models arXiv:2306.05424
Generative Visual Question AnsweringonVideoInstruct
mean· 2023-06-08
2.38
best: 3.73 (PPLLaVA-7B-dpo)
SOTA
Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models arXiv:2306.05424
Generative Visual Question AnsweringonVideoInstruct
gpt-score· 2023-06-08
2.62
best: 4.21 (PPLLaVA-7B)
SOTA
Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models arXiv:2306.05424
Video-based Generative Performance BenchmarkingonVideoInstruct
Consistency· 2023-06-08
2.37
best: 3.81 (PPLLaVA-7B-dpo)
SOTA
Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models arXiv:2306.05424
Video-based Generative Performance BenchmarkingonVideoInstruct
Contextual Understanding· 2023-06-08
2.62
best: 4.21 (PPLLaVA-7B-dpo)
SOTA
Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models arXiv:2306.05424
Video-based Generative Performance BenchmarkingonVideoInstruct
Correctness of Information· 2023-06-08
2.4
best: 3.85 (PPLLaVA-7B-dpo)
SOTA
Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models arXiv:2306.05424
Video-based Generative Performance BenchmarkingonVideoInstruct
Detail Orientation· 2023-06-08
2.52
best: 3.56 (PPLLaVA-7B-dpo)
SOTA
Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models arXiv:2306.05424
Video-based Generative Performance BenchmarkingonVideoInstruct
mean· 2023-06-08
2.38
best: 3.73 (PPLLaVA-7B-dpo)
SOTA
Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models arXiv:2306.05424
Video-based Generative Performance BenchmarkingonVideoInstruct
gpt-score· 2023-06-08
2.62
best: 4.21 (PPLLaVA-7B)
SOTA
Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models arXiv:2306.05424
Video Question AnsweringonActivityNet-QA
Accuracy· 2023-06-08
35.2
best: 61.6 (Tarsier (34B))
Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models arXiv:2306.05424
Video Question AnsweringonActivityNet-QA
Confidence score· 2023-06-08
2.7
best: 2.2 (Video Chat)
Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models arXiv:2306.05424
Video Question AnsweringonMVBench
Avg.· 2023-06-08
32.7
best: 69.3 (LinVT-Qwen2-VL (7B))
Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models arXiv:2306.05424
Video Question AnsweringonActivityNet-QA
Accuracy· 2023-06-08
35.2
best: 61.6 (Tarsier (34B))
Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models arXiv:2306.05424
Video Question AnsweringonActivityNet-QA
Confidence Score· 2023-06-08
2.7
best: 1.1 (Video LLaMA)
Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models arXiv:2306.05424
Generative Visual Question AnsweringonVideoInstruct
Temporal Understanding· 2023-06-08
1.98
best: 3.23 (VLM-RLAIF)
Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models arXiv:2306.05424
Generative Visual Question AnsweringonVideoInstruct
gpt-score· 2023-06-08
2.4
best: 4.21 (PPLLaVA-7B)
Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models arXiv:2306.05424
Generative Visual Question AnsweringonVideoInstruct
gpt-score· 2023-06-08
2.52
best: 4.21 (PPLLaVA-7B)
Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models arXiv:2306.05424
Generative Visual Question AnsweringonVideoInstruct
gpt-score· 2023-06-08
1.98
best: 4.21 (PPLLaVA-7B)
Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models arXiv:2306.05424
Generative Visual Question AnsweringonVideoInstruct
gpt-score· 2023-06-08
2.37
best: 4.21 (PPLLaVA-7B)
Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models arXiv:2306.05424
Video-based Generative Performance BenchmarkingonVideoInstruct
Temporal Understanding· 2023-06-08
1.98
best: 3.23 (VLM-RLAIF)
Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models arXiv:2306.05424
Video-based Generative Performance BenchmarkingonVideoInstruct
gpt-score· 2023-06-08
2.4
best: 4.21 (PPLLaVA-7B)
Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models arXiv:2306.05424
Video-based Generative Performance BenchmarkingonVideoInstruct
gpt-score· 2023-06-08
2.52
best: 4.21 (PPLLaVA-7B)
Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models arXiv:2306.05424
Video-based Generative Performance BenchmarkingonVideoInstruct
gpt-score· 2023-06-08
1.98
best: 4.21 (PPLLaVA-7B)
Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models arXiv:2306.05424
Video-based Generative Performance BenchmarkingonVideoInstruct
gpt-score· 2023-06-08
2.37
best: 4.21 (PPLLaVA-7B)
Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models arXiv:2306.05424

Natural Language Processing15 results

Question AnsweringonActivityNet-QA
Accuracy· 2023-06-08
35.2
best: 61.6 (Tarsier (34B))
SOTA
Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models arXiv:2306.05424
Visual Question Answering (VQA)onVideoInstruct
Consistency· 2023-06-08
2.37
best: 3.81 (PPLLaVA-7B-dpo)
SOTA
Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models arXiv:2306.05424
Visual Question Answering (VQA)onVideoInstruct
Contextual Understanding· 2023-06-08
2.62
best: 4.21 (PPLLaVA-7B-dpo)
SOTA
Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models arXiv:2306.05424
Visual Question Answering (VQA)onVideoInstruct
Correctness of Information· 2023-06-08
2.4
best: 3.85 (PPLLaVA-7B-dpo)
SOTA
Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models arXiv:2306.05424
Visual Question Answering (VQA)onVideoInstruct
Detail Orientation· 2023-06-08
2.52
best: 3.56 (PPLLaVA-7B-dpo)
SOTA
Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models arXiv:2306.05424
Visual Question Answering (VQA)onVideoInstruct
mean· 2023-06-08
2.38
best: 3.73 (PPLLaVA-7B-dpo)
SOTA
Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models arXiv:2306.05424
Visual Question Answering (VQA)onVideoInstruct
gpt-score· 2023-06-08
2.62
best: 4.21 (PPLLaVA-7B)
SOTA
Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models arXiv:2306.05424
Question AnsweringonNExT-QA (Open-ended VideoQA)
Accuracy· 2023-06-08
54.6
best: 61.6 (Flash-VStream)
Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models arXiv:2306.05424
Question AnsweringonNExT-QA (Open-ended VideoQA)
Confidence Score· 2023-06-08
3.2
best: 2.7 (MovieChat)
Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models arXiv:2306.05424
Question AnsweringonActivityNet-QA
Confidence Score· 2023-06-08
2.7
best: 1.1 (Video LLaMA)
Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models arXiv:2306.05424
Visual Question Answering (VQA)onVideoInstruct
Temporal Understanding· 2023-06-08
1.98
best: 3.23 (VLM-RLAIF)
Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models arXiv:2306.05424
Visual Question Answering (VQA)onVideoInstruct
gpt-score· 2023-06-08
2.4
best: 4.21 (PPLLaVA-7B)
Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models arXiv:2306.05424
Visual Question Answering (VQA)onVideoInstruct
gpt-score· 2023-06-08
2.52
best: 4.21 (PPLLaVA-7B)
Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models arXiv:2306.05424
Visual Question Answering (VQA)onVideoInstruct
gpt-score· 2023-06-08
1.98
best: 4.21 (PPLLaVA-7B)
Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models arXiv:2306.05424
Visual Question Answering (VQA)onVideoInstruct
gpt-score· 2023-06-08
2.37
best: 4.21 (PPLLaVA-7B)
Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models arXiv:2306.05424

Computer Vision9 results

VCGBench-DiverseonVideoInstruct
Consistency· 2023-06-08
2.06
best: 2.59 (VideoGPT+)
SOTA
Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models arXiv:2306.05424
VCGBench-DiverseonVideoInstruct
Contextual Understanding· 2023-06-08
2.46
best: 2.81 (VideoGPT+)
SOTA
Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models arXiv:2306.05424
VCGBench-DiverseonVideoInstruct
Correctness of Information· 2023-06-08
2.07
best: 2.46 (VideoGPT+)
SOTA
Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models arXiv:2306.05424
VCGBench-DiverseonVideoInstruct
Dense Captioning· 2023-06-08
0.89
best: 1.38 (VideoGPT+)
SOTA
Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models arXiv:2306.05424
VCGBench-DiverseonVideoInstruct
Detail Orientation· 2023-06-08
2.42
best: 2.73 (VideoGPT+)
SOTA
Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models arXiv:2306.05424
VCGBench-DiverseonVideoInstruct
Reasoning· 2023-06-08
3.6
best: 3.63 (VideoGPT+)
SOTA
Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models arXiv:2306.05424
VCGBench-DiverseonVideoInstruct
Spatial Understanding· 2023-06-08
2.25
best: 2.8 (VideoGPT+)
SOTA
Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models arXiv:2306.05424
VCGBench-DiverseonVideoInstruct
Temporal Understanding· 2023-06-08
1.39
best: 1.78 (VideoGPT+)
SOTA
Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models arXiv:2306.05424
VCGBench-DiverseonVideoInstruct
mean· 2023-06-08
2.08
best: 2.47 (VideoGPT+)
SOTA
Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models arXiv:2306.05424

Other1 result

Video-based Generative Performance Benchmarking (Correctness of Information)onVideoInstruct
gpt-score· 2023-06-08
2.4
best: 3.85 (PPLLaVA-7B)
SOTA
Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models arXiv:2306.05424