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/MovieChat

MovieChat

Reported on 19 benchmarks across 6 tasks · 1 paper · 10 SOTA

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

Reasoning18 results

Video Question AnsweringonMSVD-QA
Accuracy· 2023-07-31
75.2
best: 80.3 (Tarsier (34B))
SOTA
MovieChat: From Dense Token to Sparse Memory for Long Video Understanding arXiv:2307.16449
Video Question AnsweringonMSRVTT-QA
Accuracy· 2023-07-31
52.7
best: 72.4 (Flash-VStream)
SOTA
MovieChat: From Dense Token to Sparse Memory for Long Video Understanding arXiv:2307.16449
Generative Visual Question AnsweringonVideoInstruct
gpt-score· 2023-07-31
3.01
best: 4.21 (PPLLaVA-7B)
SOTA
MovieChat: From Dense Token to Sparse Memory for Long Video Understanding arXiv:2307.16449
Video-based Generative Performance BenchmarkingonVideoInstruct
gpt-score· 2023-07-31
3.01
best: 4.21 (PPLLaVA-7B)
SOTA
MovieChat: From Dense Token to Sparse Memory for Long Video Understanding arXiv:2307.16449
Video Question AnsweringonActivityNet-QA
Accuracy· 2023-07-31
45.7
best: 61.6 (Tarsier (34B))
MovieChat: From Dense Token to Sparse Memory for Long Video Understanding arXiv:2307.16449
Video Question AnsweringonActivityNet-QA
Confidence score· 2023-07-31
3.1
best: 2.2 (Video Chat)
MovieChat: From Dense Token to Sparse Memory for Long Video Understanding arXiv:2307.16449
Video Question AnsweringonMSVD-QA
Confidence Score· 2023-07-31
2.9
best: 2.5 (Video LLaMA-7B)
MovieChat: From Dense Token to Sparse Memory for Long Video Understanding arXiv:2307.16449
Video Question AnsweringonMSRVTT-QA
Confidence Score· 2023-07-31
2.6
best: 1.8 (Video LLaMA-7B)
MovieChat: From Dense Token to Sparse Memory for Long Video Understanding arXiv:2307.16449
Video Question AnsweringonActivityNet-QA
Accuracy· 2023-07-31
45.7
best: 61.6 (Tarsier (34B))
MovieChat: From Dense Token to Sparse Memory for Long Video Understanding arXiv:2307.16449
Video Question AnsweringonActivityNet-QA
Confidence Score· 2023-07-31
3.1
best: 1.1 (Video LLaMA)
MovieChat: From Dense Token to Sparse Memory for Long Video Understanding arXiv:2307.16449
Generative Visual Question AnsweringonVideoInstruct
gpt-score· 2023-07-31
2.76
best: 4.21 (PPLLaVA-7B)
MovieChat: From Dense Token to Sparse Memory for Long Video Understanding arXiv:2307.16449
Generative Visual Question AnsweringonVideoInstruct
gpt-score· 2023-07-31
2.93
best: 4.21 (PPLLaVA-7B)
MovieChat: From Dense Token to Sparse Memory for Long Video Understanding arXiv:2307.16449
Generative Visual Question AnsweringonVideoInstruct
gpt-score· 2023-07-31
2.24
best: 4.21 (PPLLaVA-7B)
MovieChat: From Dense Token to Sparse Memory for Long Video Understanding arXiv:2307.16449
Generative Visual Question AnsweringonVideoInstruct
gpt-score· 2023-07-31
2.42
best: 4.21 (PPLLaVA-7B)
MovieChat: From Dense Token to Sparse Memory for Long Video Understanding arXiv:2307.16449
Video-based Generative Performance BenchmarkingonVideoInstruct
gpt-score· 2023-07-31
2.76
best: 4.21 (PPLLaVA-7B)
MovieChat: From Dense Token to Sparse Memory for Long Video Understanding arXiv:2307.16449
Video-based Generative Performance BenchmarkingonVideoInstruct
gpt-score· 2023-07-31
2.93
best: 4.21 (PPLLaVA-7B)
MovieChat: From Dense Token to Sparse Memory for Long Video Understanding arXiv:2307.16449
Video-based Generative Performance BenchmarkingonVideoInstruct
gpt-score· 2023-07-31
2.24
best: 4.21 (PPLLaVA-7B)
MovieChat: From Dense Token to Sparse Memory for Long Video Understanding arXiv:2307.16449
Video-based Generative Performance BenchmarkingonVideoInstruct
gpt-score· 2023-07-31
2.42
best: 4.21 (PPLLaVA-7B)
MovieChat: From Dense Token to Sparse Memory for Long Video Understanding arXiv:2307.16449

Natural Language Processing13 results

Question AnsweringonNExT-QA (Open-ended VideoQA)
Confidence Score· 2023-07-31
2.7
SOTA
MovieChat: From Dense Token to Sparse Memory for Long Video Understanding arXiv:2307.16449
Question AnsweringonMSVD-QA
Accuracy· 2023-07-31
75.2
best: 80.3 (Tarsier (34B))
SOTA
MovieChat: From Dense Token to Sparse Memory for Long Video Understanding arXiv:2307.16449
Question AnsweringonMSRVTT-QA
Accuracy· 2023-07-31
52.7
best: 72.4 (Flash-VStream)
SOTA
MovieChat: From Dense Token to Sparse Memory for Long Video Understanding arXiv:2307.16449
Question AnsweringonActivityNet-QA
Accuracy· 2023-07-31
45.7
best: 61.6 (Tarsier (34B))
SOTA
MovieChat: From Dense Token to Sparse Memory for Long Video Understanding arXiv:2307.16449
Visual Question Answering (VQA)onVideoInstruct
gpt-score· 2023-07-31
3.01
best: 4.21 (PPLLaVA-7B)
SOTA
MovieChat: From Dense Token to Sparse Memory for Long Video Understanding arXiv:2307.16449
Question AnsweringonNExT-QA (Open-ended VideoQA)
Accuracy· 2023-07-31
49.9
best: 61.6 (Flash-VStream)
MovieChat: From Dense Token to Sparse Memory for Long Video Understanding arXiv:2307.16449
Question AnsweringonMSVD-QA
Confidence Score· 2023-07-31
2.9
best: 2.5 (Video LLaMA-7B)
MovieChat: From Dense Token to Sparse Memory for Long Video Understanding arXiv:2307.16449
Question AnsweringonMSRVTT-QA
Confidence Score· 2023-07-31
2.6
best: 1.8 (Video LLaMA-7B)
MovieChat: From Dense Token to Sparse Memory for Long Video Understanding arXiv:2307.16449
Question AnsweringonActivityNet-QA
Confidence Score· 2023-07-31
3.1
best: 1.1 (Video LLaMA)
MovieChat: From Dense Token to Sparse Memory for Long Video Understanding arXiv:2307.16449
Visual Question Answering (VQA)onVideoInstruct
gpt-score· 2023-07-31
2.76
best: 4.21 (PPLLaVA-7B)
MovieChat: From Dense Token to Sparse Memory for Long Video Understanding arXiv:2307.16449
Visual Question Answering (VQA)onVideoInstruct
gpt-score· 2023-07-31
2.93
best: 4.21 (PPLLaVA-7B)
MovieChat: From Dense Token to Sparse Memory for Long Video Understanding arXiv:2307.16449
Visual Question Answering (VQA)onVideoInstruct
gpt-score· 2023-07-31
2.24
best: 4.21 (PPLLaVA-7B)
MovieChat: From Dense Token to Sparse Memory for Long Video Understanding arXiv:2307.16449
Visual Question Answering (VQA)onVideoInstruct
gpt-score· 2023-07-31
2.42
best: 4.21 (PPLLaVA-7B)
MovieChat: From Dense Token to Sparse Memory for Long Video Understanding arXiv:2307.16449

Other1 result

Video-based Generative Performance Benchmarking (Correctness of Information)onVideoInstruct
gpt-score· 2023-07-31
2.76
best: 3.85 (PPLLaVA-7B)
SOTA
MovieChat: From Dense Token to Sparse Memory for Long Video Understanding arXiv:2307.16449