TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

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

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

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

Models/MiniGPT4-video-7B

MiniGPT4-video-7B

Reported on 14 benchmarks across 6 tasks · 1 paper

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

Reasoning15 results

  • Video Question AnsweringonMSVD-QA
    Accuracy· 2024-04-04
    73.92
    best: 80.3 (Tarsier (34B))
    MiniGPT4-Video: Advancing Multimodal LLMs for Video Understanding with Interleaved Visual-Textual TokensarXiv:2404.03413
  • Video Question AnsweringonTGIF-QA
    Accuracy· 2024-04-04
    72.22
    best: 82.5 (Tarsier (34B))
    MiniGPT4-Video: Advancing Multimodal LLMs for Video Understanding with Interleaved Visual-Textual TokensarXiv:2404.03413
  • Video Question AnsweringonMSRVTT-QA
    Accuracy· 2024-04-04
    59.73
    best: 72.4 (Flash-VStream)
    MiniGPT4-Video: Advancing Multimodal LLMs for Video Understanding with Interleaved Visual-Textual TokensarXiv:2404.03413
  • Video Question AnsweringonTVQA
    Accuracy· 2024-04-04
    54.21
    best: 82.2 (LLaMA-VQA)
    MiniGPT4-Video: Advancing Multimodal LLMs for Video Understanding with Interleaved Visual-Textual TokensarXiv:2404.03413
  • Video Question AnsweringonActivityNet-QA
    Accuracy· 2024-04-04
    46.3
    best: 61.6 (Tarsier (34B))
    MiniGPT4-Video: Advancing Multimodal LLMs for Video Understanding with Interleaved Visual-Textual TokensarXiv:2404.03413
  • Generative Visual Question AnsweringonVideoInstruct
    gpt-score· 2024-04-04
    3.57
    best: 4.21 (PPLLaVA-7B)
    MiniGPT4-Video: Advancing Multimodal LLMs for Video Understanding with Interleaved Visual-Textual TokensarXiv:2404.03413
  • Generative Visual Question AnsweringonVideoInstruct
    gpt-score· 2024-04-04
    3.08
    best: 4.21 (PPLLaVA-7B)
    MiniGPT4-Video: Advancing Multimodal LLMs for Video Understanding with Interleaved Visual-Textual TokensarXiv:2404.03413
  • Generative Visual Question AnsweringonVideoInstruct
    gpt-score· 2024-04-04
    3.02
    best: 4.21 (PPLLaVA-7B)
    MiniGPT4-Video: Advancing Multimodal LLMs for Video Understanding with Interleaved Visual-Textual TokensarXiv:2404.03413
  • Generative Visual Question AnsweringonVideoInstruct
    gpt-score· 2024-04-04
    2.65
    best: 4.21 (PPLLaVA-7B)
    MiniGPT4-Video: Advancing Multimodal LLMs for Video Understanding with Interleaved Visual-Textual TokensarXiv:2404.03413
  • Generative Visual Question AnsweringonVideoInstruct
    gpt-score· 2024-04-04
    2.67
    best: 4.21 (PPLLaVA-7B)
    MiniGPT4-Video: Advancing Multimodal LLMs for Video Understanding with Interleaved Visual-Textual TokensarXiv:2404.03413
  • Video-based Generative Performance BenchmarkingonVideoInstruct
    gpt-score· 2024-04-04
    3.57
    best: 4.21 (PPLLaVA-7B)
    MiniGPT4-Video: Advancing Multimodal LLMs for Video Understanding with Interleaved Visual-Textual TokensarXiv:2404.03413
  • Video-based Generative Performance BenchmarkingonVideoInstruct
    gpt-score· 2024-04-04
    3.08
    best: 4.21 (PPLLaVA-7B)
    MiniGPT4-Video: Advancing Multimodal LLMs for Video Understanding with Interleaved Visual-Textual TokensarXiv:2404.03413
  • Video-based Generative Performance BenchmarkingonVideoInstruct
    gpt-score· 2024-04-04
    3.02
    best: 4.21 (PPLLaVA-7B)
    MiniGPT4-Video: Advancing Multimodal LLMs for Video Understanding with Interleaved Visual-Textual TokensarXiv:2404.03413
  • Video-based Generative Performance BenchmarkingonVideoInstruct
    gpt-score· 2024-04-04
    2.65
    best: 4.21 (PPLLaVA-7B)
    MiniGPT4-Video: Advancing Multimodal LLMs for Video Understanding with Interleaved Visual-Textual TokensarXiv:2404.03413
  • Video-based Generative Performance BenchmarkingonVideoInstruct
    gpt-score· 2024-04-04
    2.67
    best: 4.21 (PPLLaVA-7B)
    MiniGPT4-Video: Advancing Multimodal LLMs for Video Understanding with Interleaved Visual-Textual TokensarXiv:2404.03413

Natural Language Processing10 results

  • Question AnsweringonMSVD-QA
    Accuracy· 2024-04-04
    73.92
    best: 80.3 (Tarsier (34B))
    MiniGPT4-Video: Advancing Multimodal LLMs for Video Understanding with Interleaved Visual-Textual TokensarXiv:2404.03413
  • Question AnsweringonTGIF-QA
    Accuracy· 2024-04-04
    72.22
    best: 82.5 (Tarsier (34B))
    MiniGPT4-Video: Advancing Multimodal LLMs for Video Understanding with Interleaved Visual-Textual TokensarXiv:2404.03413
  • Question AnsweringonMSRVTT-QA
    Accuracy· 2024-04-04
    59.73
    best: 72.4 (Flash-VStream)
    MiniGPT4-Video: Advancing Multimodal LLMs for Video Understanding with Interleaved Visual-Textual TokensarXiv:2404.03413
  • Question AnsweringonTVQA
    Accuracy· 2024-04-04
    54.21
    best: 59.7 (FrozenBiLM (with speech))
    MiniGPT4-Video: Advancing Multimodal LLMs for Video Understanding with Interleaved Visual-Textual TokensarXiv:2404.03413
  • Question AnsweringonActivityNet-QA
    Accuracy· 2024-04-04
    46.3
    best: 61.6 (Tarsier (34B))
    MiniGPT4-Video: Advancing Multimodal LLMs for Video Understanding with Interleaved Visual-Textual TokensarXiv:2404.03413
  • Visual Question Answering (VQA)onVideoInstruct
    gpt-score· 2024-04-04
    3.57
    best: 4.21 (PPLLaVA-7B)
    MiniGPT4-Video: Advancing Multimodal LLMs for Video Understanding with Interleaved Visual-Textual TokensarXiv:2404.03413
  • Visual Question Answering (VQA)onVideoInstruct
    gpt-score· 2024-04-04
    3.08
    best: 4.21 (PPLLaVA-7B)
    MiniGPT4-Video: Advancing Multimodal LLMs for Video Understanding with Interleaved Visual-Textual TokensarXiv:2404.03413
  • Visual Question Answering (VQA)onVideoInstruct
    gpt-score· 2024-04-04
    3.02
    best: 4.21 (PPLLaVA-7B)
    MiniGPT4-Video: Advancing Multimodal LLMs for Video Understanding with Interleaved Visual-Textual TokensarXiv:2404.03413
  • Visual Question Answering (VQA)onVideoInstruct
    gpt-score· 2024-04-04
    2.65
    best: 4.21 (PPLLaVA-7B)
    MiniGPT4-Video: Advancing Multimodal LLMs for Video Understanding with Interleaved Visual-Textual TokensarXiv:2404.03413
  • Visual Question Answering (VQA)onVideoInstruct
    gpt-score· 2024-04-04
    2.67
    best: 4.21 (PPLLaVA-7B)
    MiniGPT4-Video: Advancing Multimodal LLMs for Video Understanding with Interleaved Visual-Textual TokensarXiv:2404.03413

Other1 result

  • Video-based Generative Performance Benchmarking (Correctness of Information)onVideoInstruct
    gpt-score· 2024-04-04
    3.08
    best: 3.85 (PPLLaVA-7B)
    MiniGPT4-Video: Advancing Multimodal LLMs for Video Understanding with Interleaved Visual-Textual TokensarXiv:2404.03413