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/Video Chat

Video Chat

Reported on 27 benchmarks across 6 tasks · 1 paper · 22 SOTA

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

Reasoning26 results

  • Video Question AnsweringonActivityNet-QA
    Confidence score· 2023-05-10
    2.2
    SOTA
    VideoChat: Chat-Centric Video UnderstandingarXiv:2305.06355
  • Video Question AnsweringonActivityNet-QA
    Confidence Score· 2023-05-10
    2.2
    best: 1.1 (Video LLaMA)
    SOTA
    VideoChat: Chat-Centric Video UnderstandingarXiv:2305.06355
  • Generative Visual Question AnsweringonVideoInstruct
    Consistency· 2023-05-10
    2.24
    best: 3.81 (PPLLaVA-7B-dpo)
    SOTA
    VideoChat: Chat-Centric Video UnderstandingarXiv:2305.06355
  • Generative Visual Question AnsweringonVideoInstruct
    Contextual Understanding· 2023-05-10
    2.53
    best: 4.21 (PPLLaVA-7B-dpo)
    SOTA
    VideoChat: Chat-Centric Video UnderstandingarXiv:2305.06355
  • Generative Visual Question AnsweringonVideoInstruct
    Correctness of Information· 2023-05-10
    2.23
    best: 3.85 (PPLLaVA-7B-dpo)
    SOTA
    VideoChat: Chat-Centric Video UnderstandingarXiv:2305.06355
  • Generative Visual Question AnsweringonVideoInstruct
    Detail Orientation· 2023-05-10
    2.5
    best: 3.56 (PPLLaVA-7B-dpo)
    SOTA
    VideoChat: Chat-Centric Video UnderstandingarXiv:2305.06355
  • Generative Visual Question AnsweringonVideoInstruct
    mean· 2023-05-10
    2.29
    best: 3.73 (PPLLaVA-7B-dpo)
    SOTA
    VideoChat: Chat-Centric Video UnderstandingarXiv:2305.06355
  • Generative Visual Question AnsweringonVideoInstruct
    gpt-score· 2023-05-10
    2.53
    best: 4.21 (PPLLaVA-7B)
    SOTA
    VideoChat: Chat-Centric Video UnderstandingarXiv:2305.06355
  • Video-based Generative Performance BenchmarkingonVideoInstruct
    Consistency· 2023-05-10
    2.24
    best: 3.81 (PPLLaVA-7B-dpo)
    SOTA
    VideoChat: Chat-Centric Video UnderstandingarXiv:2305.06355
  • Video-based Generative Performance BenchmarkingonVideoInstruct
    Contextual Understanding· 2023-05-10
    2.53
    best: 4.21 (PPLLaVA-7B-dpo)
    SOTA
    VideoChat: Chat-Centric Video UnderstandingarXiv:2305.06355
  • Video-based Generative Performance BenchmarkingonVideoInstruct
    Correctness of Information· 2023-05-10
    2.23
    best: 3.85 (PPLLaVA-7B-dpo)
    SOTA
    VideoChat: Chat-Centric Video UnderstandingarXiv:2305.06355
  • Video-based Generative Performance BenchmarkingonVideoInstruct
    Detail Orientation· 2023-05-10
    2.5
    best: 3.56 (PPLLaVA-7B-dpo)
    SOTA
    VideoChat: Chat-Centric Video UnderstandingarXiv:2305.06355
  • Video-based Generative Performance BenchmarkingonVideoInstruct
    mean· 2023-05-10
    2.29
    best: 3.73 (PPLLaVA-7B-dpo)
    SOTA
    VideoChat: Chat-Centric Video UnderstandingarXiv:2305.06355
  • Video-based Generative Performance BenchmarkingonVideoInstruct
    gpt-score· 2023-05-10
    2.53
    best: 4.21 (PPLLaVA-7B)
    SOTA
    VideoChat: Chat-Centric Video UnderstandingarXiv:2305.06355
  • Video Question AnsweringonActivityNet-QA
    Accuracy· 2023-05-10
    26.5
    best: 61.6 (Tarsier (34B))
    VideoChat: Chat-Centric Video UnderstandingarXiv:2305.06355
  • Video Question AnsweringonActivityNet-QA
    Accuracy· 2023-05-10
    26.5
    best: 61.6 (Tarsier (34B))
    VideoChat: Chat-Centric Video UnderstandingarXiv:2305.06355
  • Generative Visual Question AnsweringonVideoInstruct
    Temporal Understanding· 2023-05-10
    1.94
    best: 3.23 (VLM-RLAIF)
    VideoChat: Chat-Centric Video UnderstandingarXiv:2305.06355
  • Generative Visual Question AnsweringonVideoInstruct
    gpt-score· 2023-05-10
    2.32
    best: 4.21 (PPLLaVA-7B)
    VideoChat: Chat-Centric Video UnderstandingarXiv:2305.06355
  • Generative Visual Question AnsweringonVideoInstruct
    gpt-score· 2023-05-10
    2.5
    best: 4.21 (PPLLaVA-7B)
    VideoChat: Chat-Centric Video UnderstandingarXiv:2305.06355
  • Generative Visual Question AnsweringonVideoInstruct
    gpt-score· 2023-05-10
    1.94
    best: 4.21 (PPLLaVA-7B)
    VideoChat: Chat-Centric Video UnderstandingarXiv:2305.06355
  • Generative Visual Question AnsweringonVideoInstruct
    gpt-score· 2023-05-10
    2.24
    best: 4.21 (PPLLaVA-7B)
    VideoChat: Chat-Centric Video UnderstandingarXiv:2305.06355
  • Video-based Generative Performance BenchmarkingonVideoInstruct
    Temporal Understanding· 2023-05-10
    1.94
    best: 3.23 (VLM-RLAIF)
    VideoChat: Chat-Centric Video UnderstandingarXiv:2305.06355
  • Video-based Generative Performance BenchmarkingonVideoInstruct
    gpt-score· 2023-05-10
    2.32
    best: 4.21 (PPLLaVA-7B)
    VideoChat: Chat-Centric Video UnderstandingarXiv:2305.06355
  • Video-based Generative Performance BenchmarkingonVideoInstruct
    gpt-score· 2023-05-10
    2.5
    best: 4.21 (PPLLaVA-7B)
    VideoChat: Chat-Centric Video UnderstandingarXiv:2305.06355
  • Video-based Generative Performance BenchmarkingonVideoInstruct
    gpt-score· 2023-05-10
    1.94
    best: 4.21 (PPLLaVA-7B)
    VideoChat: Chat-Centric Video UnderstandingarXiv:2305.06355
  • Video-based Generative Performance BenchmarkingonVideoInstruct
    gpt-score· 2023-05-10
    2.24
    best: 4.21 (PPLLaVA-7B)
    VideoChat: Chat-Centric Video UnderstandingarXiv:2305.06355

Natural Language Processing13 results

  • Question AnsweringonActivityNet-QA
    Confidence Score· 2023-05-10
    2.2
    best: 1.1 (Video LLaMA)
    SOTA
    VideoChat: Chat-Centric Video UnderstandingarXiv:2305.06355
  • Visual Question Answering (VQA)onVideoInstruct
    Consistency· 2023-05-10
    2.24
    best: 3.81 (PPLLaVA-7B-dpo)
    SOTA
    VideoChat: Chat-Centric Video UnderstandingarXiv:2305.06355
  • Visual Question Answering (VQA)onVideoInstruct
    Contextual Understanding· 2023-05-10
    2.53
    best: 4.21 (PPLLaVA-7B-dpo)
    SOTA
    VideoChat: Chat-Centric Video UnderstandingarXiv:2305.06355
  • Visual Question Answering (VQA)onVideoInstruct
    Correctness of Information· 2023-05-10
    2.23
    best: 3.85 (PPLLaVA-7B-dpo)
    SOTA
    VideoChat: Chat-Centric Video UnderstandingarXiv:2305.06355
  • Visual Question Answering (VQA)onVideoInstruct
    Detail Orientation· 2023-05-10
    2.5
    best: 3.56 (PPLLaVA-7B-dpo)
    SOTA
    VideoChat: Chat-Centric Video UnderstandingarXiv:2305.06355
  • Visual Question Answering (VQA)onVideoInstruct
    mean· 2023-05-10
    2.29
    best: 3.73 (PPLLaVA-7B-dpo)
    SOTA
    VideoChat: Chat-Centric Video UnderstandingarXiv:2305.06355
  • Visual Question Answering (VQA)onVideoInstruct
    gpt-score· 2023-05-10
    2.53
    best: 4.21 (PPLLaVA-7B)
    SOTA
    VideoChat: Chat-Centric Video UnderstandingarXiv:2305.06355
  • Question AnsweringonActivityNet-QA
    Accuracy· 2023-05-10
    26.5
    best: 61.6 (Tarsier (34B))
    VideoChat: Chat-Centric Video UnderstandingarXiv:2305.06355
  • Visual Question Answering (VQA)onVideoInstruct
    Temporal Understanding· 2023-05-10
    1.94
    best: 3.23 (VLM-RLAIF)
    VideoChat: Chat-Centric Video UnderstandingarXiv:2305.06355
  • Visual Question Answering (VQA)onVideoInstruct
    gpt-score· 2023-05-10
    2.32
    best: 4.21 (PPLLaVA-7B)
    VideoChat: Chat-Centric Video UnderstandingarXiv:2305.06355
  • Visual Question Answering (VQA)onVideoInstruct
    gpt-score· 2023-05-10
    2.5
    best: 4.21 (PPLLaVA-7B)
    VideoChat: Chat-Centric Video UnderstandingarXiv:2305.06355
  • Visual Question Answering (VQA)onVideoInstruct
    gpt-score· 2023-05-10
    1.94
    best: 4.21 (PPLLaVA-7B)
    VideoChat: Chat-Centric Video UnderstandingarXiv:2305.06355
  • Visual Question Answering (VQA)onVideoInstruct
    gpt-score· 2023-05-10
    2.24
    best: 4.21 (PPLLaVA-7B)
    VideoChat: Chat-Centric Video UnderstandingarXiv:2305.06355

Other1 result

  • Video-based Generative Performance Benchmarking (Correctness of Information)onVideoInstruct
    gpt-score· 2023-05-10
    2.32
    best: 3.85 (PPLLaVA-7B)
    SOTA
    VideoChat: Chat-Centric Video UnderstandingarXiv:2305.06355