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/Flash-VStream

Flash-VStream

Reported on 14 benchmarks across 2 tasks · 1 paper · 5 SOTA

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

Natural Language Processing8 results

  • Question AnsweringonNExT-QA (Open-ended VideoQA)
    Accuracy· 2024-06-12
    61.6
    SOTA
    Flash-VStream: Memory-Based Real-Time Understanding for Long Video StreamsarXiv:2406.08085
  • Question AnsweringonMSVD-QA
    Accuracy· 2024-06-12
    80.3
    SOTA
    Flash-VStream: Memory-Based Real-Time Understanding for Long Video StreamsarXiv:2406.08085
  • Question AnsweringonMSRVTT-QA
    Accuracy· 2024-06-12
    72.4
    SOTA
    Flash-VStream: Memory-Based Real-Time Understanding for Long Video StreamsarXiv:2406.08085
  • Question AnsweringonNExT-QA (Open-ended VideoQA)
    Confidence Score· 2024-06-12
    3.4
    best: 2.7 (MovieChat)
    Flash-VStream: Memory-Based Real-Time Understanding for Long Video StreamsarXiv:2406.08085
  • Question AnsweringonMSVD-QA
    Confidence Score· 2024-06-12
    3.9
    best: 2.5 (Video LLaMA-7B)
    Flash-VStream: Memory-Based Real-Time Understanding for Long Video StreamsarXiv:2406.08085
  • Question AnsweringonMSRVTT-QA
    Confidence Score· 2024-06-12
    3.4
    best: 1.8 (Video LLaMA-7B)
    Flash-VStream: Memory-Based Real-Time Understanding for Long Video StreamsarXiv:2406.08085
  • Question AnsweringonActivityNet-QA
    Accuracy· 2024-06-12
    51.9
    best: 61.6 (Tarsier (34B))
    Flash-VStream: Memory-Based Real-Time Understanding for Long Video StreamsarXiv:2406.08085
  • Question AnsweringonActivityNet-QA
    Confidence Score· 2024-06-12
    3.4
    best: 1.1 (Video LLaMA)
    Flash-VStream: Memory-Based Real-Time Understanding for Long Video StreamsarXiv:2406.08085

Reasoning6 results

  • Video Question AnsweringonMSVD-QA
    Accuracy· 2024-06-12
    80.3
    SOTA
    Flash-VStream: Memory-Based Real-Time Understanding for Long Video StreamsarXiv:2406.08085
  • Video Question AnsweringonMSRVTT-QA
    Accuracy· 2024-06-12
    72.4
    SOTA
    Flash-VStream: Memory-Based Real-Time Understanding for Long Video StreamsarXiv:2406.08085
  • Video Question AnsweringonMSVD-QA
    Confidence Score· 2024-06-12
    3.9
    best: 2.5 (Video LLaMA-7B)
    Flash-VStream: Memory-Based Real-Time Understanding for Long Video StreamsarXiv:2406.08085
  • Video Question AnsweringonMSRVTT-QA
    Confidence Score· 2024-06-12
    3.4
    best: 1.8 (Video LLaMA-7B)
    Flash-VStream: Memory-Based Real-Time Understanding for Long Video StreamsarXiv:2406.08085
  • Video Question AnsweringonActivityNet-QA
    Accuracy· 2024-06-12
    51.9
    best: 61.6 (Tarsier (34B))
    Flash-VStream: Memory-Based Real-Time Understanding for Long Video StreamsarXiv:2406.08085
  • Video Question AnsweringonActivityNet-QA
    Confidence Score· 2024-06-12
    3.4
    best: 1.1 (Video LLaMA)
    Flash-VStream: Memory-Based Real-Time Understanding for Long Video StreamsarXiv:2406.08085