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/IG-VLM

IG-VLM

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 Processing7 results

  • Question AnsweringonTGIF-QA
    Accuracy· 2024-03-27
    79.1
    best: 82.5 (Tarsier (34B))
    SOTA
    An Image Grid Can Be Worth a Video: Zero-shot Video Question Answering Using a VLMarXiv:2403.18406
  • Question AnsweringonIntentQA
    Accuracy· 2024-03-27
    65.3
    best: 71.5 (ENTER)
    SOTA
    An Image Grid Can Be Worth a Video: Zero-shot Video Question Answering Using a VLMarXiv:2403.18406
  • Question AnsweringonActivityNet-QA
    Accuracy· 2024-03-27
    58.4
    best: 61.6 (Tarsier (34B))
    SOTA
    An Image Grid Can Be Worth a Video: Zero-shot Video Question Answering Using a VLMarXiv:2403.18406
  • Question AnsweringonTGIF-QA
    Confidence Score· 2024-03-27
    4.2
    best: 2.3 (Video Chat-7B)
    An Image Grid Can Be Worth a Video: Zero-shot Video Question Answering Using a VLMarXiv:2403.18406
  • Question AnsweringonMSRVTT-QA
    Accuracy· 2024-03-27
    63.8
    best: 72.4 (Flash-VStream)
    An Image Grid Can Be Worth a Video: Zero-shot Video Question Answering Using a VLMarXiv:2403.18406
  • Question AnsweringonMSRVTT-QA
    Confidence Score· 2024-03-27
    3.5
    best: 1.8 (Video LLaMA-7B)
    An Image Grid Can Be Worth a Video: Zero-shot Video Question Answering Using a VLMarXiv:2403.18406
  • Question AnsweringonActivityNet-QA
    Confidence Score· 2024-03-27
    3.5
    best: 1.1 (Video LLaMA)
    An Image Grid Can Be Worth a Video: Zero-shot Video Question Answering Using a VLMarXiv:2403.18406

Reasoning7 results

  • Video Question AnsweringonTGIF-QA
    Accuracy· 2024-03-27
    79.1
    best: 82.5 (Tarsier (34B))
    SOTA
    An Image Grid Can Be Worth a Video: Zero-shot Video Question Answering Using a VLMarXiv:2403.18406
  • Video Question AnsweringonIntentQA
    Accuracy· 2024-03-27
    65.3
    best: 71.5 (ENTER)
    SOTA
    An Image Grid Can Be Worth a Video: Zero-shot Video Question Answering Using a VLMarXiv:2403.18406
  • Video Question AnsweringonTGIF-QA
    Confidence Score· 2024-03-27
    4.2
    best: 2.3 (Video Chat-7B)
    An Image Grid Can Be Worth a Video: Zero-shot Video Question Answering Using a VLMarXiv:2403.18406
  • Video Question AnsweringonMSRVTT-QA
    Accuracy· 2024-03-27
    63.8
    best: 72.4 (Flash-VStream)
    An Image Grid Can Be Worth a Video: Zero-shot Video Question Answering Using a VLMarXiv:2403.18406
  • Video Question AnsweringonMSRVTT-QA
    Confidence Score· 2024-03-27
    3.5
    best: 1.8 (Video LLaMA-7B)
    An Image Grid Can Be Worth a Video: Zero-shot Video Question Answering Using a VLMarXiv:2403.18406
  • Video Question AnsweringonActivityNet-QA
    Accuracy· 2024-03-27
    58.4
    best: 61.6 (Tarsier (34B))
    An Image Grid Can Be Worth a Video: Zero-shot Video Question Answering Using a VLMarXiv:2403.18406
  • Video Question AnsweringonActivityNet-QA
    Confidence Score· 2024-03-27
    3.5
    best: 1.1 (Video LLaMA)
    An Image Grid Can Be Worth a Video: Zero-shot Video Question Answering Using a VLMarXiv:2403.18406