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/SeViLA (4B)

SeViLA (4B)

Reported on 6 benchmarks across 2 tasks · 1 paper · 4 SOTA

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

Natural Language Processing3 results

  • Question AnsweringonIntentQA
    Accuracy· uses extra data· 2023-05-11
    60.9
    best: 71.5 (ENTER)
    SOTA
    Self-Chained Image-Language Model for Video Localization and Question AnsweringarXiv:2305.06988
  • Question AnsweringonEgoSchema (subset)
    Accuracy· 2023-05-11
    25.7
    best: 68.6 (Tarsier (34B))
    SOTA
    Self-Chained Image-Language Model for Video Localization and Question AnsweringarXiv:2305.06988
  • Question AnsweringonEgoSchema (fullset)
    Accuracy· 2023-05-11
    22.7
    best: 71.14 (BIMBA-LLaVA-Qwen2-7B)
    Self-Chained Image-Language Model for Video Localization and Question AnsweringarXiv:2305.06988

Reasoning3 results

  • Video Question AnsweringonIntentQA
    Accuracy· uses extra data· 2023-05-11
    60.9
    best: 71.5 (ENTER)
    SOTA
    Self-Chained Image-Language Model for Video Localization and Question AnsweringarXiv:2305.06988
  • Video Question AnsweringonEgoSchema (subset)
    Accuracy· 2023-05-11
    25.7
    best: 68.6 (Tarsier (34B))
    SOTA
    Self-Chained Image-Language Model for Video Localization and Question AnsweringarXiv:2305.06988
  • Video Question AnsweringonEgoSchema (fullset)
    Accuracy· 2023-05-11
    22.7
    best: 71.14 (BIMBA-LLaVA-Qwen2-7B)
    Self-Chained Image-Language Model for Video Localization and Question AnsweringarXiv:2305.06988