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/EgoVLPv2

EgoVLPv2

Reported on 9 benchmarks across 6 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 Processing5 results

  • Question AnsweringonEgoTaskQA
    Direct· 2023-07-11
    46.26
    SOTA
    EgoVLPv2: Egocentric Video-Language Pre-training with Fusion in the BackbonearXiv:2307.05463
  • Natural Language QueriesonEgo4D
    R@5 IoU=0.3· 2023-07-11
    23.8
    best: 45.63 (DeCafNet-100%)
    SOTA
    EgoVLPv2: Egocentric Video-Language Pre-training with Fusion in the BackbonearXiv:2307.05463
  • Natural Language QueriesonEgo4D
    R@5 IoU=0.5· 2023-07-11
    16.11
    best: 33.93 (DeCafNet-100%)
    SOTA
    EgoVLPv2: Egocentric Video-Language Pre-training with Fusion in the BackbonearXiv:2307.05463
  • Natural Language QueriesonEgo4D
    R@1 IoU=0.3· 2023-07-11
    12.95
    best: 28.05 (EgoVideo)
    EgoVLPv2: Egocentric Video-Language Pre-training with Fusion in the BackbonearXiv:2307.05463
  • Natural Language QueriesonEgo4D
    R@1 IoU=0.5· 2023-07-11
    7.91
    best: 19.31 (EgoVideo)
    EgoVLPv2: Egocentric Video-Language Pre-training with Fusion in the BackbonearXiv:2307.05463

Computer Vision2 results

  • VideoonQuery-Focused Video Summarization Dataset
    F1 (avg)· 2023-07-11
    52.08
    SOTA
    EgoVLPv2: Egocentric Video-Language Pre-training with Fusion in the BackbonearXiv:2307.05463
  • Video SummarizationonQuery-Focused Video Summarization Dataset
    F1 (avg)· 2023-07-11
    52.08
    SOTA
    EgoVLPv2: Egocentric Video-Language Pre-training with Fusion in the BackbonearXiv:2307.05463

Robots1 result

  • Activity RecognitiononCharades-Ego
    mAP· 2023-07-11
    34.1
    best: 36.1 (LaViLa (Finetuned, TimeSformer-L))
    EgoVLPv2: Egocentric Video-Language Pre-training with Fusion in the BackbonearXiv:2307.05463

Time Series1 result

  • Action RecognitiononCharades-Ego
    mAP· 2023-07-11
    34.1
    best: 36.1 (LaViLa (Finetuned, TimeSformer-L))
    EgoVLPv2: Egocentric Video-Language Pre-training with Fusion in the BackbonearXiv:2307.05463