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/AVFusion

AVFusion

Reported on 44 benchmarks across 4 tasks · 1 paper · 4 SOTA

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

Computer Vision33 results

  • VideoonTHUMOS'14
    mAP IOU@0.5· 2021-06-27
    57.18
    SOTA
    Hear Me Out: Fusional Approaches for Audio Augmented Temporal Action LocalizationarXiv:2106.14118
  • Temporal Action LocalizationonTHUMOS'14
    mAP IOU@0.5· 2021-06-27
    57.18
    SOTA
    Hear Me Out: Fusional Approaches for Audio Augmented Temporal Action LocalizationarXiv:2106.14118
  • Action LocalizationonTHUMOS'14
    mAP IOU@0.5· 2021-06-27
    57.18
    SOTA
    Hear Me Out: Fusional Approaches for Audio Augmented Temporal Action LocalizationarXiv:2106.14118
  • VideoonActivityNet-1.3
    mAP· 2021-06-27
    36.82
    best: 42.9 (RDFA-S6 (InternVideo2-6B))
    Hear Me Out: Fusional Approaches for Audio Augmented Temporal Action LocalizationarXiv:2106.14118
  • VideoonActivityNet-1.3
    mAP IOU@0.5· 2021-06-27
    54.34
    best: 64.1 (RDFA-S6 (InternVideo2-6B))
    Hear Me Out: Fusional Approaches for Audio Augmented Temporal Action LocalizationarXiv:2106.14118
  • VideoonActivityNet-1.3
    mAP IOU@0.75· 2021-06-27
    37.66
    best: 44 (RDFA-S6 (InternVideo2-6B))
    Hear Me Out: Fusional Approaches for Audio Augmented Temporal Action LocalizationarXiv:2106.14118
  • VideoonActivityNet-1.3
    mAP IOU@0.95· 2021-06-27
    8.93
    best: 10.85 (AdaTAD (VideoMAEv2-giant))
    Hear Me Out: Fusional Approaches for Audio Augmented Temporal Action LocalizationarXiv:2106.14118
  • VideoonTHUMOS’14
    Avg mAP (0.3:0.7)· uses extra data· 2021-06-27
    53.3
    best: 76.9 (AdaTAD (VideoMAEv2-giant))
    Hear Me Out: Fusional Approaches for Audio Augmented Temporal Action LocalizationarXiv:2106.14118
  • VideoonTHUMOS’14
    mAP IOU@0.3· uses extra data· 2021-06-27
    70.1
    best: 89.7 (AdaTAD (VideoMAEv2-giant))
    Hear Me Out: Fusional Approaches for Audio Augmented Temporal Action LocalizationarXiv:2106.14118
  • VideoonTHUMOS’14
    mAP IOU@0.4· uses extra data· 2021-06-27
    64.9
    best: 86.7 (AdaTAD (VideoMAEv2-giant))
    Hear Me Out: Fusional Approaches for Audio Augmented Temporal Action LocalizationarXiv:2106.14118
  • VideoonTHUMOS’14
    mAP IOU@0.5· uses extra data· 2021-06-27
    57.1
    best: 80.9 (AdaTAD (VideoMAEv2-giant))
    Hear Me Out: Fusional Approaches for Audio Augmented Temporal Action LocalizationarXiv:2106.14118
  • VideoonTHUMOS’14
    mAP IOU@0.6· uses extra data· 2021-06-27
    45.4
    best: 71 (AdaTAD (VideoMAEv2-giant))
    Hear Me Out: Fusional Approaches for Audio Augmented Temporal Action LocalizationarXiv:2106.14118
  • VideoonTHUMOS’14
    mAP IOU@0.7· uses extra data· 2021-06-27
    28.8
    best: 56.1 (AdaTAD (VideoMAEv2-giant))
    Hear Me Out: Fusional Approaches for Audio Augmented Temporal Action LocalizationarXiv:2106.14118
  • Temporal Action LocalizationonActivityNet-1.3
    mAP· 2021-06-27
    36.82
    best: 42.9 (RDFA-S6 (InternVideo2-6B))
    Hear Me Out: Fusional Approaches for Audio Augmented Temporal Action LocalizationarXiv:2106.14118
  • Temporal Action LocalizationonActivityNet-1.3
    mAP IOU@0.5· 2021-06-27
    54.34
    best: 64.1 (RDFA-S6 (InternVideo2-6B))
    Hear Me Out: Fusional Approaches for Audio Augmented Temporal Action LocalizationarXiv:2106.14118
  • Temporal Action LocalizationonActivityNet-1.3
    mAP IOU@0.75· 2021-06-27
    37.66
    best: 44 (RDFA-S6 (InternVideo2-6B))
    Hear Me Out: Fusional Approaches for Audio Augmented Temporal Action LocalizationarXiv:2106.14118
  • Temporal Action LocalizationonActivityNet-1.3
    mAP IOU@0.95· 2021-06-27
    8.93
    best: 10.85 (AdaTAD (VideoMAEv2-giant))
    Hear Me Out: Fusional Approaches for Audio Augmented Temporal Action LocalizationarXiv:2106.14118
  • Temporal Action LocalizationonTHUMOS’14
    Avg mAP (0.3:0.7)· uses extra data· 2021-06-27
    53.3
    best: 76.9 (AdaTAD (VideoMAEv2-giant))
    Hear Me Out: Fusional Approaches for Audio Augmented Temporal Action LocalizationarXiv:2106.14118
  • Temporal Action LocalizationonTHUMOS’14
    mAP IOU@0.3· uses extra data· 2021-06-27
    70.1
    best: 89.7 (AdaTAD (VideoMAEv2-giant))
    Hear Me Out: Fusional Approaches for Audio Augmented Temporal Action LocalizationarXiv:2106.14118
  • Temporal Action LocalizationonTHUMOS’14
    mAP IOU@0.4· uses extra data· 2021-06-27
    64.9
    best: 86.7 (AdaTAD (VideoMAEv2-giant))
    Hear Me Out: Fusional Approaches for Audio Augmented Temporal Action LocalizationarXiv:2106.14118
  • Temporal Action LocalizationonTHUMOS’14
    mAP IOU@0.5· uses extra data· 2021-06-27
    57.1
    best: 80.9 (AdaTAD (VideoMAEv2-giant))
    Hear Me Out: Fusional Approaches for Audio Augmented Temporal Action LocalizationarXiv:2106.14118
  • Temporal Action LocalizationonTHUMOS’14
    mAP IOU@0.6· uses extra data· 2021-06-27
    45.4
    best: 71 (AdaTAD (VideoMAEv2-giant))
    Hear Me Out: Fusional Approaches for Audio Augmented Temporal Action LocalizationarXiv:2106.14118
  • Temporal Action LocalizationonTHUMOS’14
    mAP IOU@0.7· uses extra data· 2021-06-27
    28.8
    best: 56.1 (AdaTAD (VideoMAEv2-giant))
    Hear Me Out: Fusional Approaches for Audio Augmented Temporal Action LocalizationarXiv:2106.14118
  • Action LocalizationonActivityNet-1.3
    mAP· 2021-06-27
    36.82
    best: 42.9 (RDFA-S6 (InternVideo2-6B))
    Hear Me Out: Fusional Approaches for Audio Augmented Temporal Action LocalizationarXiv:2106.14118
  • Action LocalizationonActivityNet-1.3
    mAP IOU@0.5· 2021-06-27
    54.34
    best: 64.1 (RDFA-S6 (InternVideo2-6B))
    Hear Me Out: Fusional Approaches for Audio Augmented Temporal Action LocalizationarXiv:2106.14118
  • Action LocalizationonActivityNet-1.3
    mAP IOU@0.75· 2021-06-27
    37.66
    best: 44 (RDFA-S6 (InternVideo2-6B))
    Hear Me Out: Fusional Approaches for Audio Augmented Temporal Action LocalizationarXiv:2106.14118
  • Action LocalizationonActivityNet-1.3
    mAP IOU@0.95· 2021-06-27
    8.93
    best: 10.85 (AdaTAD (VideoMAEv2-giant))
    Hear Me Out: Fusional Approaches for Audio Augmented Temporal Action LocalizationarXiv:2106.14118
  • Action LocalizationonTHUMOS’14
    Avg mAP (0.3:0.7)· uses extra data· 2021-06-27
    53.3
    best: 76.9 (AdaTAD (VideoMAEv2-giant))
    Hear Me Out: Fusional Approaches for Audio Augmented Temporal Action LocalizationarXiv:2106.14118
  • Action LocalizationonTHUMOS’14
    mAP IOU@0.3· uses extra data· 2021-06-27
    70.1
    best: 89.7 (AdaTAD (VideoMAEv2-giant))
    Hear Me Out: Fusional Approaches for Audio Augmented Temporal Action LocalizationarXiv:2106.14118
  • Action LocalizationonTHUMOS’14
    mAP IOU@0.4· uses extra data· 2021-06-27
    64.9
    best: 86.7 (AdaTAD (VideoMAEv2-giant))
    Hear Me Out: Fusional Approaches for Audio Augmented Temporal Action LocalizationarXiv:2106.14118
  • Action LocalizationonTHUMOS’14
    mAP IOU@0.5· uses extra data· 2021-06-27
    57.1
    best: 80.9 (AdaTAD (VideoMAEv2-giant))
    Hear Me Out: Fusional Approaches for Audio Augmented Temporal Action LocalizationarXiv:2106.14118
  • Action LocalizationonTHUMOS’14
    mAP IOU@0.6· uses extra data· 2021-06-27
    45.4
    best: 71 (AdaTAD (VideoMAEv2-giant))
    Hear Me Out: Fusional Approaches for Audio Augmented Temporal Action LocalizationarXiv:2106.14118
  • Action LocalizationonTHUMOS’14
    mAP IOU@0.7· uses extra data· 2021-06-27
    28.8
    best: 56.1 (AdaTAD (VideoMAEv2-giant))
    Hear Me Out: Fusional Approaches for Audio Augmented Temporal Action LocalizationarXiv:2106.14118

Methodology11 results

  • Zero-Shot LearningonTHUMOS'14
    mAP IOU@0.5· 2021-06-27
    57.18
    SOTA
    Hear Me Out: Fusional Approaches for Audio Augmented Temporal Action LocalizationarXiv:2106.14118
  • Zero-Shot LearningonActivityNet-1.3
    mAP· 2021-06-27
    36.82
    best: 42.9 (RDFA-S6 (InternVideo2-6B))
    Hear Me Out: Fusional Approaches for Audio Augmented Temporal Action LocalizationarXiv:2106.14118
  • Zero-Shot LearningonActivityNet-1.3
    mAP IOU@0.5· 2021-06-27
    54.34
    best: 64.1 (RDFA-S6 (InternVideo2-6B))
    Hear Me Out: Fusional Approaches for Audio Augmented Temporal Action LocalizationarXiv:2106.14118
  • Zero-Shot LearningonActivityNet-1.3
    mAP IOU@0.75· 2021-06-27
    37.66
    best: 44 (RDFA-S6 (InternVideo2-6B))
    Hear Me Out: Fusional Approaches for Audio Augmented Temporal Action LocalizationarXiv:2106.14118
  • Zero-Shot LearningonActivityNet-1.3
    mAP IOU@0.95· 2021-06-27
    8.93
    best: 10.85 (AdaTAD (VideoMAEv2-giant))
    Hear Me Out: Fusional Approaches for Audio Augmented Temporal Action LocalizationarXiv:2106.14118
  • Zero-Shot LearningonTHUMOS’14
    Avg mAP (0.3:0.7)· uses extra data· 2021-06-27
    53.3
    best: 76.9 (AdaTAD (VideoMAEv2-giant))
    Hear Me Out: Fusional Approaches for Audio Augmented Temporal Action LocalizationarXiv:2106.14118
  • Zero-Shot LearningonTHUMOS’14
    mAP IOU@0.3· uses extra data· 2021-06-27
    70.1
    best: 89.7 (AdaTAD (VideoMAEv2-giant))
    Hear Me Out: Fusional Approaches for Audio Augmented Temporal Action LocalizationarXiv:2106.14118
  • Zero-Shot LearningonTHUMOS’14
    mAP IOU@0.4· uses extra data· 2021-06-27
    64.9
    best: 86.7 (AdaTAD (VideoMAEv2-giant))
    Hear Me Out: Fusional Approaches for Audio Augmented Temporal Action LocalizationarXiv:2106.14118
  • Zero-Shot LearningonTHUMOS’14
    mAP IOU@0.5· uses extra data· 2021-06-27
    57.1
    best: 80.9 (AdaTAD (VideoMAEv2-giant))
    Hear Me Out: Fusional Approaches for Audio Augmented Temporal Action LocalizationarXiv:2106.14118
  • Zero-Shot LearningonTHUMOS’14
    mAP IOU@0.6· uses extra data· 2021-06-27
    45.4
    best: 71 (AdaTAD (VideoMAEv2-giant))
    Hear Me Out: Fusional Approaches for Audio Augmented Temporal Action LocalizationarXiv:2106.14118
  • Zero-Shot LearningonTHUMOS’14
    mAP IOU@0.7· uses extra data· 2021-06-27
    28.8
    best: 56.1 (AdaTAD (VideoMAEv2-giant))
    Hear Me Out: Fusional Approaches for Audio Augmented Temporal Action LocalizationarXiv:2106.14118