Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/MBT (AV)

MBT (AV)

Reported on 8 benchmarks across 3 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 Vision6 results

VideoonKinetics-Sounds
Top 1 Accuracy· 2021-06-30
85
best: 93.3 (CA2ST(B/16))
SOTA
Attention Bottlenecks for Multimodal Fusion arXiv:2107.00135
VideoonKinetics-Sounds
Top 5 Accuracy· 2021-06-30
96.8
SOTA
Attention Bottlenecks for Multimodal Fusion arXiv:2107.00135
VideoonMiT
Top 1 Accuracy· 2021-06-30
37.3
best: 53.1 (OmniVec2)
Attention Bottlenecks for Multimodal Fusion arXiv:2107.00135
VideoonMiT
Top 5 Accuracy· 2021-06-30
61.2
best: 78.2 (UMT-L (ViT-L/16))
Attention Bottlenecks for Multimodal Fusion arXiv:2107.00135
VideoonKinetics-400
Acc@1· 2021-06-30
80.8
best: 93.6 (OmniVec2)
Attention Bottlenecks for Multimodal Fusion arXiv:2107.00135
VideoonKinetics-400
Acc@5· 2021-06-30
94.6
best: 98.9 (TubeViT-H (ImageNet-1k))
Attention Bottlenecks for Multimodal Fusion arXiv:2107.00135

Audio1 result

Audio ClassificationonVGGSound
Top 5 Accuracy· 2021-06-30
85.6
best: 85.7 (MMT (Audio-Visual))
SOTA
Attention Bottlenecks for Multimodal Fusion arXiv:2107.00135

Methodology1 result

ClassificationonVGGSound
Top 5 Accuracy· 2021-06-30
85.6
best: 85.7 (MMT (Audio-Visual))
SOTA
Attention Bottlenecks for Multimodal Fusion arXiv:2107.00135