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/CA2ST(B/16)

CA2ST(B/16)

Reported on 7 benchmarks across 5 tasks · 1 paper · 1 SOTA

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

Audio2 results

Audio ClassificationonEPIC-SOUNDS
Accuracy· 2025-03-30
61
best: 78.2 (Mirasol3B)
CA^2ST: Cross-Attention in Audio, Space, and Time for Holistic Video Recognition arXiv:2503.23447
Audio ClassificationonVGGSound
Top 1 Accuracy· 2025-03-30
68.3
best: 69.8 (Mirasol3B)
CA^2ST: Cross-Attention in Audio, Space, and Time for Holistic Video Recognition arXiv:2503.23447

Methodology2 results

ClassificationonEPIC-SOUNDS
Accuracy· 2025-03-30
61
best: 78.2 (Mirasol3B)
CA^2ST: Cross-Attention in Audio, Space, and Time for Holistic Video Recognition arXiv:2503.23447
ClassificationonVGGSound
Top 1 Accuracy· 2025-03-30
68.3
best: 69.8 (Mirasol3B)
CA^2ST: Cross-Attention in Audio, Space, and Time for Holistic Video Recognition arXiv:2503.23447

Computer Vision1 result

VideoonKinetics-Sounds
Top 1 Accuracy· 2025-03-30
93.3
SOTA
CA^2ST: Cross-Attention in Audio, Space, and Time for Holistic Video Recognition arXiv:2503.23447

Robots1 result

Activity RecognitiononUCF101
3-fold Accuracy· 2025-03-30
97.2
best: 99.7 (FTP-UniFormerV2-L/14)
CA^2ST: Cross-Attention in Audio, Space, and Time for Holistic Video Recognition arXiv:2503.23447

Time Series1 result

Action RecognitiononUCF101
3-fold Accuracy· 2025-03-30
97.2
best: 99.7 (FTP-UniFormerV2-L/14)
CA^2ST: Cross-Attention in Audio, Space, and Time for Holistic Video Recognition arXiv:2503.23447