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/TESTA (ViT-B/16)

TESTA (ViT-B/16)

Reported on 25 benchmarks across 3 tasks · 1 paper · 12 SOTA

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

Computer Vision24 results

VideoonCondensed Movies
text-to-video R@1· uses extra data· 2023-10-29
24.9
SOTA
TESTA: Temporal-Spatial Token Aggregation for Long-form Video-Language Understanding arXiv:2310.19060
VideoonCondensed Movies
text-to-video R@10· uses extra data· 2023-10-29
55.1
SOTA
TESTA: Temporal-Spatial Token Aggregation for Long-form Video-Language Understanding arXiv:2310.19060
VideoonCondensed Movies
text-to-video R@5· uses extra data· 2023-10-29
46.5
SOTA
TESTA: Temporal-Spatial Token Aggregation for Long-form Video-Language Understanding arXiv:2310.19060
VideoonQuerYD
text-to-video R@1· uses extra data· 2023-10-29
83.4
SOTA
TESTA: Temporal-Spatial Token Aggregation for Long-form Video-Language Understanding arXiv:2310.19060
VideoonQuerYD
text-to-video R@10· uses extra data· 2023-10-29
95.3
SOTA
TESTA: Temporal-Spatial Token Aggregation for Long-form Video-Language Understanding arXiv:2310.19060
VideoonQuerYD
text-to-video R@5· uses extra data· 2023-10-29
93.8
SOTA
TESTA: Temporal-Spatial Token Aggregation for Long-form Video-Language Understanding arXiv:2310.19060
Video RetrievalonCondensed Movies
text-to-video R@1· uses extra data· 2023-10-29
24.9
SOTA
TESTA: Temporal-Spatial Token Aggregation for Long-form Video-Language Understanding arXiv:2310.19060
Video RetrievalonCondensed Movies
text-to-video R@10· uses extra data· 2023-10-29
55.1
SOTA
TESTA: Temporal-Spatial Token Aggregation for Long-form Video-Language Understanding arXiv:2310.19060
Video RetrievalonCondensed Movies
text-to-video R@5· uses extra data· 2023-10-29
46.5
SOTA
TESTA: Temporal-Spatial Token Aggregation for Long-form Video-Language Understanding arXiv:2310.19060
Video RetrievalonQuerYD
text-to-video R@1· uses extra data· 2023-10-29
83.4
SOTA
TESTA: Temporal-Spatial Token Aggregation for Long-form Video-Language Understanding arXiv:2310.19060
Video RetrievalonQuerYD
text-to-video R@10· uses extra data· 2023-10-29
95.3
SOTA
TESTA: Temporal-Spatial Token Aggregation for Long-form Video-Language Understanding arXiv:2310.19060
Video RetrievalonQuerYD
text-to-video R@5· uses extra data· 2023-10-29
93.8
SOTA
TESTA: Temporal-Spatial Token Aggregation for Long-form Video-Language Understanding arXiv:2310.19060
VideoonActivityNet
text-to-video R@1· uses extra data· 2023-10-29
54.8
best: 74.1 (InternVideo2-6B)
TESTA: Temporal-Spatial Token Aggregation for Long-form Video-Language Understanding arXiv:2310.19060
VideoonActivityNet
text-to-video R@10· uses extra data· 2023-10-29
89.6
best: 96.1 (GRAM)
TESTA: Temporal-Spatial Token Aggregation for Long-form Video-Language Understanding arXiv:2310.19060
VideoonActivityNet
text-to-video R@5· uses extra data· 2023-10-29
80.8
best: 90.9 (VAST)
TESTA: Temporal-Spatial Token Aggregation for Long-form Video-Language Understanding arXiv:2310.19060
VideoonDiDeMo
text-to-video R@1· uses extra data· 2023-10-29
61.2
best: 74.2 (InternVideo2-6B)
TESTA: Temporal-Spatial Token Aggregation for Long-form Video-Language Understanding arXiv:2310.19060
VideoonDiDeMo
text-to-video R@10· uses extra data· 2023-10-29
91.5
best: 94.2 (vid-TLDR (UMT-L))
TESTA: Temporal-Spatial Token Aggregation for Long-form Video-Language Understanding arXiv:2310.19060
VideoonDiDeMo
text-to-video R@5· uses extra data· 2023-10-29
87.2
best: 91.2 (vid-TLDR (UMT-L))
TESTA: Temporal-Spatial Token Aggregation for Long-form Video-Language Understanding arXiv:2310.19060
Video RetrievalonActivityNet
text-to-video R@1· uses extra data· 2023-10-29
54.8
best: 74.1 (InternVideo2-6B)
TESTA: Temporal-Spatial Token Aggregation for Long-form Video-Language Understanding arXiv:2310.19060
Video RetrievalonActivityNet
text-to-video R@10· uses extra data· 2023-10-29
89.6
best: 96.1 (GRAM)
TESTA: Temporal-Spatial Token Aggregation for Long-form Video-Language Understanding arXiv:2310.19060
Video RetrievalonActivityNet
text-to-video R@5· uses extra data· 2023-10-29
80.8
best: 90.9 (VAST)
TESTA: Temporal-Spatial Token Aggregation for Long-form Video-Language Understanding arXiv:2310.19060
Video RetrievalonDiDeMo
text-to-video R@1· uses extra data· 2023-10-29
61.2
best: 74.2 (InternVideo2-6B)
TESTA: Temporal-Spatial Token Aggregation for Long-form Video-Language Understanding arXiv:2310.19060
Video RetrievalonDiDeMo
text-to-video R@10· uses extra data· 2023-10-29
91.5
best: 94.2 (vid-TLDR (UMT-L))
TESTA: Temporal-Spatial Token Aggregation for Long-form Video-Language Understanding arXiv:2310.19060
Video RetrievalonDiDeMo
text-to-video R@5· uses extra data· 2023-10-29
87.2
best: 91.2 (vid-TLDR (UMT-L))
TESTA: Temporal-Spatial Token Aggregation for Long-form Video-Language Understanding arXiv:2310.19060

Reasoning1 result

Video Question AnsweringonActivityNet-QA
Accuracy· uses extra data· 2023-10-29
45
best: 61.6 (Tarsier (34B))
TESTA: Temporal-Spatial Token Aggregation for Long-form Video-Language Understanding arXiv:2310.19060