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/CAMoE

CAMoE

Reported on 96 benchmarks across 2 tasks · 1 paper · 52 SOTA

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

Computer Vision96 results

VideoonMSR-VTT-1kA
text-to-video R@1· uses extra data· 2021-09-09
48.8
best: 62.9 (HunYuan_tvr (huge))
SOTA
Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss arXiv:2109.04290
VideoonMSR-VTT-1kA
text-to-video R@10· uses extra data· 2021-09-09
85.3
best: 90.8 (HunYuan_tvr (huge))
SOTA
Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss arXiv:2109.04290
VideoonMSR-VTT-1kA
text-to-video R@5· uses extra data· 2021-09-09
75.6
best: 84.5 (HunYuan_tvr (huge))
SOTA
Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss arXiv:2109.04290
VideoonMSR-VTT-1kA
video-to-text R@1· uses extra data· 2021-09-09
50.3
best: 64.8 (HunYuan_tvr (huge))
SOTA
Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss arXiv:2109.04290
VideoonMSR-VTT-1kA
video-to-text R@10· uses extra data· 2021-09-09
83.8
best: 91.1 (HunYuan_tvr (huge))
SOTA
Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss arXiv:2109.04290
VideoonMSR-VTT-1kA
video-to-text R@5· uses extra data· 2021-09-09
74.6
best: 783 (PIDRo)
SOTA
Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss arXiv:2109.04290
VideoonActivityNet
text-to-video R@1· uses extra data· 2021-09-09
51
best: 74.1 (InternVideo2-6B)
SOTA
Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss arXiv:2109.04290
VideoonActivityNet
text-to-video R@10· uses extra data· 2021-09-09
87.6
best: 96.1 (GRAM)
SOTA
Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss arXiv:2109.04290
VideoonActivityNet
text-to-video R@5· uses extra data· 2021-09-09
77.7
best: 90.9 (VAST)
SOTA
Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss arXiv:2109.04290
VideoonDiDeMo
text-to-video R@1· uses extra data· 2021-09-09
43.8
best: 74.2 (InternVideo2-6B)
SOTA
Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss arXiv:2109.04290
VideoonDiDeMo
text-to-video R@5· uses extra data· 2021-09-09
71.4
best: 91.2 (vid-TLDR (UMT-L))
SOTA
Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss arXiv:2109.04290
VideoonDiDeMo
video-to-text R@1· uses extra data· 2021-09-09
45.5
best: 71.9 (InternVideo2-6B)
SOTA
Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss arXiv:2109.04290
VideoonDiDeMo
video-to-text R@10· uses extra data· 2021-09-09
80.5
best: 93.8 (vid-TLDR (UMT-L))
SOTA
Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss arXiv:2109.04290
VideoonMSR-VTT
video-to-text R@1· uses extra data· 2021-09-09
59.8
best: 64.8 (GRAM)
SOTA
Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss arXiv:2109.04290
VideoonMSR-VTT
video-to-text R@10· uses extra data· 2021-09-09
92.8
SOTA
Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss arXiv:2109.04290
VideoonMSR-VTT
video-to-text R@5· uses extra data· 2021-09-09
86.2
SOTA
Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss arXiv:2109.04290
VideoonLSMDC
text-to-video R@1· uses extra data· 2021-09-09
25.9
best: 46.4 (InternVideo2-6B)
SOTA
Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss arXiv:2109.04290
VideoonLSMDC
text-to-video R@10· uses extra data· 2021-09-09
53.7
best: 92.8 (HunYuan_tvr (huge))
SOTA
Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss arXiv:2109.04290
VideoonLSMDC
text-to-video R@5· uses extra data· 2021-09-09
46.1
best: 80.1 (HunYuan_tvr (huge))
SOTA
Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss arXiv:2109.04290
VideoonMSVD
text-to-video R@1· uses extra data· 2021-09-09
51.8
best: 61.4 (InternVideo2-6B)
SOTA
Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss arXiv:2109.04290
VideoonMSVD
text-to-video R@10· uses extra data· 2021-09-09
87.6
best: 90.3 (HunYuan_tvr (huge))
SOTA
Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss arXiv:2109.04290
VideoonMSVD
text-to-video R@5· uses extra data· 2021-09-09
87.6
SOTA
Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss arXiv:2109.04290
VideoonMSVD
video-to-text Mean Rank· uses extra data· 2021-09-09
3.1
best: 7.6 (HunYuan_tvr (huge))
SOTA
Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss arXiv:2109.04290
VideoonMSVD
video-to-text R@1· uses extra data· 2021-09-09
69.3
best: 85.2 (InternVideo2-6B)
SOTA
Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss arXiv:2109.04290
VideoonMSVD
video-to-text R@10· uses extra data· 2021-09-09
94.6
best: 97.1 (PAU)
SOTA
Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss arXiv:2109.04290
VideoonMSVD
video-to-text R@5· uses extra data· 2021-09-09
90.6
best: 94.5 (HunYuan_tvr (huge))
SOTA
Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss arXiv:2109.04290
Video RetrievalonMSR-VTT-1kA
text-to-video R@1· uses extra data· 2021-09-09
48.8
best: 62.9 (HunYuan_tvr (huge))
SOTA
Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss arXiv:2109.04290
Video RetrievalonMSR-VTT-1kA
text-to-video R@10· uses extra data· 2021-09-09
85.3
best: 90.8 (HunYuan_tvr (huge))
SOTA
Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss arXiv:2109.04290
Video RetrievalonMSR-VTT-1kA
text-to-video R@5· uses extra data· 2021-09-09
75.6
best: 84.5 (HunYuan_tvr (huge))
SOTA
Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss arXiv:2109.04290
Video RetrievalonMSR-VTT-1kA
video-to-text R@1· uses extra data· 2021-09-09
50.3
best: 64.8 (HunYuan_tvr (huge))
SOTA
Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss arXiv:2109.04290
Video RetrievalonMSR-VTT-1kA
video-to-text R@10· uses extra data· 2021-09-09
83.8
best: 91.1 (HunYuan_tvr (huge))
SOTA
Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss arXiv:2109.04290
Video RetrievalonMSR-VTT-1kA
video-to-text R@5· uses extra data· 2021-09-09
74.6
best: 783 (PIDRo)
SOTA
Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss arXiv:2109.04290
Video RetrievalonActivityNet
text-to-video R@1· uses extra data· 2021-09-09
51
best: 74.1 (InternVideo2-6B)
SOTA
Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss arXiv:2109.04290
Video RetrievalonActivityNet
text-to-video R@10· uses extra data· 2021-09-09
87.6
best: 96.1 (GRAM)
SOTA
Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss arXiv:2109.04290
Video RetrievalonActivityNet
text-to-video R@5· uses extra data· 2021-09-09
77.7
best: 90.9 (VAST)
SOTA
Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss arXiv:2109.04290
Video RetrievalonDiDeMo
text-to-video R@1· uses extra data· 2021-09-09
43.8
best: 74.2 (InternVideo2-6B)
SOTA
Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss arXiv:2109.04290
Video RetrievalonDiDeMo
text-to-video R@5· uses extra data· 2021-09-09
71.4
best: 91.2 (vid-TLDR (UMT-L))
SOTA
Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss arXiv:2109.04290
Video RetrievalonDiDeMo
video-to-text R@1· uses extra data· 2021-09-09
45.5
best: 71.9 (InternVideo2-6B)
SOTA
Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss arXiv:2109.04290
Video RetrievalonDiDeMo
video-to-text R@10· uses extra data· 2021-09-09
80.5
best: 93.8 (vid-TLDR (UMT-L))
SOTA
Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss arXiv:2109.04290
Video RetrievalonMSR-VTT
video-to-text R@1· uses extra data· 2021-09-09
59.8
best: 64.8 (GRAM)
SOTA
Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss arXiv:2109.04290
Video RetrievalonMSR-VTT
video-to-text R@10· uses extra data· 2021-09-09
92.8
SOTA
Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss arXiv:2109.04290
Video RetrievalonMSR-VTT
video-to-text R@5· uses extra data· 2021-09-09
86.2
SOTA
Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss arXiv:2109.04290
Video RetrievalonLSMDC
text-to-video R@1· uses extra data· 2021-09-09
25.9
best: 46.4 (InternVideo2-6B)
SOTA
Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss arXiv:2109.04290
Video RetrievalonLSMDC
text-to-video R@10· uses extra data· 2021-09-09
53.7
best: 92.8 (HunYuan_tvr (huge))
SOTA
Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss arXiv:2109.04290
Video RetrievalonLSMDC
text-to-video R@5· uses extra data· 2021-09-09
46.1
best: 80.1 (HunYuan_tvr (huge))
SOTA
Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss arXiv:2109.04290
Video RetrievalonMSVD
text-to-video R@1· uses extra data· 2021-09-09
51.8
best: 61.4 (InternVideo2-6B)
SOTA
Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss arXiv:2109.04290
Video RetrievalonMSVD
text-to-video R@10· uses extra data· 2021-09-09
87.6
best: 90.3 (HunYuan_tvr (huge))
SOTA
Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss arXiv:2109.04290
Video RetrievalonMSVD
text-to-video R@5· uses extra data· 2021-09-09
87.6
SOTA
Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss arXiv:2109.04290
Video RetrievalonMSVD
video-to-text Mean Rank· uses extra data· 2021-09-09
3.1
best: 7.6 (HunYuan_tvr (huge))
SOTA
Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss arXiv:2109.04290
Video RetrievalonMSVD
video-to-text R@1· uses extra data· 2021-09-09
69.3
best: 85.2 (InternVideo2-6B)
SOTA
Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss arXiv:2109.04290
Video RetrievalonMSVD
video-to-text R@10· uses extra data· 2021-09-09
94.6
best: 97.1 (PAU)
SOTA
Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss arXiv:2109.04290
Video RetrievalonMSVD
video-to-text R@5· uses extra data· 2021-09-09
90.6
best: 94.5 (HunYuan_tvr (huge))
SOTA
Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss arXiv:2109.04290
VideoonMSR-VTT-1kA
text-to-video Mean Rank· uses extra data· 2021-09-09
12.4
best: 28.2 (Collaborative Experts)
Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss arXiv:2109.04290
VideoonMSR-VTT-1kA
text-to-video Median Rank· uses extra data· 2021-09-09
2
best: 13 (JSFusion)
Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss arXiv:2109.04290
VideoonMSR-VTT-1kA
video-to-text Mean Rank· uses extra data· 2021-09-09
9.9
best: 10.2 (CenterCLIP (ViT-B/16))
Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss arXiv:2109.04290
VideoonMSR-VTT-1kA
video-to-text Median Rank· uses extra data· 2021-09-09
2
best: 5 (CLIP)
Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss arXiv:2109.04290
VideoonActivityNet
text-to-video Mean Rank· uses extra data· 2021-09-09
6.3
best: 23.1 (Collaborative Experts)
Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss arXiv:2109.04290
VideoonActivityNet
text-to-video Median Rank· uses extra data· 2021-09-09
1
best: 6 (Collaborative Experts)
Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss arXiv:2109.04290
VideoonDiDeMo
text-to-video Mean Rank· uses extra data· 2021-09-09
16.3
best: 43.7 (Collaborative Experts)
Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss arXiv:2109.04290
VideoonDiDeMo
text-to-video Median Rank· uses extra data· 2021-09-09
2
best: 8.3 (Collaborative Experts)
Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss arXiv:2109.04290
VideoonDiDeMo
text-to-video R@10· uses extra data· 2021-09-09
79.9
best: 94.2 (vid-TLDR (UMT-L))
Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss arXiv:2109.04290
VideoonDiDeMo
video-to-text Mean Rank· uses extra data· 2021-09-09
10.2
best: 39.6 (PO Loss)
Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss arXiv:2109.04290
VideoonDiDeMo
video-to-text Median Rank· uses extra data· 2021-09-09
2
best: 8 (PO Loss)
Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss arXiv:2109.04290
VideoonMSR-VTT
text-to-video Mean Rank· uses extra data· 2021-09-09
42.6
best: 213.8 (JEMC)
Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss arXiv:2109.04290
VideoonMSR-VTT
text-to-video Median Rank· uses extra data· 2021-09-09
3
best: 55 (C+LSTM+SA+FC7)
Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss arXiv:2109.04290
VideoonMSR-VTT
text-to-video R@1· uses extra data· 2021-09-09
32.9
best: 64 (GRAM)
Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss arXiv:2109.04290
VideoonMSR-VTT
text-to-video R@10· uses extra data· 2021-09-09
68.4
best: 89.6 (VAST)
Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss arXiv:2109.04290
VideoonMSR-VTT
text-to-video R@5· uses extra data· 2021-09-09
58.3
best: 84.3 (VAST)
Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss arXiv:2109.04290
VideoonMSR-VTT
video-to-text Mean Rank· uses extra data· 2021-09-09
3.8
best: 134 (JEMC)
Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss arXiv:2109.04290
VideoonMSR-VTT
video-to-text Median Rank· uses extra data· 2021-09-09
1
best: 16 (JEMC)
Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss arXiv:2109.04290
VideoonLSMDC
text-to-video Mean Rank· uses extra data· 2021-09-09
54.4
best: 58 (CLIP4Clip)
Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss arXiv:2109.04290
VideoonMSVD
text-to-video Mean Rank· uses extra data· 2021-09-09
8.9
best: 23.1 (Collaborative Experts)
Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss arXiv:2109.04290
VideoonMSVD
text-to-video Median Rank· uses extra data· 2021-09-09
1
best: 6 (SSML)
Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss arXiv:2109.04290
VideoonMSVD
video-to-text Median Rank· uses extra data· 2021-09-09
1
Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss arXiv:2109.04290
Video RetrievalonMSR-VTT-1kA
text-to-video Mean Rank· uses extra data· 2021-09-09
12.4
best: 28.2 (Collaborative Experts)
Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss arXiv:2109.04290
Video RetrievalonMSR-VTT-1kA
text-to-video Median Rank· uses extra data· 2021-09-09
2
best: 13 (JSFusion)
Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss arXiv:2109.04290
Video RetrievalonMSR-VTT-1kA
video-to-text Mean Rank· uses extra data· 2021-09-09
9.9
best: 10.2 (CenterCLIP (ViT-B/16))
Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss arXiv:2109.04290
Video RetrievalonMSR-VTT-1kA
video-to-text Median Rank· uses extra data· 2021-09-09
2
best: 5 (CLIP)
Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss arXiv:2109.04290
Video RetrievalonActivityNet
text-to-video Mean Rank· uses extra data· 2021-09-09
6.3
best: 23.1 (Collaborative Experts)
Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss arXiv:2109.04290
Video RetrievalonActivityNet
text-to-video Median Rank· uses extra data· 2021-09-09
1
best: 6 (Collaborative Experts)
Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss arXiv:2109.04290
Video RetrievalonDiDeMo
text-to-video Mean Rank· uses extra data· 2021-09-09
16.3
best: 43.7 (Collaborative Experts)
Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss arXiv:2109.04290
Video RetrievalonDiDeMo
text-to-video Median Rank· uses extra data· 2021-09-09
2
best: 8.3 (Collaborative Experts)
Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss arXiv:2109.04290
Video RetrievalonDiDeMo
text-to-video R@10· uses extra data· 2021-09-09
79.9
best: 94.2 (vid-TLDR (UMT-L))
Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss arXiv:2109.04290
Video RetrievalonDiDeMo
video-to-text Mean Rank· uses extra data· 2021-09-09
10.2
best: 39.6 (PO Loss)
Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss arXiv:2109.04290
Video RetrievalonDiDeMo
video-to-text Median Rank· uses extra data· 2021-09-09
2
best: 8 (PO Loss)
Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss arXiv:2109.04290
Video RetrievalonMSR-VTT
text-to-video Mean Rank· uses extra data· 2021-09-09
42.6
best: 213.8 (JEMC)
Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss arXiv:2109.04290
Video RetrievalonMSR-VTT
text-to-video Median Rank· uses extra data· 2021-09-09
3
best: 55 (C+LSTM+SA+FC7)
Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss arXiv:2109.04290
Video RetrievalonMSR-VTT
text-to-video R@1· uses extra data· 2021-09-09
32.9
best: 64 (GRAM)
Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss arXiv:2109.04290
Video RetrievalonMSR-VTT
text-to-video R@10· uses extra data· 2021-09-09
68.4
best: 89.6 (VAST)
Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss arXiv:2109.04290
Video RetrievalonMSR-VTT
text-to-video R@5· uses extra data· 2021-09-09
58.3
best: 84.3 (VAST)
Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss arXiv:2109.04290
Video RetrievalonMSR-VTT
video-to-text Mean Rank· uses extra data· 2021-09-09
3.8
best: 134 (JEMC)
Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss arXiv:2109.04290
Video RetrievalonMSR-VTT
video-to-text Median Rank· uses extra data· 2021-09-09
1
best: 16 (JEMC)
Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss arXiv:2109.04290
Video RetrievalonLSMDC
text-to-video Mean Rank· uses extra data· 2021-09-09
54.4
best: 58 (CLIP4Clip)
Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss arXiv:2109.04290
Video RetrievalonMSVD
text-to-video Mean Rank· uses extra data· 2021-09-09
8.9
best: 23.1 (Collaborative Experts)
Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss arXiv:2109.04290
Video RetrievalonMSVD
text-to-video Median Rank· uses extra data· 2021-09-09
1
best: 6 (SSML)
Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss arXiv:2109.04290
Video RetrievalonMSVD
video-to-text Median Rank· uses extra data· 2021-09-09
1
Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss arXiv:2109.04290