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/HunYuan_tvr

HunYuan_tvr

Reported on 92 benchmarks across 2 tasks · 1 paper · 28 SOTA

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

Computer Vision92 results

VideoonActivityNet
text-to-video R@1· uses extra data· 2022-04-07
57.3
best: 74.1 (InternVideo2-6B)
SOTA
Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations arXiv:2204.03382
VideoonActivityNet
text-to-video R@10· uses extra data· 2022-04-07
93.1
best: 96.1 (GRAM)
SOTA
Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations arXiv:2204.03382
VideoonActivityNet
text-to-video R@5· uses extra data· 2022-04-07
84.8
best: 90.9 (VAST)
SOTA
Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations arXiv:2204.03382
VideoonActivityNet
video-to-text Mean Rank· uses extra data· 2022-04-07
3.4
best: 6.7 (DiffusionRet+QB-Norm)
SOTA
Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations arXiv:2204.03382
VideoonActivityNet
video-to-text Median Rank· uses extra data· 2022-04-07
1
best: 2 (DiffusionRet+QB-Norm)
SOTA
Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations arXiv:2204.03382
VideoonActivityNet
video-to-text R@1· uses extra data· 2022-04-07
57.7
best: 69.7 (InternVideo2-6B)
SOTA
Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations arXiv:2204.03382
VideoonActivityNet
video-to-text R@10· uses extra data· 2022-04-07
93.9
best: 95.4 (GRAM)
SOTA
Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations arXiv:2204.03382
VideoonActivityNet
video-to-text R@5· uses extra data· 2022-04-07
85.7
best: 89.1 (UMT-L (ViT-L/16))
SOTA
Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations arXiv:2204.03382
VideoonDiDeMo
text-to-video R@10· uses extra data· 2022-04-07
85.7
best: 94.2 (vid-TLDR (UMT-L))
SOTA
Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations arXiv:2204.03382
VideoonDiDeMo
text-to-video R@5· uses extra data· 2022-04-07
78.2
best: 91.2 (vid-TLDR (UMT-L))
SOTA
Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations arXiv:2204.03382
VideoonDiDeMo
video-to-text R@1· uses extra data· 2022-04-07
54.8
best: 71.9 (InternVideo2-6B)
SOTA
Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations arXiv:2204.03382
VideoonDiDeMo
video-to-text R@10· uses extra data· 2022-04-07
87.2
best: 93.8 (vid-TLDR (UMT-L))
SOTA
Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations arXiv:2204.03382
VideoonDiDeMo
video-to-text R@5· uses extra data· 2022-04-07
79.9
best: 89.8 (vid-TLDR (UMT-L))
SOTA
Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations arXiv:2204.03382
VideoonLSMDC
video-to-text Mean Rank· uses extra data· 2022-04-07
48.9
SOTA
Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations arXiv:2204.03382
Video RetrievalonActivityNet
text-to-video R@1· uses extra data· 2022-04-07
57.3
best: 74.1 (InternVideo2-6B)
SOTA
Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations arXiv:2204.03382
Video RetrievalonActivityNet
text-to-video R@10· uses extra data· 2022-04-07
93.1
best: 96.1 (GRAM)
SOTA
Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations arXiv:2204.03382
Video RetrievalonActivityNet
text-to-video R@5· uses extra data· 2022-04-07
84.8
best: 90.9 (VAST)
SOTA
Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations arXiv:2204.03382
Video RetrievalonActivityNet
video-to-text Mean Rank· uses extra data· 2022-04-07
3.4
best: 6.7 (DiffusionRet+QB-Norm)
SOTA
Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations arXiv:2204.03382
Video RetrievalonActivityNet
video-to-text Median Rank· uses extra data· 2022-04-07
1
best: 2 (DiffusionRet+QB-Norm)
SOTA
Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations arXiv:2204.03382
Video RetrievalonActivityNet
video-to-text R@1· uses extra data· 2022-04-07
57.7
best: 69.7 (InternVideo2-6B)
SOTA
Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations arXiv:2204.03382
Video RetrievalonActivityNet
video-to-text R@10· uses extra data· 2022-04-07
93.9
best: 95.4 (GRAM)
SOTA
Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations arXiv:2204.03382
Video RetrievalonActivityNet
video-to-text R@5· uses extra data· 2022-04-07
85.7
best: 89.1 (UMT-L (ViT-L/16))
SOTA
Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations arXiv:2204.03382
Video RetrievalonDiDeMo
text-to-video R@10· uses extra data· 2022-04-07
85.7
best: 94.2 (vid-TLDR (UMT-L))
SOTA
Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations arXiv:2204.03382
Video RetrievalonDiDeMo
text-to-video R@5· uses extra data· 2022-04-07
78.2
best: 91.2 (vid-TLDR (UMT-L))
SOTA
Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations arXiv:2204.03382
Video RetrievalonDiDeMo
video-to-text R@1· uses extra data· 2022-04-07
54.8
best: 71.9 (InternVideo2-6B)
SOTA
Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations arXiv:2204.03382
Video RetrievalonDiDeMo
video-to-text R@10· uses extra data· 2022-04-07
87.2
best: 93.8 (vid-TLDR (UMT-L))
SOTA
Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations arXiv:2204.03382
Video RetrievalonDiDeMo
video-to-text R@5· uses extra data· 2022-04-07
79.9
best: 89.8 (vid-TLDR (UMT-L))
SOTA
Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations arXiv:2204.03382
Video RetrievalonLSMDC
video-to-text Mean Rank· uses extra data· 2022-04-07
48.9
SOTA
Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations arXiv:2204.03382
VideoonMSR-VTT-1kA
text-to-video R@1· uses extra data· 2022-04-07
55
best: 62.9 (HunYuan_tvr (huge))
Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations arXiv:2204.03382
VideoonMSR-VTT-1kA
video-to-text Mean Rank· uses extra data· 2022-04-07
7.7
best: 10.2 (CenterCLIP (ViT-B/16))
Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations arXiv:2204.03382
VideoonMSR-VTT-1kA
video-to-text Median Rank· uses extra data· 2022-04-07
1
best: 5 (CLIP)
Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations arXiv:2204.03382
VideoonMSR-VTT-1kA
video-to-text R@1· uses extra data· 2022-04-07
55.5
best: 64.8 (HunYuan_tvr (huge))
Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations arXiv:2204.03382
VideoonMSR-VTT-1kA
video-to-text R@10· uses extra data· 2022-04-07
85.8
best: 91.1 (HunYuan_tvr (huge))
Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations arXiv:2204.03382
VideoonMSR-VTT-1kA
video-to-text R@5· uses extra data· 2022-04-07
78.4
best: 783 (PIDRo)
Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations arXiv:2204.03382
VideoonActivityNet
text-to-video Mean Rank· uses extra data· 2022-04-07
4
best: 23.1 (Collaborative Experts)
Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations arXiv:2204.03382
VideoonActivityNet
text-to-video Median Rank· uses extra data· 2022-04-07
1
best: 6 (Collaborative Experts)
Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations arXiv:2204.03382
VideoonDiDeMo
text-to-video Mean Rank· uses extra data· 2022-04-07
11.1
best: 43.7 (Collaborative Experts)
Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations arXiv:2204.03382
VideoonDiDeMo
text-to-video Median Rank· uses extra data· 2022-04-07
1
best: 8.3 (Collaborative Experts)
Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations arXiv:2204.03382
VideoonDiDeMo
text-to-video R@1· uses extra data· 2022-04-07
52.1
best: 74.2 (InternVideo2-6B)
Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations arXiv:2204.03382
VideoonDiDeMo
video-to-text Mean Rank· uses extra data· 2022-04-07
7.1
best: 39.6 (PO Loss)
Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations arXiv:2204.03382
VideoonDiDeMo
video-to-text Median Rank· uses extra data· 2022-04-07
1
best: 8 (PO Loss)
Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations arXiv:2204.03382
VideoonLSMDC
text-to-video Mean Rank· uses extra data· 2022-04-07
56.4
best: 58 (CLIP4Clip)
Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations arXiv:2204.03382
VideoonLSMDC
text-to-video Median Rank· uses extra data· 2022-04-07
7
best: 56.5 (CLIP)
Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations arXiv:2204.03382
VideoonLSMDC
text-to-video R@1· uses extra data· 2022-04-07
29.7
best: 46.4 (InternVideo2-6B)
Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations arXiv:2204.03382
VideoonLSMDC
text-to-video R@10· uses extra data· 2022-04-07
55.4
best: 92.8 (HunYuan_tvr (huge))
Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations arXiv:2204.03382
VideoonLSMDC
text-to-video R@5· uses extra data· 2022-04-07
46.4
best: 80.1 (HunYuan_tvr (huge))
Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations arXiv:2204.03382
VideoonLSMDC
video-to-text Median Rank· uses extra data· 2022-04-07
7
best: 73 (CLIP)
Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations arXiv:2204.03382
VideoonLSMDC
video-to-text R@1· uses extra data· 2022-04-07
30.1
best: 46.7 (InternVideo2-6B)
Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations arXiv:2204.03382
VideoonLSMDC
video-to-text R@10· uses extra data· 2022-04-07
55.7
best: 91.8 (HunYuan_tvr (huge))
Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations arXiv:2204.03382
VideoonLSMDC
video-to-text R@5· uses extra data· 2022-04-07
47.5
best: 71.8 (HunYuan_tvr (huge))
Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations arXiv:2204.03382
VideoonMSVD
text-to-video Mean Rank· uses extra data· 2022-04-07
7.8
best: 23.1 (Collaborative Experts)
Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations arXiv:2204.03382
VideoonMSVD
text-to-video Median Rank· uses extra data· 2022-04-07
1
best: 6 (SSML)
Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations arXiv:2204.03382
VideoonMSVD
text-to-video R@1· uses extra data· 2022-04-07
58.2
best: 61.4 (InternVideo2-6B)
Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations arXiv:2204.03382
VideoonMSVD
text-to-video R@10· uses extra data· 2022-04-07
90.1
best: 90.3 (HunYuan_tvr (huge))
Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations arXiv:2204.03382
VideoonMSVD
text-to-video R@5· uses extra data· 2022-04-07
83.5
best: 87.6 (CAMoE)
Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations arXiv:2204.03382
VideoonMSVD
video-to-text Mean Rank· uses extra data· 2022-04-07
3.8
best: 7.6 (HunYuan_tvr (huge))
Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations arXiv:2204.03382
VideoonMSVD
video-to-text Median Rank· uses extra data· 2022-04-07
1
Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations arXiv:2204.03382
VideoonMSVD
video-to-text R@1· uses extra data· 2022-04-07
69.1
best: 85.2 (InternVideo2-6B)
Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations arXiv:2204.03382
VideoonMSVD
video-to-text R@10· uses extra data· 2022-04-07
95
best: 97.1 (PAU)
Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations arXiv:2204.03382
VideoonMSVD
video-to-text R@5· uses extra data· 2022-04-07
91.5
best: 94.5 (HunYuan_tvr (huge))
Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations arXiv:2204.03382
Video RetrievalonMSR-VTT-1kA
text-to-video R@1· uses extra data· 2022-04-07
55
best: 62.9 (HunYuan_tvr (huge))
Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations arXiv:2204.03382
Video RetrievalonMSR-VTT-1kA
video-to-text Mean Rank· uses extra data· 2022-04-07
7.7
best: 10.2 (CenterCLIP (ViT-B/16))
Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations arXiv:2204.03382
Video RetrievalonMSR-VTT-1kA
video-to-text Median Rank· uses extra data· 2022-04-07
1
best: 5 (CLIP)
Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations arXiv:2204.03382
Video RetrievalonMSR-VTT-1kA
video-to-text R@1· uses extra data· 2022-04-07
55.5
best: 64.8 (HunYuan_tvr (huge))
Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations arXiv:2204.03382
Video RetrievalonMSR-VTT-1kA
video-to-text R@10· uses extra data· 2022-04-07
85.8
best: 91.1 (HunYuan_tvr (huge))
Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations arXiv:2204.03382
Video RetrievalonMSR-VTT-1kA
video-to-text R@5· uses extra data· 2022-04-07
78.4
best: 783 (PIDRo)
Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations arXiv:2204.03382
Video RetrievalonActivityNet
text-to-video Mean Rank· uses extra data· 2022-04-07
4
best: 23.1 (Collaborative Experts)
Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations arXiv:2204.03382
Video RetrievalonActivityNet
text-to-video Median Rank· uses extra data· 2022-04-07
1
best: 6 (Collaborative Experts)
Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations arXiv:2204.03382
Video RetrievalonDiDeMo
text-to-video Mean Rank· uses extra data· 2022-04-07
11.1
best: 43.7 (Collaborative Experts)
Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations arXiv:2204.03382
Video RetrievalonDiDeMo
text-to-video Median Rank· uses extra data· 2022-04-07
1
best: 8.3 (Collaborative Experts)
Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations arXiv:2204.03382
Video RetrievalonDiDeMo
text-to-video R@1· uses extra data· 2022-04-07
52.1
best: 74.2 (InternVideo2-6B)
Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations arXiv:2204.03382
Video RetrievalonDiDeMo
video-to-text Mean Rank· uses extra data· 2022-04-07
7.1
best: 39.6 (PO Loss)
Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations arXiv:2204.03382
Video RetrievalonDiDeMo
video-to-text Median Rank· uses extra data· 2022-04-07
1
best: 8 (PO Loss)
Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations arXiv:2204.03382
Video RetrievalonLSMDC
text-to-video Mean Rank· uses extra data· 2022-04-07
56.4
best: 58 (CLIP4Clip)
Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations arXiv:2204.03382
Video RetrievalonLSMDC
text-to-video Median Rank· uses extra data· 2022-04-07
7
best: 56.5 (CLIP)
Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations arXiv:2204.03382
Video RetrievalonLSMDC
text-to-video R@1· uses extra data· 2022-04-07
29.7
best: 46.4 (InternVideo2-6B)
Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations arXiv:2204.03382
Video RetrievalonLSMDC
text-to-video R@10· uses extra data· 2022-04-07
55.4
best: 92.8 (HunYuan_tvr (huge))
Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations arXiv:2204.03382
Video RetrievalonLSMDC
text-to-video R@5· uses extra data· 2022-04-07
46.4
best: 80.1 (HunYuan_tvr (huge))
Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations arXiv:2204.03382
Video RetrievalonLSMDC
video-to-text Median Rank· uses extra data· 2022-04-07
7
best: 73 (CLIP)
Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations arXiv:2204.03382
Video RetrievalonLSMDC
video-to-text R@1· uses extra data· 2022-04-07
30.1
best: 46.7 (InternVideo2-6B)
Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations arXiv:2204.03382
Video RetrievalonLSMDC
video-to-text R@10· uses extra data· 2022-04-07
55.7
best: 91.8 (HunYuan_tvr (huge))
Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations arXiv:2204.03382
Video RetrievalonLSMDC
video-to-text R@5· uses extra data· 2022-04-07
47.5
best: 71.8 (HunYuan_tvr (huge))
Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations arXiv:2204.03382
Video RetrievalonMSVD
text-to-video Mean Rank· uses extra data· 2022-04-07
7.8
best: 23.1 (Collaborative Experts)
Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations arXiv:2204.03382
Video RetrievalonMSVD
text-to-video Median Rank· uses extra data· 2022-04-07
1
best: 6 (SSML)
Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations arXiv:2204.03382
Video RetrievalonMSVD
text-to-video R@1· uses extra data· 2022-04-07
58.2
best: 61.4 (InternVideo2-6B)
Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations arXiv:2204.03382
Video RetrievalonMSVD
text-to-video R@10· uses extra data· 2022-04-07
90.1
best: 90.3 (HunYuan_tvr (huge))
Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations arXiv:2204.03382
Video RetrievalonMSVD
text-to-video R@5· uses extra data· 2022-04-07
83.5
best: 87.6 (CAMoE)
Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations arXiv:2204.03382
Video RetrievalonMSVD
video-to-text Mean Rank· uses extra data· 2022-04-07
3.8
best: 7.6 (HunYuan_tvr (huge))
Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations arXiv:2204.03382
Video RetrievalonMSVD
video-to-text Median Rank· uses extra data· 2022-04-07
1
Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations arXiv:2204.03382
Video RetrievalonMSVD
video-to-text R@1· uses extra data· 2022-04-07
69.1
best: 85.2 (InternVideo2-6B)
Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations arXiv:2204.03382
Video RetrievalonMSVD
video-to-text R@10· uses extra data· 2022-04-07
95
best: 97.1 (PAU)
Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations arXiv:2204.03382
Video RetrievalonMSVD
video-to-text R@5· uses extra data· 2022-04-07
91.5
best: 94.5 (HunYuan_tvr (huge))
Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations arXiv:2204.03382