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/VLAB

VLAB

Reported on 28 benchmarks across 4 tasks · 1 paper · 3 SOTA

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

Computer Vision26 results

Video CaptioningonMSVD
METEOR· uses extra data· 2023-05-22
51.2
SOTA
VLAB: Enhancing Video Language Pre-training by Feature Adapting and Blending arXiv:2305.13167
VideoonDiDeMo
text-to-video R@1· uses extra data· 2023-05-22
56.8
best: 74.2 (InternVideo2-6B)
VLAB: Enhancing Video Language Pre-training by Feature Adapting and Blending arXiv:2305.13167
VideoonDiDeMo
text-to-video R@10· uses extra data· 2023-05-22
88.7
best: 94.2 (vid-TLDR (UMT-L))
VLAB: Enhancing Video Language Pre-training by Feature Adapting and Blending arXiv:2305.13167
VideoonDiDeMo
text-to-video R@5· uses extra data· 2023-05-22
81.6
best: 91.2 (vid-TLDR (UMT-L))
VLAB: Enhancing Video Language Pre-training by Feature Adapting and Blending arXiv:2305.13167
VideoonMSR-VTT
text-to-video R@1· uses extra data· 2023-05-22
55.1
best: 64 (GRAM)
VLAB: Enhancing Video Language Pre-training by Feature Adapting and Blending arXiv:2305.13167
VideoonMSR-VTT
text-to-video R@10· uses extra data· 2023-05-22
87.6
best: 89.6 (VAST)
VLAB: Enhancing Video Language Pre-training by Feature Adapting and Blending arXiv:2305.13167
VideoonMSR-VTT
text-to-video R@5· uses extra data· 2023-05-22
78.8
best: 84.3 (VAST)
VLAB: Enhancing Video Language Pre-training by Feature Adapting and Blending arXiv:2305.13167
VideoonMSVD
text-to-video R@1· uses extra data· 2023-05-22
57.5
best: 61.4 (InternVideo2-6B)
VLAB: Enhancing Video Language Pre-training by Feature Adapting and Blending arXiv:2305.13167
VideoonMSVD
text-to-video R@10· uses extra data· 2023-05-22
89.9
best: 90.3 (HunYuan_tvr (huge))
VLAB: Enhancing Video Language Pre-training by Feature Adapting and Blending arXiv:2305.13167
VideoonMSVD
text-to-video R@5· uses extra data· 2023-05-22
83.6
best: 87.6 (CAMoE)
VLAB: Enhancing Video Language Pre-training by Feature Adapting and Blending arXiv:2305.13167
Video CaptioningonMSR-VTT
BLEU-4· uses extra data· 2023-05-22
54.6
best: 57.8 (mPLUG-2)
VLAB: Enhancing Video Language Pre-training by Feature Adapting and Blending arXiv:2305.13167
Video CaptioningonMSR-VTT
CIDEr· uses extra data· 2023-05-22
74.9
best: 80 (mPLUG-2)
VLAB: Enhancing Video Language Pre-training by Feature Adapting and Blending arXiv:2305.13167
Video CaptioningonMSR-VTT
METEOR· uses extra data· 2023-05-22
33.4
best: 38.7 (MV-GPT)
VLAB: Enhancing Video Language Pre-training by Feature Adapting and Blending arXiv:2305.13167
Video CaptioningonMSR-VTT
ROUGE-L· uses extra data· 2023-05-22
68.3
best: 70.1 (mPLUG-2)
VLAB: Enhancing Video Language Pre-training by Feature Adapting and Blending arXiv:2305.13167
Video CaptioningonMSVD
BLEU-4· uses extra data· 2023-05-22
79.3
best: 80.7 (VALOR)
VLAB: Enhancing Video Language Pre-training by Feature Adapting and Blending arXiv:2305.13167
Video CaptioningonMSVD
CIDEr· uses extra data· 2023-05-22
179.8
best: 195.6 (MaMMUT)
VLAB: Enhancing Video Language Pre-training by Feature Adapting and Blending arXiv:2305.13167
Video CaptioningonMSVD
ROUGE-L· uses extra data· 2023-05-22
87.9
VLAB: Enhancing Video Language Pre-training by Feature Adapting and Blending arXiv:2305.13167
Video RetrievalonDiDeMo
text-to-video R@1· uses extra data· 2023-05-22
56.8
best: 74.2 (InternVideo2-6B)
VLAB: Enhancing Video Language Pre-training by Feature Adapting and Blending arXiv:2305.13167
Video RetrievalonDiDeMo
text-to-video R@10· uses extra data· 2023-05-22
88.7
best: 94.2 (vid-TLDR (UMT-L))
VLAB: Enhancing Video Language Pre-training by Feature Adapting and Blending arXiv:2305.13167
Video RetrievalonDiDeMo
text-to-video R@5· uses extra data· 2023-05-22
81.6
best: 91.2 (vid-TLDR (UMT-L))
VLAB: Enhancing Video Language Pre-training by Feature Adapting and Blending arXiv:2305.13167
Video RetrievalonMSR-VTT
text-to-video R@1· uses extra data· 2023-05-22
55.1
best: 64 (GRAM)
VLAB: Enhancing Video Language Pre-training by Feature Adapting and Blending arXiv:2305.13167
Video RetrievalonMSR-VTT
text-to-video R@10· uses extra data· 2023-05-22
87.6
best: 89.6 (VAST)
VLAB: Enhancing Video Language Pre-training by Feature Adapting and Blending arXiv:2305.13167
Video RetrievalonMSR-VTT
text-to-video R@5· uses extra data· 2023-05-22
78.8
best: 84.3 (VAST)
VLAB: Enhancing Video Language Pre-training by Feature Adapting and Blending arXiv:2305.13167
Video RetrievalonMSVD
text-to-video R@1· uses extra data· 2023-05-22
57.5
best: 61.4 (InternVideo2-6B)
VLAB: Enhancing Video Language Pre-training by Feature Adapting and Blending arXiv:2305.13167
Video RetrievalonMSVD
text-to-video R@10· uses extra data· 2023-05-22
89.9
best: 90.3 (HunYuan_tvr (huge))
VLAB: Enhancing Video Language Pre-training by Feature Adapting and Blending arXiv:2305.13167
Video RetrievalonMSVD
text-to-video R@5· uses extra data· 2023-05-22
83.6
best: 87.6 (CAMoE)
VLAB: Enhancing Video Language Pre-training by Feature Adapting and Blending arXiv:2305.13167

Natural Language Processing2 results

Visual Question Answering (VQA)onMSRVTT-QA
Accuracy· uses extra data· 2023-05-22
0.496
SOTA
VLAB: Enhancing Video Language Pre-training by Feature Adapting and Blending arXiv:2305.13167
Visual Question Answering (VQA)onMSVD-QA
Accuracy· uses extra data· 2023-05-22
0.61
SOTA
VLAB: Enhancing Video Language Pre-training by Feature Adapting and Blending arXiv:2305.13167