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/InternVideo2-1B

InternVideo2-1B

Reported on 64 benchmarks across 12 tasks · 1 paper · 7 SOTA

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

Computer Vision57 results

VideoonMiT
Top 1 Accuracy· uses extra data· 2024-03-22
50.9
best: 53.1 (OmniVec2)
SOTA
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
Zero-Shot Video RetrievalonVATEX
video-to-text R@1· uses extra data· 2024-03-22
85.4
SOTA
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
Zero-Shot Video RetrievalonMSVD
video-to-text R@1· uses extra data· 2024-03-22
83.3
SOTA
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
Zero-Shot Video RetrievalonMSVD
video-to-text R@5· uses extra data· 2024-03-22
94.3
SOTA
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
Zero-Shot Video RetrievalonDiDeMo
text-to-video R@10· uses extra data· 2024-03-22
85.1
SOTA
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
VideoonHACS
Average-mAP· 2024-03-22
42.4
best: 45.8 (RDFA-S6 (InternVideo2-6B))
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
VideoonActivityNet-1.3
mAP· 2024-03-22
40.4
best: 42.9 (RDFA-S6 (InternVideo2-6B))
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
VideoonTHUMOS’14
Avg mAP (0.3:0.7)· uses extra data· 2024-03-22
69.8
best: 76.9 (AdaTAD (VideoMAEv2-giant))
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
VideoonQVHighlights
R@1,IoU=0.5· 2024-03-22
70
best: 71.42 (InternVideo2-6B)
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
VideoonQVHighlights
R@1,IoU=0.7· 2024-03-22
54.45
best: 56.45 (InternVideo2-6B)
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
VideoonKinetics-700
Top-1 Accuracy· uses extra data· 2024-03-22
85.4
best: 85.9 (InternVideo2-6B)
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
VideoonKinetics-400
Acc@1· uses extra data· 2024-03-22
91.6
best: 93.6 (OmniVec2)
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
VideoonKinetics-600
Top-1 Accuracy· uses extra data· 2024-03-22
91.6
best: 91.9 (InternVideo2-6B)
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
Temporal Action LocalizationonHACS
Average-mAP· 2024-03-22
42.4
best: 45.8 (RDFA-S6 (InternVideo2-6B))
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
Temporal Action LocalizationonActivityNet-1.3
mAP· 2024-03-22
40.4
best: 42.9 (RDFA-S6 (InternVideo2-6B))
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
Temporal Action LocalizationonTHUMOS’14
Avg mAP (0.3:0.7)· uses extra data· 2024-03-22
69.8
best: 76.9 (AdaTAD (VideoMAEv2-giant))
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
Action LocalizationonHACS
Average-mAP· 2024-03-22
42.4
best: 45.8 (RDFA-S6 (InternVideo2-6B))
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
Action LocalizationonActivityNet-1.3
mAP· 2024-03-22
40.4
best: 42.9 (RDFA-S6 (InternVideo2-6B))
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
Action LocalizationonTHUMOS’14
Avg mAP (0.3:0.7)· uses extra data· 2024-03-22
69.8
best: 76.9 (AdaTAD (VideoMAEv2-giant))
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
Video RetrievalonQVHighlights
R@1,IoU=0.5· 2024-03-22
70
best: 71.42 (InternVideo2-6B)
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
Video RetrievalonQVHighlights
R@1,IoU=0.7· 2024-03-22
54.45
best: 56.45 (InternVideo2-6B)
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
Moment RetrievalonCharades-STA
R@1 IoU=0.5· 2024-03-22
68.36
best: 71.1 (SG-DETR (w/ PT))
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
Moment RetrievalonCharades-STA
R@1 IoU=0.7· 2024-03-22
45.03
best: 52.8 (SG-DETR (w/ PT))
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
Video GroundingonQVHighlights
R@1,IoU=0.5· 2024-03-22
70
best: 71.42 (InternVideo2-6B)
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
Video GroundingonQVHighlights
R@1,IoU=0.7· 2024-03-22
54.45
best: 56.45 (InternVideo2-6B)
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
Zero-Shot Video RetrievalonVATEX
text-to-video R@1· uses extra data· 2024-03-22
70.4
best: 83.9 (GRAM)
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
Zero-Shot Video RetrievalonVATEX
text-to-video R@10· uses extra data· 2024-03-22
96.9
best: 99.5 (GRAM)
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
Zero-Shot Video RetrievalonVATEX
text-to-video R@5· uses extra data· 2024-03-22
93.4
best: 94 (InternVideo2-6B)
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
Zero-Shot Video RetrievalonVATEX
video-to-text R@10· uses extra data· 2024-03-22
99.1
best: 99.3 (InternVideo2-6B)
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
Zero-Shot Video RetrievalonVATEX
video-to-text R@5· uses extra data· 2024-03-22
97.6
best: 97.9 (InternVideo2-6B)
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
Zero-Shot Video RetrievalonMSR-VTT
text-to-video R@1· uses extra data· 2024-03-22
51.9
best: 55.9 (InternVideo2-6B)
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
Zero-Shot Video RetrievalonMSR-VTT
text-to-video R@10· uses extra data· 2024-03-22
82.5
best: 85.1 (InternVideo2-6B)
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
Zero-Shot Video RetrievalonMSR-VTT
text-to-video R@5· uses extra data· 2024-03-22
75.3
best: 78.3 (InternVideo2-6B)
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
Zero-Shot Video RetrievalonMSR-VTT
video-to-text R@1· uses extra data· 2024-03-22
50.9
best: 53.7 (InternVideo2-6B)
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
Zero-Shot Video RetrievalonMSR-VTT
video-to-text R@10· uses extra data· 2024-03-22
81.8
best: 84.1 (InternVideo2-6B)
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
Zero-Shot Video RetrievalonMSR-VTT
video-to-text R@5· uses extra data· 2024-03-22
73.4
best: 77.5 (InternVideo2-6B)
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
Zero-Shot Video RetrievalonMSVD
text-to-video R@1· uses extra data· 2024-03-22
58.1
best: 59.3 (InternVideo2-6B)
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
Zero-Shot Video RetrievalonMSVD
text-to-video R@10· uses extra data· 2024-03-22
88.4
best: 89.6 (InternVideo2-6B)
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
Zero-Shot Video RetrievalonMSVD
text-to-video R@5· uses extra data· 2024-03-22
83
best: 84.4 (InternVideo2-6B)
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
Zero-Shot Video RetrievalonMSVD
video-to-text R@10· uses extra data· 2024-03-22
96.9
best: 97.9 (LanguageBind(ViT-L/14))
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
Zero-Shot Video RetrievalonDiDeMo
text-to-video R@1· uses extra data· 2024-03-22
57
best: 57.9 (InternVideo2-6B)
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
Zero-Shot Video RetrievalonDiDeMo
text-to-video R@5· uses extra data· 2024-03-22
80
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
Zero-Shot Video RetrievalonDiDeMo
video-to-text R@1· uses extra data· 2024-03-22
54.3
best: 57.1 (InternVideo2-6B)
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
Zero-Shot Video RetrievalonDiDeMo
video-to-text R@10· uses extra data· 2024-03-22
83.5
best: 85 (InternVideo2-6B)
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
Zero-Shot Video RetrievalonDiDeMo
video-to-text R@5· uses extra data· 2024-03-22
77.2
best: 79.9 (InternVideo2-6B)
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
Zero-Shot Video RetrievalonLSMDC
text-to-video R@1· uses extra data· 2024-03-22
32
best: 33.8 (InternVideo2-6B)
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
Zero-Shot Video RetrievalonLSMDC
text-to-video R@10· uses extra data· 2024-03-22
59.4
best: 62.2 (InternVideo2-6B)
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
Zero-Shot Video RetrievalonLSMDC
text-to-video R@5· uses extra data· 2024-03-22
52.4
best: 55.9 (InternVideo2-6B)
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
Zero-Shot Video RetrievalonLSMDC
video-to-text R@1· uses extra data· 2024-03-22
27.3
best: 30.1 (InternVideo2-6B)
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
Zero-Shot Video RetrievalonLSMDC
video-to-text R@10· uses extra data· 2024-03-22
51.6
best: 54.8 (InternVideo2-6B)
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
Zero-Shot Video RetrievalonLSMDC
video-to-text R@5· uses extra data· 2024-03-22
44.2
best: 47.7 (InternVideo2-6B)
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
Zero-Shot Video RetrievalonActivityNet
text-to-video R@1· uses extra data· 2024-03-22
60.4
best: 63.2 (InternVideo2-6B)
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
Zero-Shot Video RetrievalonActivityNet
text-to-video R@10· uses extra data· 2024-03-22
90.8
best: 92.5 (InternVideo2-6B)
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
Zero-Shot Video RetrievalonActivityNet
text-to-video R@5· uses extra data· 2024-03-22
83.9
best: 85.6 (InternVideo2-6B)
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
Zero-Shot Video RetrievalonActivityNet
video-to-text R@1· uses extra data· 2024-03-22
54.8
best: 56.5 (InternVideo2-6B)
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
Zero-Shot Video RetrievalonActivityNet
video-to-text R@10· uses extra data· 2024-03-22
89.5
best: 90.3 (InternVideo2-6B)
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
Zero-Shot Video RetrievalonActivityNet
video-to-text R@5· uses extra data· 2024-03-22
81.5
best: 82.8 (InternVideo2-6B)
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377

Methodology3 results

Zero-Shot LearningonHACS
Average-mAP· 2024-03-22
42.4
best: 45.8 (RDFA-S6 (InternVideo2-6B))
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
Zero-Shot LearningonActivityNet-1.3
mAP· 2024-03-22
40.4
best: 42.9 (RDFA-S6 (InternVideo2-6B))
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
Zero-Shot LearningonTHUMOS’14
Avg mAP (0.3:0.7)· uses extra data· 2024-03-22
69.8
best: 76.9 (AdaTAD (VideoMAEv2-giant))
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377

Natural Language Processing1 result

Question AnsweringonMVBench
Accuracy· 2024-03-22
60.9
SOTA
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377

Reasoning1 result

Video Question AnsweringonMVBench
Accuracy· 2024-03-22
60.9
SOTA
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377

Robots1 result

Activity RecognitiononSomething-Something V2
Top-1 Accuracy· uses extra data· 2024-03-22
77.1
best: 77.3 (MVD (Kinetics400 pretrain, ViT-H, 16 frame))
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377

Time Series1 result

Action RecognitiononSomething-Something V2
Top-1 Accuracy· uses extra data· 2024-03-22
77.1
best: 77.3 (MVD (Kinetics400 pretrain, ViT-H, 16 frame))
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377