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/InternVideo2-6B

InternVideo2-6B

Reported on 107 benchmarks across 13 tasks · 1 paper · 74 SOTA

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

Computer Vision87 results

VideoonVATEX
video-to-text R@1· uses extra data· 2024-03-22
89.3
SOTA
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
VideoonActivityNet
text-to-video R@1· uses extra data· 2024-03-22
74.1
SOTA
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
VideoonActivityNet
video-to-text R@1· uses extra data· 2024-03-22
69.7
SOTA
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
VideoonDiDeMo
text-to-video R@1· uses extra data· 2024-03-22
74.2
SOTA
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
VideoonDiDeMo
video-to-text R@1· uses extra data· 2024-03-22
71.9
SOTA
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
VideoonLSMDC
text-to-video R@1· uses extra data· 2024-03-22
46.4
SOTA
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
VideoonLSMDC
video-to-text R@1· uses extra data· 2024-03-22
46.7
SOTA
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
VideoonMSVD
text-to-video R@1· uses extra data· 2024-03-22
61.4
SOTA
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
VideoonMSVD
video-to-text R@1· uses extra data· 2024-03-22
85.2
SOTA
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
VideoonQVHighlights
R@1,IoU=0.5· 2024-03-22
71.42
SOTA
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
VideoonQVHighlights
R@1,IoU=0.7· 2024-03-22
56.45
SOTA
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
VideoonKinetics-700
Top-1 Accuracy· uses extra data· 2024-03-22
85.9
SOTA
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
VideoonKinetics-400
Acc@1· uses extra data· 2024-03-22
92.1
best: 93.6 (OmniVec2)
SOTA
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
VideoonKinetics-600
Top-1 Accuracy· uses extra data· 2024-03-22
91.9
SOTA
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
VideoonMIT
Top 1 Accuracy· 2024-03-22
51.2
SOTA
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
Video RetrievalonVATEX
video-to-text R@1· uses extra data· 2024-03-22
89.3
SOTA
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
Video RetrievalonActivityNet
text-to-video R@1· uses extra data· 2024-03-22
74.1
SOTA
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
Video RetrievalonActivityNet
video-to-text R@1· uses extra data· 2024-03-22
69.7
SOTA
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
Video RetrievalonDiDeMo
text-to-video R@1· uses extra data· 2024-03-22
74.2
SOTA
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
Video RetrievalonDiDeMo
video-to-text R@1· uses extra data· 2024-03-22
71.9
SOTA
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
Video RetrievalonLSMDC
text-to-video R@1· uses extra data· 2024-03-22
46.4
SOTA
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
Video RetrievalonLSMDC
video-to-text R@1· uses extra data· 2024-03-22
46.7
SOTA
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
Video RetrievalonMSVD
text-to-video R@1· uses extra data· 2024-03-22
61.4
SOTA
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
Video RetrievalonMSVD
video-to-text R@1· uses extra data· 2024-03-22
85.2
SOTA
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
Video RetrievalonQVHighlights
R@1,IoU=0.5· 2024-03-22
71.42
SOTA
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
Video RetrievalonQVHighlights
R@1,IoU=0.7· 2024-03-22
56.45
SOTA
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
Moment RetrievalonCharades-STA
R@1 IoU=0.5· 2024-03-22
70.03
best: 71.1 (SG-DETR (w/ PT))
SOTA
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
Moment RetrievalonCharades-STA
R@1 IoU=0.7· 2024-03-22
48.95
best: 52.8 (SG-DETR (w/ PT))
SOTA
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
Moment RetrievalonQVHighlights
R@1 IoU=0.5· uses extra data· 2024-03-22
71.42
best: 76.59 (LLaVA-MR)
SOTA
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
Moment RetrievalonQVHighlights
R@1 IoU=0.7· uses extra data· 2024-03-22
56.45
best: 61.48 (LLaVA-MR)
SOTA
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
Moment RetrievalonQVHighlights
mAP· uses extra data· 2024-03-22
49.24
best: 58.8 (SG-DETR (w/ PT))
SOTA
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
Video GroundingonQVHighlights
R@1,IoU=0.5· 2024-03-22
71.42
SOTA
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
Video GroundingonQVHighlights
R@1,IoU=0.7· 2024-03-22
56.45
SOTA
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
71.5
best: 83.9 (GRAM)
SOTA
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
97.1
best: 99.5 (GRAM)
SOTA
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
94
SOTA
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
99.3
SOTA
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
97.9
SOTA
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
55.9
SOTA
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
85.1
SOTA
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
78.3
SOTA
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
53.7
SOTA
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
84.1
SOTA
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
77.5
SOTA
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
59.3
SOTA
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
89.6
SOTA
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
84.4
SOTA
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
57.9
SOTA
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
SOTA
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
57.1
SOTA
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
85
SOTA
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
79.9
SOTA
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
33.8
SOTA
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
62.2
SOTA
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
55.9
SOTA
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
30.1
SOTA
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
54.8
SOTA
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
47.7
SOTA
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
63.2
SOTA
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
92.5
SOTA
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
85.6
SOTA
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
56.5
SOTA
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
90.3
SOTA
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
82.8
SOTA
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
VideoonHACS
Average-mAP· 2024-03-22
43.3
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
41.2
best: 42.9 (RDFA-S6 (InternVideo2-6B))
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
VideoonFineAction
mAP· 2024-03-22
27.7
best: 29.6 (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
72
best: 76.9 (AdaTAD (VideoMAEv2-giant))
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
VideoonVATEX
text-to-video R@1· uses extra data· 2024-03-22
75.5
best: 87.7 (GRAM)
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
VideoonMSR-VTT
text-to-video R@1· uses extra data· 2024-03-22
62.8
best: 64 (GRAM)
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
VideoonMSR-VTT
video-to-text R@1· uses extra data· 2024-03-22
60.2
best: 64.8 (GRAM)
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
Temporal Action LocalizationonHACS
Average-mAP· 2024-03-22
43.3
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
41.2
best: 42.9 (RDFA-S6 (InternVideo2-6B))
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
Temporal Action LocalizationonFineAction
mAP· 2024-03-22
27.7
best: 29.6 (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
72
best: 76.9 (AdaTAD (VideoMAEv2-giant))
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
Action LocalizationonHACS
Average-mAP· 2024-03-22
43.3
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
41.2
best: 42.9 (RDFA-S6 (InternVideo2-6B))
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
Action LocalizationonFineAction
mAP· 2024-03-22
27.7
best: 29.6 (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
72
best: 76.9 (AdaTAD (VideoMAEv2-giant))
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
Video RetrievalonVATEX
text-to-video R@1· uses extra data· 2024-03-22
75.5
best: 87.7 (GRAM)
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
Video RetrievalonMSR-VTT
text-to-video R@1· uses extra data· 2024-03-22
62.8
best: 64 (GRAM)
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
Video RetrievalonMSR-VTT
video-to-text R@1· uses extra data· 2024-03-22
60.2
best: 64.8 (GRAM)
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
85.3
best: 85.4 (InternVideo2-1B)
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
83.1
best: 83.3 (InternVideo2-1B)
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
97
best: 97.9 (LanguageBind(ViT-L/14))
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
94.2
best: 94.3 (InternVideo2-1B)
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
84.6
best: 85.1 (InternVideo2-1B)
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377

Robots6 results

Activity RecognitiononHACS
Top 1 Accuracy· uses extra data· 2024-03-22
97
SOTA
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
Activity RecognitiononSomething-Something V2
GFLOPs· uses extra data· 2024-03-22
13321
SOTA
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
Activity RecognitiononSomething-Something V2
Parameters· uses extra data· 2024-03-22
2131
SOTA
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
Activity RecognitiononSomething-Something V2
Top-1 Accuracy· uses extra data· 2024-03-22
1
best: 77.3 (MVD (Kinetics400 pretrain, ViT-H, 16 frame))
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
Activity RecognitiononSomething-Something V2
Top-5 Accuracy· uses extra data· 2024-03-22
12
best: 96.3 (DejaVid)
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
Activity RecognitiononActivityNet
mAP· uses extra data· 2024-03-22
95.9
best: 96.9 (Text4Vis (w/ ViT-L))
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377

Time Series6 results

Action RecognitiononHACS
Top 1 Accuracy· uses extra data· 2024-03-22
97
SOTA
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
Action RecognitiononSomething-Something V2
GFLOPs· uses extra data· 2024-03-22
13321
SOTA
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
Action RecognitiononSomething-Something V2
Parameters· uses extra data· 2024-03-22
2131
SOTA
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
Action RecognitiononSomething-Something V2
Top-1 Accuracy· uses extra data· 2024-03-22
1
best: 77.3 (MVD (Kinetics400 pretrain, ViT-H, 16 frame))
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
Action RecognitiononSomething-Something V2
Top-5 Accuracy· uses extra data· 2024-03-22
12
best: 96.3 (DejaVid)
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
Action RecognitiononActivityNet
mAP· uses extra data· 2024-03-22
95.9
best: 96.9 (Text4Vis (w/ ViT-L))
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377

Methodology4 results

Zero-Shot LearningonHACS
Average-mAP· 2024-03-22
43.3
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
41.2
best: 42.9 (RDFA-S6 (InternVideo2-6B))
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
Zero-Shot LearningonFineAction
mAP· 2024-03-22
27.7
best: 29.6 (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
72
best: 76.9 (AdaTAD (VideoMAEv2-giant))
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377

Audio2 results

Text to Audio RetrievalonAudioCaps
R@1· uses extra data· 2024-03-22
55.2
SOTA
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377
Text to Audio RetrievalonClotho
R@1· uses extra data· 2024-03-22
27.2
best: 27.69 (PaSST-RoBERTa & Estimated Audio–Caption Correspondences)
SOTA
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377

Natural Language Processing1 result

Question AnsweringonEgoSchema (fullset)
Accuracy· 2024-03-22
60.2
best: 71.14 (BIMBA-LLaVA-Qwen2-7B)
SOTA
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377

Reasoning1 result

Video Question AnsweringonEgoSchema (fullset)
Accuracy· 2024-03-22
60.2
best: 71.14 (BIMBA-LLaVA-Qwen2-7B)
SOTA
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding arXiv:2403.15377