Tasks
SotA
Datasets
Papers
Methods
Submit
About
Datasets
/
Activity
Activity
Benchmarks
General Classification
/
Accuracy
Related Benchmarks
ActivityNet
/
Action Detection
/
mIoU
ActivityNet
/
Action Recognition
/
mAP
ActivityNet
/
Action Recognition In Videos
/
mAP
ActivityNet
/
Activity Recognition
/
mAP
ActivityNet
/
Video
/
Top 1 Accuracy
ActivityNet
/
Video
/
Top 5 Accuracy
ActivityNet
/
Video
/
text-to-video Mean Rank
ActivityNet
/
Video
/
text-to-video Median Rank
ActivityNet
/
Video
/
text-to-video R@1
ActivityNet
/
Video
/
text-to-video R@10
ActivityNet
/
Video
/
text-to-video R@5
ActivityNet
/
Video
/
text-to-video R@50
ActivityNet
/
Video
/
video-to-text Mean Rank
ActivityNet
/
Video
/
video-to-text Median Rank
ActivityNet
/
Video
/
video-to-text R@1
ActivityNet
/
Video
/
video-to-text R@10
ActivityNet
/
Video
/
video-to-text R@5
ActivityNet
/
Video
/
video-to-text R@50
ActivityNet
/
Video Retrieval
/
text-to-video Mean Rank
ActivityNet
/
Video Retrieval
/
text-to-video Median Rank
ActivityNet
/
Video Retrieval
/
text-to-video R@1
ActivityNet
/
Video Retrieval
/
text-to-video R@10
ActivityNet
/
Video Retrieval
/
text-to-video R@5
ActivityNet
/
Video Retrieval
/
text-to-video R@50
ActivityNet
/
Video Retrieval
/
video-to-text Mean Rank
ActivityNet
/
Video Retrieval
/
video-to-text Median Rank
ActivityNet
/
Video Retrieval
/
video-to-text R@1
ActivityNet
/
Video Retrieval
/
video-to-text R@10
ActivityNet
/
Video Retrieval
/
video-to-text R@5
ActivityNet
/
Video Retrieval
/
video-to-text R@50
ActivityNet
/
Visual Question Answering (VQA)
/
ClipMatch@1
ActivityNet
/
Visual Question Answering (VQA)
/
ClipMatch@5
ActivityNet
/
Visual Question Answering (VQA)
/
Contains
ActivityNet
/
Visual Question Answering (VQA)
/
ExactMatch
ActivityNet
/
Visual Question Answering (VQA)
/
Follow-up ClipMatch@1
ActivityNet
/
Visual Question Answering (VQA)
/
Follow-up ClipMatch@5
ActivityNet
/
Visual Question Answering (VQA)
/
Follow-up Contains
ActivityNet
/
Visual Question Answering (VQA)
/
Follow-up ExactMatch
ActivityNet
/
Zero-Shot Action Recognition
/
Top-1 Accuracy
ActivityNet
/
Zero-Shot Video Retrieval
/
text-to-video R@1
ActivityNet
/
Zero-Shot Video Retrieval
/
text-to-video R@10
ActivityNet
/
Zero-Shot Video Retrieval
/
text-to-video R@5
ActivityNet
/
Zero-Shot Video Retrieval
/
video-to-text R@1
ActivityNet
/
Zero-Shot Video Retrieval
/
video-to-text R@10
ActivityNet
/
Zero-Shot Video Retrieval
/
video-to-text R@5
ActivityNet Adverbs
/
Video
/
Acc-A
ActivityNet Adverbs
/
Video
/
mAP M
ActivityNet Adverbs
/
Video
/
mAP W
ActivityNet Adverbs
/
Video Retrieval
/
Acc-A
ActivityNet Adverbs
/
Video Retrieval
/
mAP M
ActivityNet Adverbs
/
Video Retrieval
/
mAP W
ActivityNet Adverbs
/
Video-Adverb Retrieval
/
Acc-A
ActivityNet Adverbs
/
Video-Adverb Retrieval
/
mAP M
ActivityNet Adverbs
/
Video-Adverb Retrieval
/
mAP W
ActivityNet Captions
/
10-shot image generation
/
Recall@Sum
ActivityNet Captions
/
Action Localization
/
Average F1
ActivityNet Captions
/
Action Localization
/
Average Precision
ActivityNet Captions
/
Action Localization
/
Average Recall
ActivityNet Captions
/
Dense Captioning
/
Live Score
ActivityNet Captions
/
Dense Video Captioning
/
BLEU-3
ActivityNet Captions
/
Dense Video Captioning
/
BLEU-4
ActivityNet Captions
/
Dense Video Captioning
/
BLEU4
ActivityNet Captions
/
Dense Video Captioning
/
CIDEr
ActivityNet Captions
/
Dense Video Captioning
/
DIV-1
ActivityNet Captions
/
Dense Video Captioning
/
DIV-2
ActivityNet Captions
/
Dense Video Captioning
/
F1
ActivityNet Captions
/
Dense Video Captioning
/
METEOR
ActivityNet Captions
/
Dense Video Captioning
/
Precision
ActivityNet Captions
/
Dense Video Captioning
/
RE-4
ActivityNet Captions
/
Dense Video Captioning
/
Recall
ActivityNet Captions
/
Dense Video Captioning
/
SODA
ActivityNet Captions
/
Temporal Action Localization
/
Average F1
ActivityNet Captions
/
Temporal Action Localization
/
Average Precision
ActivityNet Captions
/
Temporal Action Localization
/
Average Recall
ActivityNet Captions
/
Text to Video Retrieval
/
Recall@Sum
ActivityNet Captions
/
Video
/
Average F1
ActivityNet Captions
/
Video
/
Average Precision
ActivityNet Captions
/
Video
/
Average Recall
ActivityNet Captions
/
Video
/
R@1,IoU=0.5
ActivityNet Captions
/
Video
/
R@1,IoU=0.7
ActivityNet Captions
/
Video
/
R@5,IoU=0.5
ActivityNet Captions
/
Video
/
R@5,IoU=0.7
ActivityNet Captions
/
Video Captioning
/
BLEU-3
ActivityNet Captions
/
Video Captioning
/
BLEU-4
ActivityNet Captions
/
Video Captioning
/
BLEU4
ActivityNet Captions
/
Video Captioning
/
CIDEr
ActivityNet Captions
/
Video Captioning
/
DIV-1
ActivityNet Captions
/
Video Captioning
/
DIV-2
ActivityNet Captions
/
Video Captioning
/
F1
ActivityNet Captions
/
Video Captioning
/
Live Score
ActivityNet Captions
/
Video Captioning
/
METEOR
ActivityNet Captions
/
Video Captioning
/
Precision
ActivityNet Captions
/
Video Captioning
/
RE-4
ActivityNet Captions
/
Video Captioning
/
ROUGE-L
ActivityNet Captions
/
Video Captioning
/
Recall
ActivityNet Captions
/
Video Captioning
/
SODA
ActivityNet Captions
/
Zero-Shot Learning
/
Average F1
ActivityNet Captions
/
Zero-Shot Learning
/
Average Precision
ActivityNet Captions
/
Zero-Shot Learning
/
Average Recall
ActivityNet-1.2
/
Action Localization
/
Mean mAP
ActivityNet-1.2
/
Action Localization
/
mAP IOU@0.1
ActivityNet-1.2
/
Action Localization
/
mAP IOU@0.3
ActivityNet-1.2
/
Action Localization
/
mAP IOU@0.5
ActivityNet-1.2
/
Action Localization
/
mAP IOU@0.7
ActivityNet-1.2
/
Action Localization
/
mAP@0.5
ActivityNet-1.2
/
Temporal Action Localization
/
Mean mAP
ActivityNet-1.2
/
Temporal Action Localization
/
mAP IOU@0.1
ActivityNet-1.2
/
Temporal Action Localization
/
mAP IOU@0.3
ActivityNet-1.2
/
Temporal Action Localization
/
mAP IOU@0.5
ActivityNet-1.2
/
Temporal Action Localization
/
mAP IOU@0.7
ActivityNet-1.2
/
Temporal Action Localization
/
mAP@0.5
ActivityNet-1.2
/
Video
/
Mean mAP
ActivityNet-1.2
/
Video
/
mAP
ActivityNet-1.2
/
Video
/
mAP IOU@0.1
ActivityNet-1.2
/
Video
/
mAP IOU@0.3
ActivityNet-1.2
/
Video
/
mAP IOU@0.5
ActivityNet-1.2
/
Video
/
mAP IOU@0.7
ActivityNet-1.2
/
Video
/
mAP@0.5
ActivityNet-1.2
/
Weakly Supervised Action Localization
/
Mean mAP
ActivityNet-1.2
/
Weakly Supervised Action Localization
/
mAP@0.5
ActivityNet-1.2
/
Zero-Shot Learning
/
Mean mAP
ActivityNet-1.2
/
Zero-Shot Learning
/
mAP IOU@0.1
ActivityNet-1.2
/
Zero-Shot Learning
/
mAP IOU@0.3
ActivityNet-1.2
/
Zero-Shot Learning
/
mAP IOU@0.5
ActivityNet-1.2
/
Zero-Shot Learning
/
mAP IOU@0.7
ActivityNet-1.2
/
Zero-Shot Learning
/
mAP@0.5
ActivityNet-1.3
/
Action Localization
/
AR@100
ActivityNet-1.3
/
Action Localization
/
AUC (test)
ActivityNet-1.3
/
Action Localization
/
AUC (val)
ActivityNet-1.3
/
Action Localization
/
mAP
ActivityNet-1.3
/
Action Localization
/
mAP IOU@0.5
ActivityNet-1.3
/
Action Localization
/
mAP IOU@0.75
ActivityNet-1.3
/
Action Localization
/
mAP IOU@0.95
ActivityNet-1.3
/
Action Localization
/
mAP@0.5
ActivityNet-1.3
/
Action Localization
/
mAP@0.5:0.95
ActivityNet-1.3
/
Temporal Action Localization
/
AR@100
ActivityNet-1.3
/
Temporal Action Localization
/
AUC (test)
ActivityNet-1.3
/
Temporal Action Localization
/
AUC (val)
ActivityNet-1.3
/
Temporal Action Localization
/
mAP
ActivityNet-1.3
/
Temporal Action Localization
/
mAP IOU@0.5
ActivityNet-1.3
/
Temporal Action Localization
/
mAP IOU@0.75
ActivityNet-1.3
/
Temporal Action Localization
/
mAP IOU@0.95
ActivityNet-1.3
/
Temporal Action Localization
/
mAP@0.5
ActivityNet-1.3
/
Temporal Action Localization
/
mAP@0.5:0.95
ActivityNet-1.3
/
Video
/
AR@100
ActivityNet-1.3
/
Video
/
AUC (test)
ActivityNet-1.3
/
Video
/
AUC (val)
ActivityNet-1.3
/
Video
/
mAP
ActivityNet-1.3
/
Video
/
mAP IOU@0.5
ActivityNet-1.3
/
Video
/
mAP IOU@0.75
ActivityNet-1.3
/
Video
/
mAP IOU@0.95
ActivityNet-1.3
/
Video
/
mAP@0.5
ActivityNet-1.3
/
Video
/
mAP@0.5:0.95
ActivityNet-1.3
/
Weakly Supervised Action Localization
/
mAP@0.5
ActivityNet-1.3
/
Weakly Supervised Action Localization
/
mAP@0.5:0.95
ActivityNet-1.3
/
Weakly-supervised Temporal Action Localization
/
mAP
ActivityNet-1.3
/
Weakly-supervised Temporal Action Localization
/
mAP IOU@0.5
ActivityNet-1.3
/
Weakly-supervised Temporal Action Localization
/
mAP IOU@0.75
ActivityNet-1.3
/
Weakly-supervised Temporal Action Localization
/
mAP IOU@0.95
ActivityNet-1.3
/
Zero-Shot Learning
/
AR@100
ActivityNet-1.3
/
Zero-Shot Learning
/
AUC (test)
ActivityNet-1.3
/
Zero-Shot Learning
/
AUC (val)
ActivityNet-1.3
/
Zero-Shot Learning
/
mAP
ActivityNet-1.3
/
Zero-Shot Learning
/
mAP IOU@0.5
ActivityNet-1.3
/
Zero-Shot Learning
/
mAP IOU@0.75
ActivityNet-1.3
/
Zero-Shot Learning
/
mAP IOU@0.95
ActivityNet-1.3
/
Zero-Shot Learning
/
mAP@0.5
ActivityNet-1.3
/
Zero-Shot Learning
/
mAP@0.5:0.95
ActivityNet-GZSL (cls)
/
Zero-Shot Learning
/
HM
ActivityNet-GZSL (cls)
/
Zero-Shot Learning
/
ZSL
ActivityNet-GZSL(main)
/
Zero-Shot Learning
/
HM
ActivityNet-GZSL(main)
/
Zero-Shot Learning
/
ZSL
ActivityNet-QA
/
Question Answering
/
Accuracy
ActivityNet-QA
/
Question Answering
/
Confidence Score
ActivityNet-QA
/
Video Question Answering
/
Accuracy
ActivityNet-QA
/
Video Question Answering
/
Confidence Score
ActivityNet-QA
/
Video Question Answering
/
Confidence score