Action Recognition In Videos

Action Recognition in Videos is a task in computer vision and pattern recognition where the goal is to identify and categorize human actions performed in a video sequence. The task involves analyzing the spatiotemporal dynamics of the actions and mapping them to a predefined set of action classes, such as running, jumping, or swimming.

Papers

Recently Added Most Hyped Most Active Needs Verification Most Verified

Showing 51–60 of 124 papers

Title	Date	Tasks	Status
Co-training Transformer with Videos and Images Improves Action Recognition	Dec 14, 2021	Action ClassificationAction Recognition	—Unverified
Technical Report: Disentangled Action Parsing Networks for Accurate Part-level Action Parsing	Nov 5, 2021	Action ParsingAction Recognition	—Unverified
Class incremental learning for video action classification	Sep 19, 2021	Action ClassificationAction Recognition In Videos	—Unverified
NAS-TC: Neural Architecture Search on Temporal Convolutions for Complex Action Recognition	Mar 17, 2021	Action RecognitionAction Recognition In Videos	—Unverified
Video Transformer Network	Feb 1, 2021	Action ClassificationAction Recognition	CodeCode Available
Temporal Difference Networks for Action Recognition	Jan 1, 2021	Action RecognitionAction Recognition In Videos	—Unverified
Towards Improving Spatiotemporal Action Recognition in Videos	Dec 15, 2020	Action DetectionAction Localization	CodeCode Available
Developing Motion Code Embedding for Action Recognition in Videos	Dec 10, 2020	Action RecognitionAction Recognition In Videos	—Unverified
Pose And Joint-Aware Action Recognition	Oct 16, 2020	Action ClassificationAction Recognition	CodeCode Available
Toward Accurate Person-level Action Recognition in Videos of Crowded Scenes	Oct 16, 2020	Action RecognitionAction Recognition In Videos	—Unverified

Show:10 25 50

← PrevPage 6 of 13Next →

All datasets Jester (Gesture Recognition)PKU-MMD UCF101 Something-Something V2 Kinetics 400 AVA v2.2 FS-Something-Something V2-Full FS-Something-Something V2-Small Sports-1M THUMOS14 ActivityNet AVA v2.1

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	CPNet Res34, 5 CP	Val	96.7	—	Unverified
2	STM (Resnet-50, 16 frames)	Val	96.7	—	Unverified
3	MFNet	Val	96.68	—	Unverified
4	DIN	Val	95.31	—	Unverified
5	MultiScale TRN	Val	95.31	—	Unverified
6	convSTAR	Val	92.7	—	Unverified
7	3D-SqueezeNet	Val	90.77	—	Unverified
8	3D-ShuffleNetV2 0.25x	Val	86.91	—	Unverified
9	3D-MobileNetV2 0.2x	Val	86.43	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	MMNet	X-Sub	97.4	—	Unverified
2	DSCNet (RGB + Pose)	X-Sub	97.4	—	Unverified
3	EPAM-Net	X-Sub	96.2	—	Unverified
4	DVANet (RGB only)	X-Sub	95.8	—	Unverified
5	TSMF	X-Sub	95.8	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	STM (ImageNet+Kinetics pretrain)	3-fold Accuracy	96.2	—	Unverified
2	3D-SqueezeNet	3-fold Accuracy	74.94	—	Unverified
3	3D-ShuffleNetV2 0.25x	3-fold Accuracy	56.52	—	Unverified
4	3D-MobileNetV2 0.2x	3-fold Accuracy	55.56	—	Unverified
5	Baseline UCF101	3-fold Accuracy	43.9	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	STM (16 frames, ImageNet pretraining)	Top-1 Accuracy	64.2	—	Unverified
2	CPNet Res34, 5 CP	Top-1 Accuracy	57.65	—	Unverified
3	2-Stream TRN	Top-1 Accuracy	55.52	—	Unverified
4	DIN	Top-1 Accuracy	34.11	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Florence	Top-1 Accuracy	86.5	—	Unverified
2	ActionCLIP (ViT-B/16)	Top-1 Accuracy	83.8	—	Unverified
3	Frozen Backbone, SwinV2-G-ext22K (Video-Swin)	Top-1 Accuracy	81.7	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	YOWO+LFB*	mAP (Val)	20.2	—	Unverified
2	VideoMAE V2	mAP (Val)	18.24	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	ITANet	Top-1 Accuracy(5-Way-1-Shot)	49.2	—	Unverified
2	OTAM[3]++	Top-1 Accuracy(5-Way-1-Shot)	42.8	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	ITANet	Top-1 Accuracy(5-Way-1-Shot)	39.8	—	Unverified
2	CMN[35]	Top-1 Accuracy(5-Way-1-Shot)	36.2	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	G-Blend	Video hit@1	74.8	—	Unverified
2	LSTM +Pretrained on YT-8M	Video hit@1	65.7	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Single-stream R-C3D (two-way buffer)	mAP@0.1	54.5	—	Unverified
2	Single-stream R-C3D (one-way buffer)	mAP@0.1	51.6	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	LSTM + Pretrained on YT-8M	mAP	75.6	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	YOWO+LFB*	mAP (Val)	19.2	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	STM (ImageNet+Kinetics pretrain)	Average accuracy of 3 splits	72.2	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Florence	Top-1 Accuracy	87.8	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	G-Blend	Clip Hit@1	49.7	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	2D-3D-Softargmax (RGB only)	Accuracy (CS)	85.5	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	STM (16 frames, ImageNet pretraining)	Top 1 Accuracy	50.7	—	Unverified