Action Recognition

Action Recognition is a computer vision task that involves recognizing human actions in videos or images. The goal is to classify and categorize the actions being performed in the video or image into a predefined set of action classes.

In the video domain, it is an open question whether training an action classification network on a sufficiently large dataset, will give a similar boost in performance when applied to a different temporal task or dataset. The challenges of building video datasets has meant that most popular benchmarks for action recognition are small, having on the order of 10k videos.

Please note some benchmarks may be located in the Action Classification or Video Classification tasks, e.g. Kinetics-400.

Papers

Recently Added Most Hyped Most Active Needs Verification Most Verified

Showing 751–760 of 2759 papers

Title	Date	Tasks	Status	Score
Learning with privileged information via adversarial discriminative modality distillation	Oct 19, 2018	Action RecognitionHallucination	CodeCode Available	5
Learning Video Representations from Correspondence Proposals	May 20, 2019	Action RecognitionAction Recognition In Videos	CodeCode Available	5
Discriminating Spatial and Temporal Relevance in Deep Taylor Decompositions for Explainable Activity Recognition	Aug 5, 2019	Action RecognitionActivity Recognition	CodeCode Available	5
Learn to cycle: Time-consistent feature discovery for action recognition	Jun 15, 2020	Action ClassificationAction Recognition	CodeCode Available	5
Learning to Estimate Pose by Watching Videos	Apr 13, 2017	Action RecognitionPose Estimation	CodeCode Available	5
Learning To Score Olympic Events	Nov 16, 2016	Action Quality AssessmentAction Recognition	CodeCode Available	5
Learning Spatio-Temporal Features with 3D Residual Networks for Action Recognition	Aug 25, 2017	Action RecognitionHand-Gesture Recognition	CodeCode Available	5
Learning Spatio-Temporal Representation with Local and Global Diffusion	Jun 13, 2019	Action ClassificationAction Detection	CodeCode Available	5
Learning Mutual Excitation for Hand-to-Hand and Human-to-Human Interaction Recognition	Feb 4, 2024	Action RecognitionHuman Interaction Recognition	CodeCode Available	5
Audio-Visual Scene Analysis with Self-Supervised Multisensory Features	Apr 10, 2018	Action RecognitionAudio Source Separation	CodeCode Available	5

Show:10 25 50

← PrevPage 76 of 276Next →

All datasets Something-Something V2 UCF101 HMDB-51 Something-Something V1 AVA v2.2 EPIC-KITCHENS-100 NTU RGB+D NTU RGB+D 120 Diving-48 ActivityNet AVA v2.1 H2O (2 Hands and Objects)

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	MViTv2-B (IN-21K + Kinetics400 pretrain)	Top-5 Accuracy	93.4	—	Unverified
2	RSANet-R50 (8+16 frames, ImageNet pretrained, 2 clips)	Top-5 Accuracy	91.1	—	Unverified
3	MVD (Kinetics400 pretrain, ViT-H, 16 frame)	Top-1 Accuracy	77.3	—	Unverified
4	DejaVid	Top-1 Accuracy	77.2	—	Unverified
5	InternVideo	Top-1 Accuracy	77.2	—	Unverified
6	InternVideo2-1B	Top-1 Accuracy	77.1	—	Unverified
7	VideoMAE V2-g	Top-1 Accuracy	77	—	Unverified
8	MVD (Kinetics400 pretrain, ViT-L, 16 frame)	Top-1 Accuracy	76.7	—	Unverified
9	Hiera-L (no extra data)	Top-1 Accuracy	76.5	—	Unverified
10	TubeViT-L	Top-1 Accuracy	76.1	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	FTP-UniFormerV2-L/14	3-fold Accuracy	99.7	—	Unverified
2	OmniVec2	3-fold Accuracy	99.6	—	Unverified
3	VideoMAE V2-g	3-fold Accuracy	99.6	—	Unverified
4	OmniVec	3-fold Accuracy	99.6	—	Unverified
5	BIKE	3-fold Accuracy	98.8	—	Unverified
6	SMART	3-fold Accuracy	98.64	—	Unverified
7	OmniSource (SlowOnly-8x8-R101-RGB + I3D-Flow)	3-fold Accuracy	98.6	—	Unverified
8	PERF-Net (multi-distilled S3D)	3-fold Accuracy	98.6	—	Unverified
9	ZeroI2V ViT-L/14	3-fold Accuracy	98.6	—	Unverified
10	LGD-3D Two-stream	3-fold Accuracy	98.2	—	Unverified