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 2401–2425 of 2759 papers

Title	Date	Tasks	Status	Hype
Learning without Prejudice: Avoiding Bias in Webly-Supervised Action Recognition	Jun 14, 2017	Action RecognitionOptical Flow Estimation	—Unverified	0
The "something something" video database for learning and evaluating visual common sense	Jun 13, 2017	Action RecognitionCommon Sense Reasoning	CodeCode Available	1
Joint Max Margin and Semantic Features for Continuous Event Detection in Complex Scenes	Jun 13, 2017	Action RecognitionEvent Detection	—Unverified	0
Learning to Learn from Noisy Web Videos	Jun 9, 2017	Action RecognitionQ-Learning	—Unverified	0
Concurrence-Aware Long Short-Term Sub-Memories for Person-Person Action Recognition	Jun 3, 2017	Action RecognitionTemporal Action Localization	—Unverified	0
Deep manifold-to-manifold transforming network for action recognition	May 30, 2017	Action RecognitionTemporal Action Localization	—Unverified	0
Continuous Video to Simple Signals for Swimming Stroke Detection with Convolutional Neural Networks	May 28, 2017	Action RecognitionTemporal Action Localization	—Unverified	0
Sequence Summarization Using Order-constrained Kernelized Feature Subspaces	May 24, 2017	Action RecognitionRiemannian optimization	—Unverified	0
Ridiculously Fast Shot Boundary Detection with Fully Convolutional Neural Networks	May 23, 2017	Action RecognitionBoundary Detection	CodeCode Available	0
Two-Stream 3D Convolutional Neural Network for Skeleton-Based Action Recognition	May 23, 2017	3D Action RecognitionAction Recognition	—Unverified	0
AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actions	May 23, 2017	Actin DetectionAction Detection	CodeCode Available	1
Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset	May 22, 2017	Action ClassificationAction Recognition	CodeCode Available	1
Learning Spatiotemporal Features for Infrared Action Recognition with 3D Convolutional Neural Networks	May 18, 2017	Action RecognitionOptical Flow Estimation	—Unverified	0
Single Image Action Recognition by Predicting Space-Time Saliency	May 12, 2017	Action ClassificationAction Recognition	—Unverified	0
An Improved Video Analysis using Context based Extension of LSH	May 10, 2017	Action RecognitionRetrieval	—Unverified	0
Deep Spatio-temporal Manifold Network for Action Recognition	May 9, 2017	Action RecognitionTemporal Action Localization	—Unverified	0
CHAM: action recognition using convolutional hierarchical attention model	May 9, 2017	Action RecognitionImage Captioning	—Unverified	0
Temporal Segment Networks for Action Recognition in Videos	May 8, 2017	Action ClassificationAction Recognition	CodeCode Available	2
Investigation of Different Skeleton Features for CNN-based 3D Action Recognition	May 2, 2017	3D Action RecognitionAction Analysis	CodeCode Available	0
Joint Denoising / Compression of Image Contours via Shape Prior and Context Tree	Apr 30, 2017	Action RecognitionDenoising	—Unverified	0
Action Understanding with Multiple Classes of Actors	Apr 27, 2017	Action RecognitionAction Segmentation	—Unverified	0
Skeleton-based Action Recognition with Convolutional Neural Networks	Apr 25, 2017	Action ClassificationAction Detection	CodeCode Available	1
An Analysis of Action Recognition Datasets for Language and Vision Tasks	Apr 24, 2017	Action RecognitionImage Retrieval	—Unverified	0
Body Joint guided 3D Deep Convolutional Descriptors for Action Recognition	Apr 24, 2017	Action RecognitionTemporal Action Localization	—Unverified	0
Second-order Temporal Pooling for Action Recognition	Apr 23, 2017	Action RecognitionTemporal Action Localization	—Unverified	0

Show:10 25 50

← PrevPage 97 of 111Next →

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