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 2626–2650 of 2759 papers

Title	Date	Tasks	Status	Hype
Long-Range Trajectories from Global and Local Motion Representations	Sep 29, 2015	Action RecognitionMotion Segmentation	—Unverified	0
Hyper-Fisher Vectors for Action Recognition	Sep 28, 2015	Action RecognitionTemporal Action Localization	—Unverified	0
Bio-Inspired Human Action Recognition using Hybrid Max-Product Neuro-Fuzzy Classifier and Quantum-Behaved PSO	Sep 13, 2015	Action RecognitionForm	—Unverified	0
Manipulated Object Proposal: A Discriminative Object Extraction and Feature Fusion Framework for First-Person Daily Activity Recognition	Sep 2, 2015	Action RecognitionActivity Recognition	—Unverified	0
Action Recognition by Hierarchical Mid-level Action Elements	Aug 31, 2015	Action ParsingAction Recognition	—Unverified	0
Cooking in the kitchen: Recognizing and Segmenting Human Activities in Videos	Aug 25, 2015	Action RecognitionTemporal Action Localization	—Unverified	0
Action Recognition based on Subdivision-Fusion Model	Aug 18, 2015	Action Recognitionmodel	—Unverified	0
Multimodal Multipart Learning for Action Recognition in Depth Videos	Jul 31, 2015	Action Recognitionfeature selection	—Unverified	0
Action recognition in still images by latent superpixel classification	Jul 30, 2015	Action RecognitionAction Recognition In Still Images	—Unverified	0
Every Moment Counts: Dense Detailed Labeling of Actions in Complex Videos	Jul 21, 2015	Action RecognitionRetrieval	CodeCode Available	0
Towards Good Practices for Very Deep Two-Stream ConvNets	Jul 8, 2015	Action RecognitionAction Recognition In Videos	CodeCode Available	1
Time Series Classification using the Hidden-Unit Logistic Model	Jun 16, 2015	Action RecognitionAction Unit Detection	—Unverified	0
Slow and steady feature analysis: higher order temporal coherence in video	Jun 15, 2015	Action RecognitionTemporal Action Localization	—Unverified	0
P-CNN: Pose-based CNN Features for Action Recognition	Jun 11, 2015	Action RecognitionTemporal Action Localization	—Unverified	0
Hierarchical recurrent neural network for skeleton based action recognition	Jun 7, 2015	Action RecognitionComputational Efficiency	—Unverified	0
First-Take-All: Temporal Order-Preserving Hashing for 3D Action Videos	Jun 6, 2015	3D Action RecognitionAction Recognition	—Unverified	0
Modeling Video Evolution for Action Recognition	Jun 1, 2015	Action RecognitionSkeleton Based Action Recognition	—Unverified	0
Space-Time Tree Ensemble for Action Recognition	Jun 1, 2015	Action RecognitionClustering	—Unverified	0
Interaction Part Mining: A Mid-Level Approach for Fine-Grained Action Recognition	Jun 1, 2015	Action RecognitionFine-grained Action Recognition	—Unverified	0
Learning a Non-Linear Knowledge Transfer Model for Cross-View Action Recognition	Jun 1, 2015	Action RecognitionTemporal Action Localization	—Unverified	0
Can Humans Fly? Action Understanding With Multiple Classes of Actors	Jun 1, 2015	Action RecognitionAction Understanding	—Unverified	0
DevNet: A Deep Event Network for Multimedia Event Detection and Evidence Recounting	Jun 1, 2015	Action RecognitionEvent Detection	—Unverified	0
Multi-Feature Max-Margin Hierarchical Bayesian Model for Action Recognition	Jun 1, 2015	Action RecognitionGeneral Classification	—Unverified	0
Bilinear Heterogeneous Information Machine for RGB-D Action Recognition	Jun 1, 2015	Action RecognitionTemporal Action Localization	—Unverified	0
ActivityNet: A Large-Scale Video Benchmark for Human Activity Understanding	Jun 1, 2015	Action DetectionAction Recognition	CodeCode Available	0

Show:10 25 50

← PrevPage 106 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