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 1776–1800 of 2759 papers

Title	Date	Tasks	Status	Hype
Action Localization through Continual Predictive Learning	Mar 26, 2020	Action LocalizationAction Recognition	—Unverified	0
Modeling Cross-view Interaction Consistency for Paired Egocentric Interaction Recognition	Mar 24, 2020	Action Recognition	—Unverified	0
Ensembles of Deep Neural Networks for Action Recognition in Still Images	Mar 22, 2020	Action ClassificationAction Recognition	—Unverified	0
Temporally Coherent Embeddings for Self-Supervised Video Representation Learning	Mar 21, 2020	Action RecognitionMetric Learning	CodeCode Available	1
Temporal Extension Module for Skeleton-Based Action Recognition	Mar 19, 2020	Action RecognitionSkeleton Based Action Recognition	—Unverified	0
STH: Spatio-Temporal Hybrid Convolution for Efficient Action Recognition	Mar 18, 2020	Action Recognition	—Unverified	0
Predictively Encoded Graph Convolutional Network for Noise-Robust Skeleton-based Action Recognition	Mar 17, 2020	Action RecognitionSkeleton Based Action Recognition	CodeCode Available	1
Feedback Graph Convolutional Network for Skeleton-based Action Recognition	Mar 17, 2020	Action RecognitionSkeleton Based Action Recognition	—Unverified	0
Energy-based Periodicity Mining with Deep Features for Action Repetition Counting in Unconstrained Videos	Mar 15, 2020	Action Recognition	—Unverified	0
Gimme Signals: Discriminative signal encoding for multimodal activity recognition	Mar 13, 2020	Action RecognitionActivity Recognition	CodeCode Available	1
Skeleton Based Action Recognition using a Stacked Denoising Autoencoder with Constraints of Privileged Information	Mar 12, 2020	Action RecognitionDenoising	—Unverified	0
Top-1 Solution of Multi-Moments in Time Challenge 2019	Mar 12, 2020	Action RecognitionVideo Understanding	CodeCode Available	1
Beyond the Camera: Neural Networks in World Coordinates	Mar 12, 2020	Action RecognitionVideo Stabilization	—Unverified	0
On Compositions of Transformations in Contrastive Self-Supervised Learning	Mar 9, 2020	Action RecognitionAudio Classification	CodeCode Available	1
Unifying Graph Embedding Features with Graph Convolutional Networks for Skeleton-based Action Recognition	Mar 6, 2020	Action RecognitionGraph Embedding	—Unverified	0
Self-Supervised Visual Learning by Variable Playback Speeds Prediction of a Video	Mar 5, 2020	Action RecognitionRepresentation Learning	CodeCode Available	0
The iCub multisensor datasets for robot and computer vision applications	Mar 4, 2020	Action RecognitionGeneral Classification	—Unverified	0
Image-based OoD-Detector Principles on Graph-based Input Data in Human Action Recognition	Mar 3, 2020	Action RecognitionMetric Learning	—Unverified	0
Infrared and 3D skeleton feature fusion for RGB-D action recognition	Feb 28, 2020	Action ClassificationAction Recognition	CodeCode Available	1
Evolving Losses for Unsupervised Video Representation Learning	Feb 26, 2020	Action RecognitionFew-Shot Learning	—Unverified	0
Human Action Recognition using Local Two-Stream Convolution Neural Network Features and Support Vector Machines	Feb 19, 2020	Action ClassificationAction Recognition	—Unverified	0
Knowledge Integration Networks for Action Recognition	Feb 18, 2020	Action RecognitionHuman Parsing	—Unverified	0
A Survey on 3D Skeleton-Based Action Recognition Using Learning Method	Feb 14, 2020	Action RecognitionDeep Learning	—Unverified	0
Variational Conditional Dependence Hidden Markov Models for Skeleton-Based Action Recognition	Feb 13, 2020	Action RecognitionMissing Values	—Unverified	0
Learning spatio-temporal representations with temporal squeeze pooling	Feb 11, 2020	Action RecognitionClassification	—Unverified	0

Show:10 25 50

← PrevPage 72 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