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 776–800 of 2759 papers

Title	Date	Tasks	Status	Score
Learning Visual Actions Using Multiple Verb-Only Labels	Jul 25, 2019	Action RecognitionCross-Modal Retrieval	CodeCode Available	5
Audio-Visual Model Distillation Using Acoustic Images	Apr 16, 2019	Action RecognitionAudio Classification	CodeCode Available	5
Learning To Score Olympic Events	Nov 16, 2016	Action Quality AssessmentAction Recognition	CodeCode Available	5
Efficient Human Vision Inspired Action Recognition using Adaptive Spatiotemporal Sampling	Jul 12, 2022	Action Recognition	CodeCode Available	5
DetReIDX: A Stress-Test Dataset for Real-World UAV-Based Person Recognition	May 7, 2025	Action RecognitionFederated Lifelong Person ReID	CodeCode Available	5
Learning to Estimate Pose by Watching Videos	Apr 13, 2017	Action RecognitionPose Estimation	CodeCode Available	5
Learning with privileged information via adversarial discriminative modality distillation	Oct 19, 2018	Action RecognitionHallucination	CodeCode Available	5
Learning Spatio-Temporal Representation with Local and Global Diffusion	Jun 13, 2019	Action ClassificationAction Detection	CodeCode Available	5
Learning Spatio-Temporal Features with 3D Residual Networks for Action Recognition	Aug 25, 2017	Action RecognitionHand-Gesture Recognition	CodeCode Available	5
Detecting the Starting Frame of Actions in Video	Jun 7, 2019	Action Recognition	CodeCode Available	5
Detecting Object States vs Detecting Objects: A New Dataset and a Quantitative Experimental Study	Dec 15, 2021	Action RecognitionAffordance Detection	CodeCode Available	5
Efficient Transfer Learning for Video-language Foundation Models	Nov 18, 2024	Action RecognitionFew-Shot Learning	CodeCode Available	5
Learning Skeletal Graph Neural Networks for Hard 3D Pose Estimation	Aug 16, 2021	3D Human Pose Estimation3D Pose Estimation	CodeCode Available	5
Action Recognition based on Cross-Situational Action-object Statistics	Aug 15, 2022	Action RecognitionObject	CodeCode Available	5
Describing Videos by Exploiting Temporal Structure	Feb 27, 2015	Action RecognitionImage Description	CodeCode Available	5
Learn to cycle: Time-consistent feature discovery for action recognition	Jun 15, 2020	Action ClassificationAction Recognition	CodeCode Available	5
Learning Graph Convolutional Network for Skeleton-based Human Action Recognition by Neural Searching	Nov 11, 2019	Action RecognitionNeural Architecture Search	CodeCode Available	5
Learning Human Action Recognition Representations Without Real Humans	Nov 10, 2023	Action RecognitionEthics	CodeCode Available	5
On Modality Bias Recognition and Reduction	Feb 25, 2022	Action RecognitionMulti-modal Classification	CodeCode Available	5
Learning from Video and Text via Large-Scale Discriminative Clustering	Jul 27, 2017	Action RecognitionClustering	CodeCode Available	5
Egocentric RGB+Depth Action Recognition in Industry-Like Settings	Sep 25, 2023	Action Recognition	CodeCode Available	5
Attentive Semantic Video Generation using Captions	Aug 20, 2017	Action RecognitionStyle Transfer	CodeCode Available	5
Beyond the Self: Using Grounded Affordances to Interpret and Describe Others' Actions	Feb 26, 2019	Action RecognitionTemporal Action Localization	CodeCode Available	5
Learning Gating ConvNet for Two-Stream based Methods in Action Recognition	Sep 12, 2017	Action ClassificationAction Recognition	CodeCode Available	5
Learning long-term dependencies for action recognition with a biologically-inspired deep network	Nov 16, 2016	Action RecognitionTemporal Action Localization	CodeCode Available	5

Show:10 25 50

← PrevPage 32 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	InternVideo	Top-1 Accuracy	77.2	—	Unverified
5	DejaVid	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	OmniVec	3-fold Accuracy	99.6	—	Unverified
4	VideoMAE V2-g	3-fold Accuracy	99.6	—	Unverified
5	BIKE	3-fold Accuracy	98.8	—	Unverified
6	SMART	3-fold Accuracy	98.64	—	Unverified
7	ZeroI2V ViT-L/14	3-fold Accuracy	98.6	—	Unverified
8	OmniSource (SlowOnly-8x8-R101-RGB + I3D-Flow)	3-fold Accuracy	98.6	—	Unverified
9	PERF-Net (multi-distilled S3D)	3-fold Accuracy	98.6	—	Unverified
10	Text4Vis	3-fold Accuracy	98.2	—	Unverified