SOTAVerified

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 AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 2101–2150 of 2759 papers

TitleStatusHype
STEP: Spatio-Temporal Progressive Learning for Video Action DetectionCode0
Out-of-Distribution Detection for Generalized Zero-Shot Action RecognitionCode0
DDLSTM: Dual-Domain LSTM for Cross-Dataset Action Recognition—0
Audio-Visual Model Distillation Using Acoustic ImagesCode0
REPAIR: Removing Representation Bias by Dataset ResamplingCode0
Multi-View Region Adaptive Multi-temporal DMM and RGB Action Recognition—0
Recurrent Space-time Graph Neural NetworksCode0
Attentive Action and Context Factorization—0
Localized Trajectories for 2D and 3D Action Recognition—0
Action Recognition from Single Timestamp Supervision in Untrimmed VideosCode0
Knowledge Distillation for Human Action Anticipation—0
SCSampler: Sampling Salient Clips from Video for Efficient Action Recognition—0
Relational Action Forecasting—0
LP-3DCNN: Unveiling Local Phase in 3D Convolutional Neural Networks—0
Attention Distillation for Learning Video Representations—0
End-to-End Video Captioning—0
Video Classification with Channel-Separated Convolutional NetworksCode0
Resource Efficient 3D Convolutional Neural NetworksCode0
Semantics-Guided Neural Networks for Efficient Skeleton-Based Human Action RecognitionCode0
On the Importance of Video Action Recognition for Visual Lipreading—0
Contextual Action Cues from Camera Sensor for Multi-Stream Action Recognition—0
Spatiotemporal Filtering for Event-Based Action Recognition—0
MFAS: Multimodal Fusion Architecture Search—0
Two-Stream Action Recognition-Oriented Video Super-ResolutionCode0
Investigation on Combining 3D Convolution of Image Data and Optical Flow to Generate Temporal Action Proposals—0
A Hybrid Framework for Action Recognition in Low-Quality Video Sequences—0
Collaborative Spatio-temporal Feature Learning for Video Action RecognitionCode0
Spatiotemporal Pyramid Network for Video Action Recognition—0
STAR-Net: Action Recognition using Spatio-Temporal Activation Reprojection—0
Beyond the Self: Using Grounded Affordances to Interpret and Describe Others' ActionsCode0
IF-TTN: Information Fused Temporal Transformation Network for Video Action Recognition—0
Privacy-Preserving Action Recognition using Coded Aperture Videos—0
An Attention Enhanced Graph Convolutional LSTM Network for Skeleton-Based Action Recognition—0
Learning Transferable Self-attentive Representations for Action Recognition in Untrimmed Videos with Weak Supervision—0
Dynamic Matrix Decomposition for Action Recognition—0
A Mobile Robot Generating Video Summaries of Seniors' Indoor Activities—0
Spatio-temporal Action Recognition: A Survey—0
DistInit: Learning Video Representations Without a Single Labeled Video—0
ODN: Opening the Deep Network for Open-set Action Recognition—0
Skeleton-based Action Recognition of People Handling Objects—0
Semantic Image Networks for Human Action Recognition—0
DMC-Net: Generating Discriminative Motion Cues for Fast Compressed Video Action Recognition—0
UAV-GESTURE: A Dataset for UAV Control and Gesture RecognitionCode0
Mutual Context Network for Jointly Estimating Egocentric Gaze and Actions—0
Action2Vec: A Crossmodal Embedding Approach to Action Learning—0
Cross-modal Learning by Hallucinating Missing Modalities in RGB-D VisionCode0
Learning to Recognize 3D Human Action from A New Skeleton-based Representation Using Deep Convolutional Neural Networks—0
Coupled Recurrent Network (CRN)—0
Temporal Hockey Action Recognition via Pose and Optical Flows—0
Canonical Correlation Analysis for Misaligned Satellite Image Change Detection—0
Show:102550
← PrevPage 43 of 56Next →
All datasetsSomething-Something V2UCF101HMDB-51Something-Something V1AVA v2.2EPIC-KITCHENS-100NTU RGB+DNTU RGB+D 120Diving-48ActivityNetAVA v2.1H2O (2 Hands and Objects)

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1MViTv2-B (IN-21K + Kinetics400 pretrain)Top-5 Accuracy93.4—Unverified
2RSANet-R50 (8+16 frames, ImageNet pretrained, 2 clips)Top-5 Accuracy91.1—Unverified
3MVD (Kinetics400 pretrain, ViT-H, 16 frame)Top-1 Accuracy77.3—Unverified
4DejaVidTop-1 Accuracy77.2—Unverified
5InternVideoTop-1 Accuracy77.2—Unverified
6InternVideo2-1BTop-1 Accuracy77.1—Unverified
7VideoMAE V2-gTop-1 Accuracy77—Unverified
8MVD (Kinetics400 pretrain, ViT-L, 16 frame)Top-1 Accuracy76.7—Unverified
9Hiera-L (no extra data)Top-1 Accuracy76.5—Unverified
10TubeViT-LTop-1 Accuracy76.1—Unverified
#ModelMetricClaimedVerifiedStatus
1FTP-UniFormerV2-L/143-fold Accuracy99.7—Unverified
2OmniVec23-fold Accuracy99.6—Unverified
3VideoMAE V2-g3-fold Accuracy99.6—Unverified
4OmniVec3-fold Accuracy99.6—Unverified
5BIKE3-fold Accuracy98.8—Unverified
6SMART3-fold Accuracy98.64—Unverified
7OmniSource (SlowOnly-8x8-R101-RGB + I3D-Flow)3-fold Accuracy98.6—Unverified
8PERF-Net (multi-distilled S3D)3-fold Accuracy98.6—Unverified
9ZeroI2V ViT-L/143-fold Accuracy98.6—Unverified
10LGD-3D Two-stream3-fold Accuracy98.2—Unverified