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 2251–2300 of 2759 papers

TitleStatusHype
Skeleton-Based Action Recognition with Spatial Reasoning and Temporal Stack Learning—0
Learning Optical Flow via Dilated Networks and Occlusion Reasoning—0
Relational Network for Skeleton-Based Action Recognition—0
Object Activity Scene Description, Construction and Recognition—0
Unsupervised representation learning with long-term dynamics for skeleton based action recognition—0
Actor and Observer: Joint Modeling of First and Third-Person VideosCode0
ECO: Efficient Convolutional Network for Online Video UnderstandingCode0
Memory Attention Networks for Skeleton-based Action RecognitionCode0
View Adaptive Neural Networks for High Performance Skeleton-based Human Action RecognitionCode0
Co-occurrence Feature Learning from Skeleton Data for Action Recognition and Detection with Hierarchical AggregationCode1
PM-GANs: Discriminative Representation Learning for Action Recognition Using Partial-modalities—0
STAIR Actions: A Video Dataset of Everyday Home ActionsCode0
SoccerNet: A Scalable Dataset for Action Spotting in Soccer VideosCode1
Audio-Visual Scene Analysis with Self-Supervised Multisensory FeaturesCode0
End-to-End Learning of Motion Representation for Video UnderstandingCode0
DIY Human Action Data Set Generation—0
Non-Linear Temporal Subspace Representations for Activity Recognition—0
Video Representation Learning Using Discriminative Pooling—0
Towards Universal Representation for Unseen Action Recognition—0
Learning and Recognizing Human Action from Skeleton Movement with Deep Residual Neural Networks—0
Exploiting deep residual networks for human action recognition from skeletal data—0
T-RECS: Training for Rate-Invariant Embeddings by Controlling Speed for Action Recognition—0
Featureless: Bypassing feature extraction in action categorization—0
Attention-based Temporal Weighted Convolutional Neural Network for Action Recognition—0
Deja Vu: Motion Prediction in Static ImagesCode0
Depth Pooling Based Large-scale 3D Action Recognition with Convolutional Neural Networks—0
Analysis of Hand Segmentation in the WildCode0
Sparse Adversarial Perturbations for VideosCode1
Learning clip representations for skeleton-based 3d action recognition—0
Spatio-Temporal Graph Convolution for Skeleton Based Action Recognition—0
2D/3D Pose Estimation and Action Recognition using Multitask Deep LearningCode0
Real-Time End-to-End Action Detection with Two-Stream Networks—0
Glimpse Clouds: Human Activity Recognition from Unstructured Feature PointsCode0
Learning Representative Temporal Features for Action Recognition—0
Fisherposes for Human Action Recognition Using Kinect Sensor DataCode0
Musical Chair: Efficient Real-Time Recognition Using Collaborative IoT Devices—0
Human Action Adverb Recognition: ADHA Dataset and A Three-Stream Hybrid Model—0
Deep-Temporal LSTM for Daily Living Action Recognition—0
Action Recognition with Spatio-Temporal Visual Attention on Skeleton Image Sequences—0
Histogram of Oriented Depth Gradients for Action Recognition—0
A Generative Approach to Zero-Shot and Few-Shot Action Recognition—0
Let's Dance: Learning From Online Dance VideosCode0
Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action RecognitionCode1
DiscrimNet: Semi-Supervised Action Recognition from Videos using Generative Adversarial Networks—0
Multivariate LSTM-FCNs for Time Series ClassificationCode1
Semi-supervised Fisher vector network—0
Fully-Coupled Two-Stream Spatiotemporal Networks for Extremely Low Resolution Action Recognition—0
Moments in Time Dataset: one million videos for event understandingCode0
Ensemble One-dimensional Convolution Neural Networks for Skeleton-based Action Recognition—0
What have we learned from deep representations for action recognition?—0
Show:102550
← PrevPage 46 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