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 2451–2500 of 2759 papers

TitleStatusHype
Improving Interpretability of Deep Neural Networks with Semantic Information—0
UntrimmedNets for Weakly Supervised Action Recognition and DetectionCode0
A New Representation of Skeleton Sequences for 3D Action Recognition—0
On Geometric Features for Skeleton-Based Action Recognition using Multilayer LSTM NetworksCode0
Scene Flow to Action Map: A New Representation for RGB-D based Action Recognition with Convolutional Neural Networks—0
Evolution-Preserving Dense Trajectory Descriptors—0
Joint Discovery of Object States and Manipulation ActionsCode0
Robust features for facial action recognition—0
Deep Local Video Feature for Action Recognition—0
Higher-order Pooling of CNN Features via Kernel Linearization for Action Recognition—0
Action Recognition: From Static Datasets to Moving Robots—0
Learning Linear Dynamical Systems with High-Order Tensor Data for Skeleton based Action Recognition—0
Ordered Pooling of Optical Flow Sequences for Action Recognition—0
AENet: Learning Deep Audio Features for Video AnalysisCode0
Action Recognition Based on Joint Trajectory Maps with Convolutional Neural Networks—0
Human Action Attribute Learning From Video Data Using Low-Rank Representations—0
Efficient Action Detection in Untrimmed Videos via Multi-Task Learning—0
Deep Motion Features for Visual Tracking—0
Dynamic Action Recognition: A convolutional neural network model for temporally organized joint location data—0
Asynchronous Temporal Fields for Action RecognitionCode0
Deep Learning on Lie Groups for Skeleton-based Action Recognition—0
Single Image Action Recognition using Semantic Body Part Actions—0
Scale Coding Bag of Deep Features for Human Attribute and Action Recognition—0
ActionFlowNet: Learning Motion Representation for Action Recognition—0
Procedural Generation of Videos to Train Deep Action Recognition Networks—0
Action Recognition with Dynamic Image NetworksCode0
Learning from Small Sample Sets by Combining Unsupervised Meta-Training with CNNs—0
Deep Alternative Neural Network: Exploring Contexts as Early as Possible for Action Recognition—0
Deep Quantization: Encoding Convolutional Activations with Deep Generative Model—0
Social Scene Understanding: End-to-End Multi-Person Action Localization and Collective Activity Recognition—0
Action Recognition Based on Optimal Joint Selection and Discriminative Depth DescriptorCode0
Multi-Task Zero-Shot Action Recognition with Prioritised Data Augmentation—0
AdaScan: Adaptive Scan Pooling in Deep Convolutional Neural Networks for Human Action Recognition in Videos—0
Adaptive Down-Sampling and Dimension Reduction in Time Elastic Kernel Machines for Efficient Recognition of Isolated Gestures—0
Learning Multi-level Features For Sensor-based Human Action Recognition—0
Self-Supervised Video Representation Learning With Odd-One-Out Networks—0
An End-to-End Spatio-Temporal Attention Model for Human Action Recognition from Skeleton Data—0
Deep Action- and Context-Aware Sequence Learning for Activity Recognition and Anticipation—0
Joint Network based Attention for Action Recognition—0
Learning long-term dependencies for action recognition with a biologically-inspired deep networkCode0
Learning To Score Olympic EventsCode0
Action Recognition Based on Joint Trajectory Maps Using Convolutional Neural Networks—0
Action2Activity: Recognizing Complex Activities from Sensor Data—0
Spatiotemporal Residual Networks for Video Action RecognitionCode1
Sliding Dictionary Based Sparse Representation For Action Recognition—0
Exploiting Structure Sparsity for Covariance-based Visual Representation—0
Review of Action Recognition and Detection MethodsCode0
ARTiS: Appearance-based Action Recognition in Task Space for Real-Time Human-Robot Collaboration—0
Semi-Coupled Two-Stream Fusion ConvNets for Action Recognition at Extremely Low Resolutions—0
YouTube-8M: A Large-Scale Video Classification BenchmarkCode1
Show:102550
← PrevPage 50 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