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 2501–2550 of 2759 papers

TitleStatusHype
Real-time Human Pose Estimation from Video with Convolutional Neural Networks—0
Pose from Action: Unsupervised Learning of Pose Features based on Motion—0
Multi-region two-stream R-CNN for action detection—0
Lie-X: Depth Image Based Articulated Object Pose Estimation, Tracking, and Action Recognition on Lie Groups—0
Sequential Deep Trajectory Descriptor for Action Recognition with Three-stream CNN—0
A Tube-and-Droplet-based Approach for Representing and Analyzing Motion Trajectories—0
Image and Video Mining through Online Learning—0
Making a Case for Learning Motion Representations with Phase—0
Human Action Recognition without Human—0
Spatio-temporal Aware Non-negative Component Representation for Action Recognition—0
Sympathy for the Details: Dense Trajectories and Hybrid Classification Architectures for Action Recognition—0
We Can "See" You via Wi-Fi - WiFi Action Recognition via Vision-based Methods—0
Depth2Action: Exploring Embedded Depth for Large-Scale Action Recognition—0
Discriminatively Trained Latent Ordinal Model for Video Classification—0
Multiview Cauchy Estimator Feature Embedding for Depth and Inertial Sensor-Based Human Action Recognition—0
Fusing Deep Convolutional Networks for Large Scale Visual Concept Classification—0
Temporal Segment Networks: Towards Good Practices for Deep Action RecognitionCode2
A Survey of Visual Analysis of Human Motion and Its Applications—0
Dynamic Probabilistic Network Based Human Action Recognition—0
Emotion-Based Crowd Representation for Abnormality Detection—0
Spatio-Temporal LSTM with Trust Gates for 3D Human Action Recognition—0
Kinematic-Layout-aware Random Forests for Depth-based Action Recognition—0
Hierarchical Attention Network for Action Recognition in Videos—0
Multi-Camera Action Dataset for Cross-Camera Action Recognition Benchmarking—0
Annotation Methodologies for Vision and Language Dataset Creation—0
Transition Forests: Learning Discriminative Temporal Transitions for Action Recognition and Detection—0
Action Recognition with Joint Attention on Multi-Level Deep Features—0
Zero-Shot Visual Recognition via Bidirectional Latent Embedding—0
VideoLSTM Convolves, Attends and Flows for Action RecognitionCode0
Rolling Rotations for Recognizing Human Actions from 3D Skeletal Data—0
A Hierarchical Pose-Based Approach to Complex Action Understanding Using Dictionaries of Actionlets and Motion Poselets—0
Hand Action Detection from Ego-centric Depth Sequences with Error-correcting Hough Transform—0
Temporal Action Detection Using a Statistical Language ModelCode0
You Lead, We Exceed: Labor-Free Video Concept Learning by Jointly Exploiting Web Videos and Images—0
Cascaded Interactional Targeting Network for Egocentric Video Analysis—0
A Key Volume Mining Deep Framework for Action Recognition—0
Thin-Slicing for Pose: Learning to Understand Pose Without Explicit Pose Estimation—0
Regularizing Long Short Term Memory With 3D Human-Skeleton Sequences for Action Recognition—0
Harnessing Object and Scene Semantics for Large-Scale Video Understanding—0
VLAD3: Encoding Dynamics of Deep Features for Action Recognition—0
Fast Temporal Activity Proposals for Efficient Detection of Human Actions in Untrimmed Videos—0
Force From Motion: Decoding Physical Sensation in a First Person Video—0
Progressively Parsing Interactional Objects for Fine Grained Action Detection—0
First Person Action Recognition Using Deep Learned Descriptors—0
Efficient Temporal Sequence Comparison and Classification Using Gram Matrix Embeddings on a Riemannian Manifold—0
A Multi-Stream Bi-Directional Recurrent Neural Network for Fine-Grained Action Detection—0
Discriminative Hierarchical Rank Pooling for Activity Recognition—0
Mining 3D Key-Pose-Motifs for Action Recognition—0
Pairwise Linear Regression Classification for Image Set Retrieval—0
3D Action Recognition From Novel Viewpoints—0
Show:102550
← PrevPage 51 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