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 2201–2250 of 2759 papers

TitleStatusHype
Motion Feature Network: Fixed Motion Filter for Action Recognition—0
Contrastive Video Representation Learning via Adversarial Perturbations—0
Deep Discriminative Model for Video Classification—0
Correlation Net: Spatiotemporal multimodal deep learning for action recognition—0
Towards Privacy-Preserving Visual Recognition via Adversarial Training: A Pilot StudyCode1
Signal Alignment for Humanoid Skeletons via the Globally Optimal Reparameterization Algorithm—0
Skeletal Movement to Color Map: A Novel Representation for 3D Action Recognition with Inception Residual Networks—0
The Globally Optimal Reparameterization Algorithm: an Alternative to Fast Dynamic Time Warping for Action Recognition in Video Sequences—0
Adding Attentiveness to the Neurons in Recurrent Neural Networks—0
Video-based Person Re-identification via 3D Convolutional Networks and Non-local Attention—0
A Variational Time Series Feature Extractor for Action PredictionCode0
3D Human Action Recognition with Siamese-LSTM Based Deep Metric Learning—0
Cooperative Learning of Audio and Video Models from Self-Supervised Synchronization—0
Action Recognition for Depth Video using Multi-view Dynamic ImagesCode0
A Novel Geometric Framework on Gram Matrix Trajectories for Human Behavior Understanding—0
YH Technologies at ActivityNet Challenge 2018—0
Human Action Recognition and Prediction: A Survey—0
Exploiting Spatial-Temporal Modelling and Multi-Modal Fusion for Human Action Recognition—0
CNN-based Action Recognition and Supervised Domain Adaptation on 3D Body Skeletons via Kernel Feature Maps—0
Classifying Object Manipulation Actions based on Grasp-types and Motion-Constraints—0
Modality Distillation with Multiple Stream Networks for Action RecognitionCode0
Pose Encoding for Robust Skeleton-Based Action Recognition—0
Two Stream Self-Supervised Learning for Action Recognition—0
Massively Parallel Video Networks—0
Action4D: Real-time Action Recognition in the Crowd and Clutter—0
Videos as Space-Time Region Graphs—0
Squeeze-and-Excitation on Spatial and Temporal Deep Feature Space for Action Recognition—0
Temporal Hallucinating for Action Recognition With Few Still Images—0
Pulling Actions out of Context: Explicit Separation for Effective Combination—0
Learning and Using the Arrow of Time—0
SSNet: Scale Selection Network for Online 3D Action Prediction—0
PoTion: Pose MoTion Representation for Action Recognition—0
Recognize Actions by Disentangling Components of Dynamics—0
Coding Kendall's Shape Trajectories for 3D Action Recognition—0
PoseFlow: A Deep Motion Representation for Understanding Human Behaviors in Videos—0
Recognizing Human Actions as the Evolution of Pose Estimation Maps—0
Geometry Guided Convolutional Neural Networks for Self-Supervised Video Representation Learning—0
Deep Progressive Reinforcement Learning for Skeleton-Based Action Recognition—0
Making Convolutional Networks Recurrent for Visual Sequence Learning—0
MiCT: Mixed 3D/2D Convolutional Tube for Human Action Recognition—0
RNN for Affects at SemEval-2018 Task 1: Formulating Affect Identification as a Binary Classification Problem—0
A Fine-to-Coarse Convolutional Neural Network for 3D Human Action Recognition—0
Pose-Based Two-Stream Relational Networks for Action Recognition in Videos—0
DEEPEYE: A Compact and Accurate Video Comprehension at Terminal Devices Compressed with Quantization and Tensorization—0
Two-Stream Adaptive Graph Convolutional Networks for Skeleton-Based Action RecognitionCode0
Fast Retinomorphic Event Stream for Video Recognition and Reinforcement Learning—0
Graph Edge Convolutional Neural Networks for Skeleton Based Action Recognition—0
Towards an Unequivocal Representation of Actions—0
Visual Attribute-augmented Three-dimensional Convolutional Neural Network for Enhanced Human Action Recognition—0
Low-Latency Human Action Recognition with Weighted Multi-Region Convolutional Neural Network—0
Show:102550
← PrevPage 45 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