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 2301–2350 of 2759 papers

TitleStatusHype
Distributed non-parametric deep and wide networks—0
A Unified Method for First and Third Person Action Recognition—0
HACS: Human Action Clips and Segments Dataset for Recognition and Temporal LocalizationCode0
On the Integration of Optical Flow and Action Recognition—0
Human Action Recognition: Pose-based Attention draws focus to Hands—0
Learning Compact Recurrent Neural Networks with Block-Term Tensor Decomposition—0
Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video ClassificationCode0
Deception Detection in Videos—0
Im2Flow: Motion Hallucination from Static Images for Action RecognitionCode0
Cooperative Training of Deep Aggregation Networks for RGB-D Action Recognition—0
Robust 3D Action Recognition through Sampling Local Appearances and Global Distributions—0
Multimodal Visual Concept Learning with Weakly Supervised TechniquesCode0
Compressed Video Action RecognitionCode0
Label Efficient Learning of Transferable Representations acrosss Domains and Tasks—0
Label Efficient Learning of Transferable Representations across Domains and Tasks—0
A Closer Look at Spatiotemporal Convolutions for Action RecognitionCode1
Optical Flow Guided Feature: A Fast and Robust Motion Representation for Video Action RecognitionCode0
Action Recognition in Video Sequences using Deep Bi-Directional LSTM With CNN FeaturesCode0
Revisiting hand-crafted feature for action recognition: a set of improved dense trajectoriesCode0
Learning Spatio-Temporal Representation with Pseudo-3D Residual NetworksCode1
Scalable and Compact 3D Action Recognition with Approximated RBF Kernel Machines—0
Highly Efficient Human Action Recognition with Quantum Genetic Algorithm Optimized Support Vector Machine—0
Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?Code2
Predictive Learning: Using Future Representation Learning Variantial Autoencoder for Human Action Prediction—0
Appearance-and-Relation Networks for Video ClassificationCode0
Temporal 3D ConvNets: New Architecture and Transfer Learning for Video ClassificationCode1
Temporal Relational Reasoning in VideosCode0
Train, Diagnose and Fix: Interpretable Approach for Fine-grained Action Recognition—0
Multi-Level Recurrent Residual Networks for Action Recognition—0
Non-local Neural NetworksCode1
Action Recognition with Coarse-to-Fine Deep Feature Integration and Asynchronous Fusion—0
Excitation Backprop for RNNsCode0
Action-Attending Graphic Neural Network—0
Attend and Interact: Higher-Order Object Interactions for Video Understanding—0
Skepxels: Spatio-temporal Image Representation of Human Skeleton Joints for Action Recognition—0
End-to-end Video-level Representation Learning for Action RecognitionCode0
Egocentric Hand Detection Via Dynamic Region Growing—0
Attentional Pooling for Action RecognitionCode0
Grad-CAM++: Improved Visual Explanations for Deep Convolutional NetworksCode1
3D CNNs on Distance Matrices for Human Action RecognitionCode0
Adaptive RNN Tree for Large-Scale Human Action Recognition—0
RPAN: An End-to-End Recurrent Pose-Attention Network for Action Recognition in VideosCode0
A Generative Restricted Boltzmann Machine Based Method for High-Dimensional Motion Data Modeling—0
Generalized Zero-Shot Learning for Action Recognition with Web-Scale Video Data—0
Learning to Recognize Actions from Limited Training Examples Using a Recurrent Spiking Neural Model—0
Real-Time Action Detection in Video Surveillance using Sub-Action Descriptor with Multi-CNNCode0
CAMREP- Concordia Action and Motion Repository—0
Ensemble Deep Learning for Skeleton-Based Action Recognition Using Temporal Sliding LSTM NetworksCode0
Learning Action Recognition Model From Depth and Skeleton Videos—0
Flip-Invariant Motion Representation—0
Show:102550
← PrevPage 47 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