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 2151–2200 of 2759 papers

TitleStatusHype
D3D: Distilled 3D Networks for Video Action RecognitionCode0
Action Machine: Rethinking Action Recognition in Trimmed Videos—0
TAN: Temporal Aggregation Network for Dense Multi-label Action Recognition—0
Improving the Performance of Unimodal Dynamic Hand-Gesture Recognition with Multimodal TrainingCode0
Nrityantar: Pose oblivious Indian classical dance sequence classification system—0
Dynamic Graph Modules for Modeling Object-Object Interactions in Activity Recognition—0
Long-Term Feature Banks for Detailed Video UnderstandingCode0
Learning Discriminative Motion Features Through Detection—0
Loss Guided Activation for Action Recognition in Still Images—0
Unsupervised Feature Learning of Human Actions as Trajectories in Pose Embedding ManifoldCode0
Video Action Transformer Network—0
Multimodal Explanations by Predicting Counterfactuality in Videos—0
MS-ASL: A Large-Scale Data Set and Benchmark for Understanding American Sign Language—0
SUSiNet: See, Understand and Summarize it—0
A^2-Nets: Double Attention NetworksCode0
Trajectory Convolution for Action Recognition—0
Structure-Aware Convolutional Neural NetworksCode0
Graph-Based Global Reasoning NetworksCode0
Iterative Projection and Matching: Finding Structure-preserving Representatives and Its Application to Computer VisionCode0
Optimized Skeleton-based Action Recognition via Sparsified Graph Regression—0
Self-Supervised Spatiotemporal Feature Learning via Video Rotation Prediction—0
Unrepresentative video data: A review and evaluation—0
Adversarial Attacks for Optical Flow-Based Action Recognition Classifiers—0
Multi-granularity Generator for Temporal Action Proposal—0
Stacked Spatio-Temporal Graph Convolutional Networks for Action Segmentation—0
LSTA: Long Short-Term Attention for Egocentric Action RecognitionCode0
Evolving Space-Time Neural Architectures for Videos—0
Privacy-Preserving Action Recognition for Smart Hospitals using Low-Resolution Depth Images—0
Temporal Bilinear Networks for Video Action Recognition—0
Learning Conditional Random Fields with Augmented Observations for Partially Observed Action Recognition—0
Self-Supervised Video Representation Learning with Space-Time Cubic Puzzles—0
RGB-D Based Action Recognition with Light-weight 3D Convolutional Networks—0
Multi-Task Learning of Generalizable Representations for Video Action Recognition—0
Higher-order Network for Action Recognition—0
Relational Long Short-Term Memory for Video Action Recognition—0
A Perceptual Prediction Framework for Self Supervised Event SegmentationCode0
Skeleton-Based Action Recognition with Synchronous Local and Non-local Spatio-temporal Learning and Frequency Attention—0
Cross and Learn: Cross-Modal Self-SupervisionCode0
Leveraging Random Label Memorization for Unsupervised Pre-Training—0
StNet: Local and Global Spatial-Temporal Modeling for Action RecognitionCode0
Hierarchical Long Short-Term Concurrent Memory for Human Interaction Recognition—0
Informed Democracy: Voting-based Novelty Detection for Action Recognition—0
DeepGRU: Deep Gesture Recognition UtilityCode0
Random Temporal Skipping for Multirate Video Analysis—0
ActionXPose: A Novel 2D Multi-view Pose-based Algorithm for Real-time Human Action Recognition—0
A^2-Nets: Double Attention Networks—0
Real-time Action Recognition with Dissimilarity-based Training of Specialized Module Networks—0
Fine-grained Video Categorization with Redundancy Reduction Attention—0
Learning with privileged information via adversarial discriminative modality distillationCode0
Cross-Modal and Hierarchical Modeling of Video and TextCode0
Show:102550
← PrevPage 44 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
4InternVideoTop-1 Accuracy77.2—Unverified
5DejaVidTop-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
3OmniVec3-fold Accuracy99.6—Unverified
4VideoMAE V2-g3-fold Accuracy99.6—Unverified
5BIKE3-fold Accuracy98.8—Unverified
6SMART3-fold Accuracy98.64—Unverified
7ZeroI2V ViT-L/143-fold Accuracy98.6—Unverified
8OmniSource (SlowOnly-8x8-R101-RGB + I3D-Flow)3-fold Accuracy98.6—Unverified
9PERF-Net (multi-distilled S3D)3-fold Accuracy98.6—Unverified
10Text4Vis3-fold Accuracy98.2—Unverified