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 1451–1500 of 2759 papers

TitleStatusHype
Syntactically Guided Generative Embeddings for Zero-Shot Skeleton Action RecognitionCode1
NTU-X: An Enhanced Large-scale Dataset for Improving Pose-based Recognition of Subtle Human ActionsCode1
SkeletonVis: Interactive Visualization for Understanding Adversarial Attacks on Human Action Recognition Models—0
A Two-stream Neural Network for Pose-based Hand Gesture Recognition—0
Bridging the gap between Human Action Recognition and Online Action Detection—0
TCLR: Temporal Contrastive Learning for Video RepresentationCode1
Few-shot Action Recognition with Prototype-centered Attentive LearningCode1
ArtEmis: Affective Language for Visual ArtCode1
Human Action Recognition Based on Multi-scale Feature Maps from Depth Video Sequences—0
CLASTER: Clustering with Reinforcement Learning for Zero-Shot Action Recognition—0
Temporal-Relational CrossTransformers for Few-Shot Action RecognitionCode1
Video action recognition for lane-change classification and prediction of surrounding vehicles—0
Temporally Guided Articulated Hand Pose Tracking in Surgical VideosCode1
Learning from Weakly-labeled Web Videos via Exploring Sub-Concepts—0
Trear: Transformer-based RGB-D Egocentric Action Recognition—0
Temporal Contrastive Graph Learning for Video Action Recognition and Retrieval—0
Transformers in Vision: A Survey—0
Uncertainty-sensitive Activity Recognition: a Reliability Benchmark and the CARING Models—0
Refining activation downsampling with SoftPoolCode1
Vi2CLR: Video and Image for Visual Contrastive Learning of Representation—0
Else-Net: Elastic Semantic Network for Continual Action Recognition From Skeleton Data—0
Efficient Action Recognition via Dynamic Knowledge Propagation—0
Interactive Prototype Learning for Egocentric Action Recognition—0
Self-Supervised 3D Skeleton Action Representation Learning With Motion Consistency and Continuity—0
Contrast and Order Representations for Video Self-Supervised Learning—0
Geometric Deep Neural Network Using Rigid and Non-Rigid Transformations for Human Action Recognition—0
Normalized Human Pose Features for Human Action Video Alignment—0
Exploring Sub-Pseudo Labels for Learning from Weakly-Labeled Web Videos—0
A Unified Framework to Analyze and Design the Nonlocal Blocks for Neural Networks—0
Learning Self-Similarity in Space and Time as a Generalized Motion for Action RecognitionCode1
Learning Visual Representation from Human Interactions—0
Temporal Difference Networks for Action Recognition—0
Beyond the Pixels: Exploring the Effects of Bit-Level Network and File Corruptions on Video Model Robustness—0
The 3TConv: An Intrinsic Approach to Explainable 3D CNNs—0
3D Human motion anticipation and classification—0
2D or not 2D? Adaptive 3D Convolution Selection for Efficient Video Recognition—0
Tensor Representations for Action RecognitionCode1
Action Recognition with Kernel-based Graph Convolutional Networks—0
Skeleton-DML: Deep Metric Learning for Skeleton-Based One-Shot Action RecognitionCode1
Faster and Accurate Compressed Video Action Recognition Straight from the Frequency Domain—0
Human Action Recognition from Various Data Modalities: A Review—0
Anchor-Based Spatio-Temporal Attention 3D Convolutional Networks for Dynamic 3D Point Cloud Sequences—0
Recent Advances of Generic Object Detection with Deep Learning: A Review—0
SMART Frame Selection for Action Recognition—0
TDN: Temporal Difference Networks for Efficient Action RecognitionCode1
Smoothed Gaussian Mixture Models for Video Classification and Recommendation—0
Weakly-Supervised Action Localization and Action Recognition using Global-Local Attention of 3D CNN—0
Temporal Graph Modeling for Skeleton-based Action Recognition—0
NUTA: Non-uniform Temporal Aggregation for Action Recognition—0
Towards Improving Spatiotemporal Action Recognition in VideosCode0
Show:102550
← PrevPage 30 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