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 2651–2700 of 2759 papers

TitleStatusHype
Dynamically Encoded Actions Based on Spacetime Saliency—0
Elastic Functional Coding of Human Actions: From Vector-Fields to Latent Variables—0
Motion Part Regularization: Improving Action Recognition via Trajectory Selection—0
A Novel Locally Linear KNN Model for Visual Recognition—0
Delving Into Egocentric Actions—0
Joint Action Recognition and Pose Estimation From Video—0
What do 15,000 Object Categories Tell Us About Classifying and Localizing Actions?—0
Action Recognition with Trajectory-Pooled Deep-Convolutional DescriptorsCode0
Visual Semantic Role LabelingCode1
The Best of Both Worlds: Combining Data-independent and Data-driven Approaches for Action Recognition—0
Contextual Action Recognition with R*CNNCode0
Modeling Representation of Videos for Anomaly Detection using Deep Learning: A Review—0
Fusing multiple features for depth-based action recognition—0
Differential Recurrent Neural Networks for Action Recognition—0
A robust and efficient video representation for action recognition—0
Learning discriminative trajectorylet detector sets for accurate skeleton-based action recognition—0
Temporal Localization of Fine-Grained Actions in Videos by Domain Transfer from Web ImagesCode0
Beyond Short Snippets: Deep Networks for Video ClassificationCode0
Discriminative Bayesian Dictionary Learning for Classification—0
Video-Based Action Recognition Using Rate-Invariant Analysis of Covariance Trajectories—0
Temporal Pyramid Pooling Based Convolutional Neural Networks for Action Recognition—0
Describing Videos by Exploiting Temporal StructureCode0
Unsupervised Learning of Video Representations using LSTMsCode1
Multi-Action Recognition via Stochastic Modelling of Optical Flow and Gradients—0
Semantic Embedding Space for Zero-Shot Action Recognition—0
Multimodal Task-Driven Dictionary Learning for Image ClassificationCode0
Linear-time Online Action Detection From 3D Skeletal Data Using Bags of Gesturelets—0
Learning Latent Spatio-Temporal Compositional Model for Human Action Recognition—0
Feature Sampling Strategies for Action Recognition—0
Advances in Human Action Recognition: A Survey—0
Deep Convolutional Neural Networks for Action Recognition Using Depth Map Sequences—0
Reconstruction-free action inference from compressive imagers—0
Gradient Boundary Histograms for Action Recognition—0
Learning Spatiotemporal Features with 3D Convolutional NetworksCode2
Submodular Attribute Selection for Action Recognition in Video—0
Beyond Gaussian Pyramid: Multi-skip Feature Stacking for Action Recognition—0
CIDEr: Consensus-based Image Description EvaluationCode1
A Nonparametric Bayesian Approach Toward Stacked Convolutional Independent Component Analysis—0
A Latent Clothing Attribute Approach for Human Pose Estimation—0
Histogram of Oriented Principal Components for Cross-View Action Recognition—0
Mining Mid-level Features for Action Recognition Based on Effective Skeleton Representation—0
10,000+ Times Accelerated Robust Subset Selection (ARSS)—0
Action Recognition in the Frequency Domain—0
Sparse Coding on Symmetric Positive Definite Manifolds using Bregman Divergences—0
Temporal Extension of Scale Pyramid and Spatial Pyramid Matching for Action Recognition—0
Skeletal quads: Human action recognition using joint quadruples—0
Down-Sampling coupled to Elastic Kernel Machines for Efficient Recognition of Isolated Gestures—0
Robust Statistical Approach for Extraction of Moving Human Silhouettes from Videos—0
HOPC: Histogram of Oriented Principal Components of 3D Pointclouds for Action Recognition—0
A discussion on the validation tests employed to compare human action recognition methods using the MSR Action3D dataset—0
Show:102550
← PrevPage 54 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