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 2601–2650 of 2759 papers

TitleStatusHype
RNN Fisher Vectors for Action Recognition and Image Annotation—0
Explaining NonLinear Classification Decisions with Deep Taylor DecompositionCode0
Moving poselets: A discriminative and interpretable skeletal motion representation for action recognition—0
Rank Pooling for Action RecognitionCode0
Actions ~ TransformationsCode0
Action Detection by Implicit Intentional Motion Clustering—0
Bayesian Non-Parametric Inference for Manifold Based MoCap Representation—0
Actionness-Assisted Recognition of Actions—0
Beyond Covariance: Feature Representation With Nonlinear Kernel Matrices—0
Learning Ensembles of Potential Functions for Structured Prediction With Latent Variables—0
Per-Sample Kernel Adaptation for Visual Recognition and Grouping—0
Recursive Frechet Mean Computation on the Grassmannian and its Applications to Computer Vision—0
Category-Blind Human Action Recognition: A Practical Recognition System—0
Unsupervised Domain Adaptation for Zero-Shot Learning—0
Fine-Grain Annotation of Cricket Videos—0
Delving Deeper into Convolutional Networks for Learning Video RepresentationsCode0
Collecting and Annotating the Large Continuous Action Dataset—0
From Pose to Activity: Surveying Datasets and Introducing CONVERSE—0
Hierarchical Spatial Sum-Product Networks for Action Recognition in Still Images—0
Learning Mid-level Words on Riemannian Manifold for Action Recognition—0
Handcrafted Local Features are Convolutional Neural Networks—0
Transductive Zero-Shot Action Recognition by Word-Vector Embedding—0
Improving performance of recurrent neural network with relu nonlinearity—0
Hand-Object Interaction and Precise Localization in Transitive Action Recognition—0
Action Recognition using Visual AttentionCode0
Online Action Recognition based on Incremental Learning of Weighted Covariance Descriptors—0
Pooling the Convolutional Layers in Deep ConvNets for Action Recognition—0
Action recognition from depth maps using deep convolutional neural networks—0
Beyond Spatial Pyramid Matching: Space-time Extended Descriptor for Action Recognition—0
A Novel Approach for Human Action Recognition from Silhouette Images—0
Human Action Recognition using Factorized Spatio-Temporal Convolutional Networks—0
Long-Range Trajectories from Global and Local Motion Representations—0
Hyper-Fisher Vectors for Action Recognition—0
Bio-Inspired Human Action Recognition using Hybrid Max-Product Neuro-Fuzzy Classifier and Quantum-Behaved PSO—0
Manipulated Object Proposal: A Discriminative Object Extraction and Feature Fusion Framework for First-Person Daily Activity Recognition—0
Action Recognition by Hierarchical Mid-level Action Elements—0
Cooking in the kitchen: Recognizing and Segmenting Human Activities in Videos—0
Action Recognition based on Subdivision-Fusion Model—0
Multimodal Multipart Learning for Action Recognition in Depth Videos—0
Action recognition in still images by latent superpixel classification—0
Every Moment Counts: Dense Detailed Labeling of Actions in Complex VideosCode0
Time Series Classification using the Hidden-Unit Logistic Model—0
Slow and steady feature analysis: higher order temporal coherence in video—0
P-CNN: Pose-based CNN Features for Action Recognition—0
Hierarchical recurrent neural network for skeleton based action recognition—0
First-Take-All: Temporal Order-Preserving Hashing for 3D Action Videos—0
Dynamically Encoded Actions Based on Spacetime Saliency—0
DevNet: A Deep Event Network for Multimedia Event Detection and Evidence Recounting—0
Motion Part Regularization: Improving Action Recognition via Trajectory Selection—0
Elastic Functional Coding of Human Actions: From Vector-Fields to Latent Variables—0
Show:102550
← PrevPage 53 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