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

Showing 26762700 of 2759 papers

TitleStatusHype
Multimodal Task-Driven Dictionary Learning for Image ClassificationCode0
Linear-time Online Action Detection From 3D Skeletal Data Using Bags of Gesturelets0
Learning Latent Spatio-Temporal Compositional Model for Human Action Recognition0
Feature Sampling Strategies for Action Recognition0
Advances in Human Action Recognition: A Survey0
Deep Convolutional Neural Networks for Action Recognition Using Depth Map Sequences0
Reconstruction-free action inference from compressive imagers0
Gradient Boundary Histograms for Action Recognition0
Learning Spatiotemporal Features with 3D Convolutional NetworksCode2
Submodular Attribute Selection for Action Recognition in Video0
Beyond Gaussian Pyramid: Multi-skip Feature Stacking for Action Recognition0
CIDEr: Consensus-based Image Description EvaluationCode1
A Nonparametric Bayesian Approach Toward Stacked Convolutional Independent Component Analysis0
A Latent Clothing Attribute Approach for Human Pose Estimation0
Histogram of Oriented Principal Components for Cross-View Action Recognition0
Mining Mid-level Features for Action Recognition Based on Effective Skeleton Representation0
10,000+ Times Accelerated Robust Subset Selection (ARSS)0
Action Recognition in the Frequency Domain0
Sparse Coding on Symmetric Positive Definite Manifolds using Bregman Divergences0
Temporal Extension of Scale Pyramid and Spatial Pyramid Matching for Action Recognition0
Skeletal quads: Human action recognition using joint quadruples0
Down-Sampling coupled to Elastic Kernel Machines for Efficient Recognition of Isolated Gestures0
Robust Statistical Approach for Extraction of Moving Human Silhouettes from Videos0
HOPC: Histogram of Oriented Principal Components of 3D Pointclouds for Action Recognition0
A discussion on the validation tests employed to compare human action recognition methods using the MSR Action3D dataset0
Show:102550
← PrevPage 108 of 111Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1MViTv2-B (IN-21K + Kinetics400 pretrain)Top-5 Accuracy93.4Unverified
2RSANet-R50 (8+16 frames, ImageNet pretrained, 2 clips)Top-5 Accuracy91.1Unverified
3MVD (Kinetics400 pretrain, ViT-H, 16 frame)Top-1 Accuracy77.3Unverified
4DejaVidTop-1 Accuracy77.2Unverified
5InternVideoTop-1 Accuracy77.2Unverified
6InternVideo2-1BTop-1 Accuracy77.1Unverified
7VideoMAE V2-gTop-1 Accuracy77Unverified
8MVD (Kinetics400 pretrain, ViT-L, 16 frame)Top-1 Accuracy76.7Unverified
9Hiera-L (no extra data)Top-1 Accuracy76.5Unverified
10TubeViT-LTop-1 Accuracy76.1Unverified
#ModelMetricClaimedVerifiedStatus
1FTP-UniFormerV2-L/143-fold Accuracy99.7Unverified
2OmniVec23-fold Accuracy99.6Unverified
3VideoMAE V2-g3-fold Accuracy99.6Unverified
4OmniVec3-fold Accuracy99.6Unverified
5BIKE3-fold Accuracy98.8Unverified
6SMART3-fold Accuracy98.64Unverified
7OmniSource (SlowOnly-8x8-R101-RGB + I3D-Flow)3-fold Accuracy98.6Unverified
8PERF-Net (multi-distilled S3D)3-fold Accuracy98.6Unverified
9ZeroI2V ViT-L/143-fold Accuracy98.6Unverified
10LGD-3D Two-stream3-fold Accuracy98.2Unverified