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 751–800 of 2759 papers

TitleStatusHype
Activation-wise Propagation: A Universal Strategy to Break Timestep Constraints in Spiking Neural Networks for 3D Data Processing—0
A Hierarchical Context Model for Event Recognition in Surveillance Video—0
Action Recognition Based on Joint Trajectory Maps Using Convolutional Neural Networks—0
3D Convolutional Networks for Action Recognition: Application to Sport Gesture Recognition—0
Feature sampling and partitioning for visual vocabulary generation on large action classification datasets—0
A Grid-based Representation for Human Action Recognition—0
FBK-HUPBA Submission to the EPIC-Kitchens 2019 Action Recognition Challenge—0
FBK-HUPBA Submission to the EPIC-Kitchens Action Recognition 2020 Challenge—0
Beyond the Camera: Neural Networks in World Coordinates—0
A Generative Restricted Boltzmann Machine Based Method for High-Dimensional Motion Data Modeling—0
Action Recognition Based on Joint Trajectory Maps with Convolutional Neural Networks—0
Fast Temporal Activity Proposals for Efficient Detection of Human Actions in Untrimmed Videos—0
Beyond Spatial Pyramid Matching: Space-time Extended Descriptor for Action Recognition—0
A Baseline Framework for Part-level Action Parsing and Action Recognition—0
Fast, invariant representation for human action in the visual system—0
Beyond Short Clips: End-to-End Video-Level Learning with Collaborative Memories—0
Beyond Image Classification: A Video Benchmark and Dual-Branch Hybrid Discrimination Framework for Compositional Zero-Shot Learning—0
A baseline on continual learning methods for video action recognition—0
Fast Retinomorphic Event Stream for Video Recognition and Reinforcement Learning—0
Feature and Region Selection for Visual Learning—0
Beyond Gaussian Pyramid: Multi-skip Feature Stacking for Action Recognition—0
Beyond Covariance: Feature Representation With Nonlinear Kernel Matrices—0
A Fine-to-Coarse Convolutional Neural Network for 3D Human Action Recognition—0
FACTS: Fine-Grained Action Classification for Tactical Sports—0
Efficient Feature Extraction, Encoding and Classification for Action Recognition—0
AFE-CNN: 3D Skeleton-based Action Recognition with Action Feature Enhancement—0
Efficient Attention-free Video Shift Transformers—0
Efficient Action Recognition via Dynamic Knowledge Propagation—0
Better Exploiting Motion for Better Action Recognition—0
Efficient Modelling Across Time of Human Actions and Interactions—0
Action Recognition based Industrial Safety Violation Detection—0
Efficient Nonlinear Markov Models for Human Motion—0
Faster and Accurate Compressed Video Action Recognition Straight from the Frequency Domain—0
Efficient Selective Audio Masked Multimodal Bottleneck Transformer for Audio-Video Classification—0
Efficient Spatialtemporal Context Modeling for Action Recognition—0
Efficient Temporal Sequence Comparison and Classification Using Gram Matrix Embeddings on a Riemannian Manifold—0
A Generative Approach to Zero-Shot and Few-Shot Action Recognition—0
Efficient Action Recognition Using Confidence Distillation—0
EgoAdapt: Adaptive Multisensory Distillation and Policy Learning for Efficient Egocentric Perception—0
Efficient Action Localization with Approximately Normalized Fisher Vectors—0
Efficient Action Detection in Untrimmed Videos via Multi-Task Learning—0
Egocentric Action Recognition by Video Attention and Temporal Context—0
Egocentric Activity Recognition and Localization on a 3D Map—0
Egocentric Hand Detection Via Dynamic Region Growing—0
Egocentric Hand Track and Object-based Human Action Recognition—0
Beyond the Pixels: Exploring the Effects of Bit-Level Network and File Corruptions on Video Model Robustness—0
Benchmarking Sensitivity of Continual Graph Learning for Skeleton-Based Action Recognition—0
Egocentric View Hand Action Recognition by Leveraging Hand Surface and Hand Grasp Type—0
Egocentric zone-aware action recognition across environments—0
AE-Net:Adjoint Enhancement Network for Efficient Action Recognition in Video Understanding—0
Show:102550
← PrevPage 16 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