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 1151–1200 of 2759 papers

TitleStatusHype
Tell me what you see: A zero-shot action recognition method based on natural language descriptionsCode1
Cross-Model Pseudo-Labeling for Semi-Supervised Action Recognition—0
Self-attention based anchor proposal for skeleton-based action recognition—0
Distillation of Human-Object Interaction Contexts for Action Recognition—0
Analysis and Evaluation of Kinect-based Action Recognition AlgorithmsCode0
Masked Feature Prediction for Self-Supervised Visual Pre-TrainingCode1
Temporal Shuffling for Defending Deep Action Recognition Models against Adversarial AttacksCode0
Detecting Object States vs Detecting Objects: A New Dataset and a Quantitative Experimental StudyCode0
Temporal Transformer Networks with Self-Supervision for Action Recognition—0
Co-training Transformer with Videos and Images Improves Action Recognition—0
Multi-Expert Human Action Recognition with Hierarchical Super-Class Learning—0
Real Time Action Recognition from Video Footage—0
SVIP: Sequence VerIfication for Procedures in VideosCode1
Self-supervised Spatiotemporal Representation Learning by Exploiting Video Continuity—0
Spatio-temporal Relation Modeling for Few-shot Action RecognitionCode1
Contextualized Spatio-Temporal Contrastive Learning with Self-SupervisionCode0
Topology-aware Convolutional Neural Network for Efficient Skeleton-based Action RecognitionCode1
Prompting Visual-Language Models for Efficient Video UnderstandingCode1
Cross-modal Manifold Cutmix for Self-supervised Video Representation Learning—0
E^2(GO)MOTION: Motion Augmented Event Stream for Egocentric Action RecognitionCode1
Time-Equivariant Contrastive Video Representation Learning—0
TCGL: Temporal Contrastive Graph for Self-supervised Video Representation LearningCode1
Contrastive Learning from Extremely Augmented Skeleton Sequences for Self-supervised Action RecognitionCode1
Learning Connectivity with Graph Convolutional Networks for Skeleton-based Action Recognition—0
STSM: Spatio-Temporal Shift Module for Efficient Action Recognition—0
Deep Efficient Continuous Manifold Learning for Time Series ModelingCode0
Make A Long Image Short: Adaptive Token Length for Vision Transformers—0
Self-supervised Video TransformerCode1
BEVT: BERT Pretraining of Video TransformersCode1
Stacked Temporal Attention: Improving First-person Action Recognition by Emphasizing Discriminative Clips—0
MViTv2: Improved Multiscale Vision Transformers for Classification and DetectionCode1
Graph Convolutional Module for Temporal Action Localization in Videos—0
MAU: A Motion-Aware Unit for Video Prediction and BeyondCode1
Your head is there to move you around: Goal-driven models of the primate dorsal pathway—0
Dynamic Normalization and Relay for Video Action RecognitionCode0
Spatiotemporal Joint Filter Decomposition in 3D Convolutional Neural Networks—0
Reformulating Zero-shot Action Recognition for Multi-label Actions—0
Anonymization for Skeleton Action RecognitionCode1
Learning from Temporal Gradient for Semi-supervised Action RecognitionCode1
Cross Your Body: A Cognitive Assessment System for Children—0
MorphMLP: An Efficient MLP-Like Backbone for Spatial-Temporal Representation LearningCode0
Florence: A New Foundation Model for Computer VisionCode1
Contrast-reconstruction Representation Learning for Self-supervised Skeleton-based Action Recognition—0
Action Recognition with Domain Invariant Features of Skeleton Image—0
Evaluating Transformers for Lightweight Action Recognition—0
M2A: Motion Aware Attention for Accurate Video Action RecognitionCode1
Real-time 3D human action recognition based on Hyperpoint sequenceCode1
UBnormal: New Benchmark for Supervised Open-Set Video Anomaly DetectionCode1
A Central Difference Graph Convolutional Operator for Skeleton-Based Action RecognitionCode0
Multi-Scale Semantics-Guided Neural Networks for Efficient Skeleton-Based Human Action Recognition—0
Show:102550
← PrevPage 24 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