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 1351–1400 of 2759 papers

TitleStatusHype
Handcrafted localized phase features for human action recognition—0
ANUBIS: Skeleton Action Recognition Dataset, Review, and Benchmark—0
Cross-modal Representation Learning for Zero-shot Action Recognition—0
Preserve Pre-trained Knowledge: Transfer Learning With Self-Distillation For Action Recognition—0
On Negative Sampling for Audio-Visual Contrastive Learning from Movies—0
Self-supervised Contrastive Learning for Audio-Visual Action Recognition—0
HuMMan: Multi-Modal 4D Human Dataset for Versatile Sensing and Modeling—0
Human-Centered Prior-Guided and Task-Dependent Multi-Task Representation Learning for Action Recognition Pre-Training—0
Temporal Relevance Analysis for Video Action Models—0
iCAR: Bridging Image Classification and Image-text Alignment for Visual RecognitionCode0
Unsupervised Human Action Recognition with Skeletal Graph Laplacian and Self-Supervised Viewpoints InvarianceCode0
A Survey of Video-based Action Quality Assessment—0
FenceNet: Fine-grained Footwork Recognition in Fencing—0
THORN: Temporal Human-Object Relation Network for Action Recognition—0
STAU: A SpatioTemporal-Aware Unit for Video Prediction and Beyond—0
ActAR: Actor-Driven Pose Embeddings for Video Action Recognition—0
Performance Evaluation of Action Recognition Models on Low Quality Videos—0
Model-agnostic Multi-Domain Learning with Domain-Specific Adapters for Action Recognition—0
Invisible-to-Visible: Privacy-Aware Human Instance Segmentation using Airborne Ultrasound via Collaborative Learning Variational Autoencoder—0
3D Convolutional Networks for Action Recognition: Application to Sport Gesture Recognition—0
Towards End-to-End Integration of Dialog History for Improved Spoken Language Understanding—0
Is my Driver Observation Model Overconfident? Input-guided Calibration Networks for Reliable and Interpretable Confidence Estimates—0
SOS! Self-supervised Learning Over Sets Of Handled Objects In Egocentric Action Recognition—0
Probabilistic Representations for Video Contrastive Learning—0
Frequency Selective Augmentation for Video Representation Learning—0
MM-SEAL: A Large-scale Video Dataset of Multi-person Multi-grained Spatio-temporally Action Localization—0
Hierarchical Self-supervised Representation Learning for Movie Understanding—0
OccamNets: Mitigating Dataset Bias by Favoring Simpler HypothesesCode0
Direct Dense Pose Estimation—0
Vision Transformer with Cross-attention by Temporal Shift for Efficient Action Recognition—0
ObjectMix: Data Augmentation by Copy-Pasting Objects in Videos for Action Recognition—0
SpatioTemporal Focus for Skeleton-based Action Recognition—0
CycDA: Unsupervised Cycle Domain Adaptation from Image to VideoCode0
Controllable Augmentations for Video Representation Learning—0
Assembly101: A Large-Scale Multi-View Video Dataset for Understanding Procedural ActivitiesCode0
Rethinking Zero-shot Action Recognition: Learning from Latent Atomic ActionsCode0
Class-Incremental Learning for Action Recognition in Videos—0
Movie Genre Classification by Language Augmentation and Shot SamplingCode0
FitCLIP: Refining Large-Scale Pretrained Image-Text Models for Zero-Shot Video Understanding TasksCode0
LocATe: End-to-end Localization of Actions in 3D with Transformers—0
FAR: Fourier Aerial Video RecognitionCode0
Point3D: tracking actions as moving points with 3D CNNs—0
Know your sensORs -- A Modality Study For Surgical Action Classification—0
Gate-Shift-Fuse for Video Action RecognitionCode0
Context-LSTM: a robust classifier for video detection on UCF101—0
TFCNet: Temporal Fully Connected Networks for Static Unbiased Temporal Reasoning—0
End-to-End Semantic Video Transformer for Zero-Shot Action RecognitionCode0
Data-Folding and Hyperspace Coding for Multi-Dimensonal Time-Series Data Imaging—0
Part-level Action Parsing via a Pose-guided Coarse-to-Fine Framework—0
Universal Prototype Transport for Zero-Shot Action Recognition and Localization—0
Show:102550
← PrevPage 28 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