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 2651–2700 of 2759 papers

TitleStatusHype
Leveraging Foundation Model Automatic Data Augmentation Strategies and Skeletal Points for Hands Action Recognition in Industrial Assembly Lines—0
Leveraging Foundation Models for Multimodal Graph-Based Action Recognition—0
Leveraging Hierarchical Parametric Networks for Skeletal Joints Based Action Segmentation and Recognition—0
Towards Achieving Perfect Multimodal Alignment—0
Leveraging Random Label Memorization for Unsupervised Pre-Training—0
Leveraging Self-Supervised Training for Unintentional Action Recognition—0
Leveraging Temporal Context in Low Representational Power Regimes—0
Developing the Path Signature Methodology and its Application to Landmark-based Human Action Recognition—0
Leveraging YOLO-World and GPT-4V LMMs for Zero-Shot Person Detection and Action Recognition in Drone Imagery—0
Lie-X: Depth Image Based Articulated Object Pose Estimation, Tracking, and Action Recognition on Lie Groups—0
LIGAR: Lightweight General-purpose Action Recognition—0
Lighter Stacked Hourglass Human Pose Estimation—0
Lightweight Delivery Detection on Doorbell Cameras—0
Linear-time Online Action Detection From 3D Skeletal Data Using Bags of Gesturelets—0
Literature Review of Action Recognition in the Wild—0
Livestock Monitoring with Transformer—0
LLMs are Good Action Recognizers—0
Locality preserving projection on SPD matrix Lie group: algorithm and analysis—0
Localized Trajectories for 2D and 3D Action Recognition—0
LocATe: End-to-end Localization of Actions in 3D with Transformers—0
Log-Euclidean Bag of Words for Human Action Recognition—0
LoKi: Low-dimensional KAN for Efficient Fine-tuning Image Models—0
Long-Range Trajectories from Global and Local Motion Representations—0
Long-Short Temporal Contrastive Learning of Video Transformers—0
Long-Short Temporal Modeling for Efficient Action Recognition—0
Long Short View Feature Decomposition via Contrastive Video Representation Learning—0
Looking Ahead: Anticipating Pedestrians Crossing with Future Frames Prediction—0
Look, Listen, and Attack: Backdoor Attacks Against Video Action Recognition—0
Look, Listen, and Attend: Co-Attention Network for Self-Supervised Audio-Visual Representation Learning—0
LORTSAR: Low-Rank Transformer for Skeleton-based Action Recognition—0
Loss Guided Activation for Action Recognition in Still Images—0
LoTE-Animal: A Long Time-span Dataset for Endangered Animal Behavior Understanding—0
Love in Action: Gamifying Public Video Cameras for Fostering Social Relationships in Real World—0
Lower Limb Movements Recognition Based on Feature Recursive Elimination and Backpropagation Neural Network—0
Low-Latency Human Action Recognition with Weighted Multi-Region Convolutional Neural Network—0
Low-Resolution Action Recognition for Tiny Actions Challenge—0
LP-3DCNN: Unveiling Local Phase in 3D Convolutional Neural Networks—0
LSC-ADL: An Activity of Daily Living (ADL)-Annotated Lifelog Dataset Generated via Semi-Automatic Clustering—0
M2-CLIP: A Multimodal, Multi-task Adapting Framework for Video Action Recognition—0
M^33D: Learning 3D priors using Multi-Modal Masked Autoencoders for 2D image and video understanding—0
M^3Net: Multi-view Encoding, Matching, and Fusion for Few-shot Fine-grained Action Recognition—0
MAiVAR: Multimodal Audio-Image and Video Action Recognizer—0
MAiVAR-T: Multimodal Audio-image and Video Action Recognizer using Transformers—0
Make A Long Image Short: Adaptive Token Length for Vision Transformers—0
Make A Long Image Short: Adaptive Token Length for Vision Transformers—0
Making a Case for Learning Motion Representations with Phase—0
Making Convolutional Networks Recurrent for Visual Sequence Learning—0
Making the Invisible Visible: Action Recognition Through Walls and Occlusions—0
MAMBA4D: Efficient Long-Sequence Point Cloud Video Understanding with Disentangled Spatial-Temporal State Space Models—0
Manipulated Object Proposal: A Discriminative Object Extraction and Feature Fusion Framework for First-Person Daily Activity Recognition—0
Show:102550
← PrevPage 54 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