SOTAVerified

Activity Recognition

Human Activity Recognition is the problem of identifying events performed by humans given a video input. It is formulated as a binary (or multiclass) classification problem of outputting activity class labels. Activity Recognition is an important problem with many societal applications including smart surveillance, video search/retrieval, intelligent robots, and other monitoring systems.

Source: Learning Latent Sub-events in Activity Videos Using Temporal Attention Filters

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 51–100 of 1322 papers

TitleStatusHype
HHAR-net: Hierarchical Human Activity Recognition using Neural NetworksCode1
DATTA: Domain-Adversarial Test-Time Adaptation for Cross-Domain WiFi-Based Human Activity RecognitionCode1
Privacy and Utility Preserving Sensor-Data TransformationsCode1
Protecting Sensory Data against Sensitive InferencesCode1
IMU2CLIP: Multimodal Contrastive Learning for IMU Motion Sensors from Egocentric Videos and TextCode1
Gimme Signals: Discriminative signal encoding for multimodal activity recognitionCode1
RelCon: Relative Contrastive Learning for a Motion Foundation Model for Wearable DataCode1
RF-Net: a Unified Meta-learning Framework for RF-enabled One-shot Human Activity RecognitionCode1
Fine-Grained Egocentric Hand-Object Segmentation: Dataset, Model, and ApplicationsCode1
Deep Unsupervised Domain Adaptation for Time Series Classification: a BenchmarkCode1
Self-Supervised PPG Representation Learning Shows High Inter-Subject VariabilityCode1
Self-supervised transfer learning of physiological representations from free-living wearable dataCode1
GroupFormer: Group Activity Recognition with Clustered Spatial-Temporal TransformerCode1
SHARP: Environment and Person Independent Activity Recognition with Commodity IEEE 802.11 Access PointsCode1
Ego-Exo: Transferring Visual Representations from Third-person to First-person VideosCode1
ESPRESSO: Entropy and ShaPe awaRe timE-Series SegmentatiOn for processing heterogeneous sensor dataCode1
Exploring Few-Shot Adaptation for Activity Recognition on Diverse DomainsCode1
Finding Order in Chaos: A Novel Data Augmentation Method for Time Series in Contrastive LearningCode1
A Review of Deep Learning Methods for Photoplethysmography DataCode1
Generating Virtual On-body Accelerometer Data from Virtual Textual Descriptions for Human Activity RecognitionCode1
Dual-path Adaptation from Image to Video TransformersCode1
Autoregressive Adaptive Hypergraph Transformer for Skeleton-based Activity RecognitionCode1
Attention-Based Deep Learning Framework for Human Activity Recognition with User AdaptationCode1
Hierarchical Self Attention Based Autoencoder for Open-Set Human Activity RecognitionCode1
Audio-Adaptive Activity Recognition Across Video DomainsCode1
Efficient Two-Stream Network for Violence Detection Using Separable Convolutional LSTMCode1
Action-slot: Visual Action-centric Representations for Multi-label Atomic Activity Recognition in Traffic ScenesCode1
Human Activity Segmentation Challenge @ ECML/PKDD’23Code1
CholecTriplet2021: A benchmark challenge for surgical action triplet recognitionCode1
A Federated Learning Aggregation Algorithm for Pervasive Computing: Evaluation and ComparisonCode1
Interactive Fusion of Multi-level Features for Compositional Activity RecognitionCode1
BASAR:Black-box Attack on Skeletal Action RecognitionCode1
LaMPP: Language Models as Probabilistic Priors for Perception and ActionCode1
Bridge-Prompt: Towards Ordinal Action Understanding in Instructional VideosCode1
Challenges in Multi-centric Generalization: Phase and Step Recognition in Roux-en-Y Gastric Bypass SurgeryCode1
CALDA: Improving Multi-Source Time Series Domain Adaptation with Contrastive Adversarial LearningCode1
COMODO: Cross-Modal Video-to-IMU Distillation for Efficient Egocentric Human Activity RecognitionCode1
Lightweight Transformers for Human Activity Recognition on Mobile DevicesCode1
milliFlow: Scene Flow Estimation on mmWave Radar Point Cloud for Human Motion SensingCode1
Exploring Contrastive Learning in Human Activity Recognition for HealthcareCode1
Comparing Self-Supervised Learning Techniques for Wearable Human Activity RecognitionCode1
COMPOSER: Compositional Reasoning of Group Activity in Videos with Keypoint-Only ModalityCode1
Multimodal Transformer for Nursing Activity RecognitionCode1
Multi-stage Learning for Radar Pulse Activity SegmentationCode1
Hard No-Box Adversarial Attack on Skeleton-Based Human Action Recognition with Skeleton-Motion-Informed GradientCode1
Convolutional Tensor-Train LSTM for Spatio-temporal LearningCode1
NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity UnderstandingCode1
Online Semi-Supervised Learning of Composite Event Rules by Combining Structure and Mass-Based Predicate SimilarityCode1
DANA: Dimension-Adaptive Neural Architecture for Multivariate Sensor DataCode1
IMUGPT 2.0: Language-Based Cross Modality Transfer for Sensor-Based Human Activity RecognitionCode1
Show:102550
← PrevPage 2 of 27Next →
All datasetsRWF-2000Stanford40First-Person Hand Action BenchmarkSelf-stimulatory Behavior Dataset

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Structured Keypoint PoolingAccuracy93.4—Unverified
2Semi-Supervised Hard Attention (SSHA); pretrained on Deepmind Kinetics datasetAccuracy90.4—Unverified
3Human Skeletons + Change DetectionAccuracy90.25—Unverified
4Separable Convolutional LSTMAccuracy89.75—Unverified
5SPIL ConvolutionAccuracy89.3—Unverified
6Flow Gated NetworkAccuracy87.25—Unverified
#ModelMetricClaimedVerifiedStatus
1FocusCLIPTop-3 Accuracy (%)10.47—Unverified
2CLIPTop-3 Accuracy (%)6.49—Unverified
#ModelMetricClaimedVerifiedStatus
1Boutaleb et al.1:1 Accuracy97.91—Unverified
#ModelMetricClaimedVerifiedStatus
1all-landmark-modelActivity Recognition0.76—Unverified