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 51–75 of 1322 papers

TitleStatusHype
3D Human Shape and Pose from a Single Low-Resolution Image with Self-Supervised LearningCode1
CALDA: Improving Multi-Source Time Series Domain Adaptation with Contrastive Adversarial LearningCode1
Learning Disentangled Behaviour Patterns for Wearable-based Human Activity RecognitionCode1
CholecTriplet2021: A benchmark challenge for surgical action triplet recognitionCode1
COMODO: Cross-Modal Video-to-IMU Distillation for Efficient Egocentric Human Activity RecognitionCode1
COMPOSER: Compositional Reasoning of Group Activity in Videos with Keypoint-Only ModalityCode1
Comparing Self-Supervised Learning Techniques for Wearable Human Activity RecognitionCode1
Meta-HAR: Federated Representation Learning for Human Activity RecognitionCode1
Contrastive Learning with Cross-Modal Knowledge Mining for Multimodal Human Activity RecognitionCode1
MOMA-LRG: Language-Refined Graphs for Multi-Object Multi-Actor Activity ParsingCode1
Multimodal Transformer for Nursing Activity RecognitionCode1
Multi-stage Learning for Radar Pulse Activity SegmentationCode1
DeepSense: A Unified Deep Learning Framework for Time-Series Mobile Sensing Data ProcessingCode1
Efficient Two-Stream Network for Violence Detection Using Separable Convolutional LSTMCode1
DANA: Dimension-Adaptive Neural Architecture for Multivariate Sensor DataCode1
A Federated Learning Aggregation Algorithm for Pervasive Computing: Evaluation and ComparisonCode1
DATTA: Domain-Adversarial Test-Time Adaptation for Cross-Domain WiFi-Based Human Activity RecognitionCode1
Deep Learning for Time Series Classification and Extrinsic Regression: A Current SurveyCode1
Deep Unsupervised Domain Adaptation for Time Series Classification: a BenchmarkCode1
BASAR:Black-box Attack on Skeletal Action RecognitionCode1
SHARP: Environment and Person Independent Activity Recognition with Commodity IEEE 802.11 Access PointsCode1
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
Show:102550
← PrevPage 3 of 53Next →
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