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 76–100 of 1322 papers

TitleStatusHype
PartImageNet: A Large, High-Quality Dataset of PartsCode1
CubeLearn: End-to-end Learning for Human Motion Recognition from Raw mmWave Radar SignalsCode1
RF-Net: a Unified Meta-learning Framework for RF-enabled One-shot Human Activity RecognitionCode1
A Federated Learning Aggregation Algorithm for Pervasive Computing: Evaluation and ComparisonCode1
OPERAnet: A Multimodal Activity Recognition Dataset Acquired from Radio Frequency and Vision-based SensorsCode1
CALDA: Improving Multi-Source Time Series Domain Adaptation with Contrastive Adversarial LearningCode1
Transformer Networks for Data Augmentation of Human Physical Activity RecognitionCode1
GroupFormer: Group Activity Recognition with Clustered Spatial-Temporal TransformerCode1
Spatio-Temporal Dynamic Inference Network for Group Activity RecognitionCode1
Classification of Abnormal Hand Movement for Aiding in Autism Detection: Machine Learning StudyCode1
Transfer Learning for Pose Estimation of Illustrated CharactersCode1
Improving Deep Learning for HAR with shallow LSTMsCode1
Let's Play for Action: Recognizing Activities of Daily Living by Learning from Life Simulation Video GamesCode1
Meta-HAR: Federated Representation Learning for Human Activity RecognitionCode1
Learning Group Activities from Skeletons without Individual Action LabelsCode1
Ego-Exo: Transferring Visual Representations from Third-person to First-person VideosCode1
SHARP: Environment and Person Independent Activity Recognition with Commodity IEEE 802.11 Access PointsCode1
Interpretable Deep Learning for the Remote Characterisation of Ambulation in Multiple Sclerosis using SmartphonesCode1
BASAR:Black-box Attack on Skeletal Action RecognitionCode1
Hierarchical Self Attention Based Autoencoder for Open-Set Human Activity RecognitionCode1
Efficient Two-Stream Network for Violence Detection Using Separable Convolutional LSTMCode1
SelfHAR: Improving Human Activity Recognition through Self-training with Unlabeled DataCode1
Human Activity Recognition using Wearable Sensors: Review, Challenges, Evaluation BenchmarkCode1
Interactive Fusion of Multi-level Features for Compositional Activity RecognitionCode1
Exploring Contrastive Learning in Human Activity Recognition for HealthcareCode1
Show:102550
← PrevPage 4 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