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 Added Most Hyped Most Active Needs Verification Most Verified

Showing 81–90 of 1322 papers

Title	Date	Tasks	Status	Hype
CALDA: Improving Multi-Source Time Series Domain Adaptation with Contrastive Adversarial Learning	Sep 30, 2021	Activity RecognitionContrastive Learning	CodeCode Available	1
Transformer Networks for Data Augmentation of Human Physical Activity Recognition	Sep 2, 2021	Activity RecognitionData Augmentation	CodeCode Available	1
GroupFormer: Group Activity Recognition with Clustered Spatial-Temporal Transformer	Aug 28, 2021	Activity RecognitionGroup Activity Recognition	CodeCode Available	1
Spatio-Temporal Dynamic Inference Network for Group Activity Recognition	Aug 26, 2021	Activity RecognitionGroup Activity Recognition	CodeCode Available	1
Classification of Abnormal Hand Movement for Aiding in Autism Detection: Machine Learning Study	Aug 18, 2021	Action DetectionActivity Detection	CodeCode Available	1
Transfer Learning for Pose Estimation of Illustrated Characters	Aug 4, 2021	Activity RecognitionPose Estimation	CodeCode Available	1
Improving Deep Learning for HAR with shallow LSTMs	Aug 2, 2021	Activity RecognitionDeep Learning	CodeCode Available	1
Let's Play for Action: Recognizing Activities of Daily Living by Learning from Life Simulation Video Games	Jul 12, 2021	Action ClassificationActivity Recognition	CodeCode Available	1
Meta-HAR: Federated Representation Learning for Human Activity Recognition	May 31, 2021	Activity PredictionActivity Recognition	CodeCode Available	1
Learning Group Activities from Skeletons without Individual Action Labels	May 14, 2021	Activity RecognitionGroup Activity Recognition	CodeCode Available	1

Show:10 25 50

← PrevPage 9 of 133Next →

All datasets RWF-2000 Stanford40 First-Person Hand Action Benchmark Self-stimulatory Behavior Dataset

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	Structured Keypoint Pooling	Accuracy	93.4	—	Unverified
2	Semi-Supervised Hard Attention (SSHA); pretrained on Deepmind Kinetics dataset	Accuracy	90.4	—	Unverified
3	Human Skeletons + Change Detection	Accuracy	90.25	—	Unverified
4	Separable Convolutional LSTM	Accuracy	89.75	—	Unverified
5	SPIL Convolution	Accuracy	89.3	—	Unverified
6	Flow Gated Network	Accuracy	87.25	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	FocusCLIP	Top-3 Accuracy (%)	10.47	—	Unverified
2	CLIP	Top-3 Accuracy (%)	6.49	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Boutaleb et al.	1:1 Accuracy	97.91	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	all-landmark-model	Activity Recognition	0.76	—	Unverified