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 1171–1180 of 1322 papers

Title	Date	Tasks	Status
A Survey of Human Activity Recognition Using WiFi CSI	Aug 23, 2017	Activity RecognitionBIG-bench Machine Learning	CodeCode Available
Activity Recognition based on a Magnitude-Orientation Stream Network	Aug 22, 2017	Activity RecognitionOptical Flow Estimation	—Unverified
Deep Residual Bidir-LSTM for Human Activity Recognition Using Wearable Sensors	Aug 22, 2017	Activity RecognitionHuman Activity Recognition	CodeCode Available
Early Improving Recurrent Elastic Highway Network	Aug 14, 2017	Activity RecognitionHuman Activity Recognition	—Unverified
Extreme Low Resolution Activity Recognition with Multi-Siamese Embedding Learning	Aug 3, 2017	Activity RecognitionPrivacy Preserving	—Unverified
Zero-Shot Activity Recognition with Verb Attribute Induction	Jul 29, 2017	Activity RecognitionAttribute	CodeCode Available
Multi-kernel learning of deep convolutional features for action recognition	Jul 21, 2017	Action RecognitionActivity Recognition	—Unverified
Sequential Lifted Bayesian Filtering in Multiset Rewriting Systems	Jul 20, 2017	Activity RecognitionState Space Models	—Unverified
Deep Learning for Sensor-based Activity Recognition: A Survey	Jul 12, 2017	Activity RecognitionDeep Learning	CodeCode Available
An Interactive Greedy Approach to Group Sparsity in High Dimensions	Jul 10, 2017	Activity RecognitionHuman Activity Recognition	CodeCode Available

Show:10 25 50

← PrevPage 118 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