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 551–560 of 1322 papers

Title	Date	Tasks	Status	Hype
Unsupervised Learning of 3D Scene Flow with 3D Odometry Assistance	Sep 11, 2022	Activity RecognitionAutonomous Driving	—Unverified	0
Alignment-based conformance checking over probabilistic events	Sep 9, 2022	Activity Recognition	CodeCode Available	0
Human Activity Recognition on Microcontrollers with Quantized and Adaptive Deep Neural Networks	Sep 2, 2022	Activity RecognitionHuman Activity Recognition	—Unverified	0
To Store or Not? Online Data Selection for Federated Learning with Limited Storage	Sep 1, 2022	Activity RecognitionData Valuation	—Unverified	0
RecLight: A Recurrent Neural Network Accelerator with Integrated Silicon Photonics	Aug 31, 2022	Activity RecognitionAnomaly Detection	—Unverified	0
Group Activity Recognition in Basketball Tracking Data -- Neural Embeddings in Team Sports (NETS)	Aug 31, 2022	Activity RecognitionGroup Activity Recognition	—Unverified	0
Attentive pooling for Group Activity Recognition	Aug 31, 2022	Activity RecognitionGroup Activity Recognition	—Unverified	0
Self-Supervised Human Activity Recognition with Localized Time-Frequency Contrastive Representation Learning	Aug 26, 2022	Activity RecognitionClassification	—Unverified	0
SFusion: Self-attention based N-to-One Multimodal Fusion Block	Aug 26, 2022	Activity RecognitionBrain Tumor Segmentation	CodeCode Available	1
Contact-Free Multi-Target Tracking Using Distributed Massive MIMO-OFDM Communication System: Prototype and Analysis	Aug 23, 2022	Activity RecognitionCompressive Sensing	—Unverified	0

Show:10 25 50

← PrevPage 56 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