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 1–10 of 1322 papers

Title	Date	Tasks	Status	Hype	Score
HARDVS: Revisiting Human Activity Recognition with Dynamic Vision Sensors	Nov 17, 2022	Activity PredictionActivity Recognition	CodeCode Available	3	5
ALS-HAR: Harnessing Wearable Ambient Light Sensors to Enhance IMU-based Human Activity Recogntion	Aug 18, 2024	Activity RecognitionHuman Activity Recognition	CodeCode Available	3	5
Self-Supervised Contrastive Pre-Training For Time Series via Time-Frequency Consistency	Jun 17, 2022	Activity RecognitionDomain Adaptation	CodeCode Available	2	5
Class-incremental Learning for Time Series: Benchmark and Evaluation	Feb 19, 2024	Activity RecognitionBenchmarking	CodeCode Available	2	5
AutoFi: Towards Automatic WiFi Human Sensing via Geometric Self-Supervised Learning	Apr 12, 2022	Activity RecognitionDomain Adaptation	CodeCode Available	2	5
NeuFlow: Real-time, High-accuracy Optical Flow Estimation on Robots Using Edge Devices	Mar 15, 2024	Activity RecognitionEdge-computing	CodeCode Available	2	5
Deep learning for time series classification	Oct 1, 2020	Activity RecognitionClassification	CodeCode Available	2	5
SenseFi: A Library and Benchmark on Deep-Learning-Empowered WiFi Human Sensing	Jul 16, 2022	Activity RecognitionDeep Learning	CodeCode Available	2	5
Human Activity Recognition using RGB-Event based Sensors: A Multi-modal Heat Conduction Model and A Benchmark Dataset	Apr 8, 2025	Activity RecognitionHuman Activity Recognition	CodeCode Available	2	5
SensorLLM: Human-Intuitive Alignment of Multivariate Sensor Data with LLMs for Activity Recognition	Oct 14, 2024	Activity RecognitionDescriptive	CodeCode Available	2	5

Show:10 25 50

← PrevPage 1 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