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 51–60 of 1322 papers

Title	Date	Tasks	Status	Hype	Score
3D Human Shape and Pose from a Single Low-Resolution Image with Self-Supervised Learning	Jul 27, 2020	3D Human Pose Estimation3D Shape Reconstruction	CodeCode Available	1	5
Audio-Adaptive Activity Recognition Across Video Domains	Mar 27, 2022	Activity RecognitionDomain Adaptation	CodeCode Available	1	5
Contrastive Learning with Cross-Modal Knowledge Mining for Multimodal Human Activity Recognition	May 20, 2022	Activity RecognitionContrastive Learning	CodeCode Available	1	5
A Federated Learning Aggregation Algorithm for Pervasive Computing: Evaluation and Comparison	Oct 19, 2021	Activity RecognitionFederated Learning	CodeCode Available	1	5
CholecTriplet2021: A benchmark challenge for surgical action triplet recognition	Apr 10, 2022	Action DetectionAction Triplet Recognition	CodeCode Available	1	5
Human skeletons and change detection for efficient violence detection in surveillance videos	May 20, 2023	Activity RecognitionChange Detection	CodeCode Available	1	5
Bridge-Prompt: Towards Ordinal Action Understanding in Instructional Videos	Mar 26, 2022	Action SegmentationAction Understanding	CodeCode Available	1	5
IMU2CLIP: Multimodal Contrastive Learning for IMU Motion Sensors from Egocentric Videos and Text	Oct 26, 2022	Activity RecognitionContrastive Learning	CodeCode Available	1	5
CALDA: Improving Multi-Source Time Series Domain Adaptation with Contrastive Adversarial Learning	Sep 30, 2021	Activity RecognitionContrastive Learning	CodeCode Available	1	5
COMODO: Cross-Modal Video-to-IMU Distillation for Efficient Egocentric Human Activity Recognition	Mar 10, 2025	Activity RecognitionHuman Activity Recognition	CodeCode Available	1	5

Show:10 25 50

← PrevPage 6 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