PaddleDetection
Object Detection toolkit based on PaddlePaddle. It supports object detection, instance segmentation, multiple object tracking and real-time multi-person keypoint detection.
- 14k
- Python
- Apache-2.0
- 6 mo ago
Object Detection toolkit based on PaddlePaddle. It supports object detection, instance segmentation, multiple object tracking and real-time multi-person keypoint detection.
Human Activity Recognition example using TensorFlow on smartphone sensors dataset and an LSTM RNN. Classifying the type of movement amongst six activity categories - Guillaume Chevalier
Real-Time Spatio-Temporally Localized Activity Detection by Tracking Body Keypoints
Python implementation of KNN and DTW classification algorithm
[IJCAI-21] "Time-Series Representation Learning via Temporal and Contextual Contrasting"
Convolutional Neural Network for Human Activity Recognition in Tensorflow
MotionSense Dataset for Human Activity and Attribute Recognition ( time-series data generated by smartphone's sensors: accelerometer and gyroscope) (PMC Journal) (IoTDI'19)
An up-to-date & curated list of Awesome IMU-based Human Activity Recognition(Ubiquitous Computing) papers, methods & resources. Please note that most of the collections of researches are mainly based on IMU data.
Unity's privacy-preserving human-centric synthetic data generator
Using deep stacked residual bidirectional LSTM cells (RNN) with TensorFlow, we do Human Activity Recognition (HAR). Classifying the type of movement amongst 6 categories or 18 categories on 2 different datasets.
Always up-to-date, most comprehensive HAR resource — continuously scanned and auto-updated from Papers with Code. 53 datasets integrated across all modalities.
Abnormal Human Behaviors Detection/ Road Accident Detection From Surveillance Videos/ Real-World Anomaly Detection in Surveillance Videos/ C3D Feature Extraction
Classifying the physical activities performed by a user based on accelerometer and gyroscope sensor data collected by a smartphone in the user’s pocket. The activities to be classified are: Standing, Sitting, Stairsup, StairsDown, Walking and Cycling.
Implementation of Action Recognition using 3D Convnet on UCF-101 dataset.
DANA: Dimension-Adaptive Neural Architecture (UbiComp'21)( ACM IMWUT)
Jupyter Notebook for Human Activity Recognition (HAR) with Keras and CoreML
Official code for "SimPSI: A Simple Strategy to Preserve Spectral Information in Time Series Data Augmentation", AAAI 2024.
Python+YOLOv8-based human/animal/object detection DVR framework with GUI, webUI and Telegram alerts
WiFi CSI-based gesture recognition using dual-path ensemble deep learning (CNN2D + CNN1D-LSTM). 90.19% accuracy on ESP32 hardware with 426K parameters.
SCAR-Net, Submission to the Cooking Activity Recognition Challenge, ABC: competition track
This python opencv code is used to segment the human object from the video frame
[ECCV 2024]Temporary code for "Ad-HGformer: An Adaptive HyperGraph Transformer for Skeletal Action Recognition"
Code for paper "Automated Spatial-Temporal Graph Neural Network Search for Skeleton-based Human Action Recognition on Edge Devices"
Classify 15 human activities from images using MobileNetV2
Runs in the browser on Hugging Face
This experiment is the classification of human activities using a 2D pose time series dataset and an LSTM RNN. The idea is to prove the concept that using a series of 2D poses, rather than 3D poses or a raw 2D images, can produce an accurate estimation of the behaviour of a person or animal.
A Machine Learning approach to predict the activities of person.
Reproducible human activity recognition using CNN, LSTM, and GRU models on UCI smartphone accelerometer and gyroscope data, with TensorFlow training, evaluation, tests, and paper-aligned experiments.