Awesome

Awesome Human Activity Recognition

• 1. Datasets
• 2. Paper with code (By year)
  • 2020
  • 2019
  • 2018
  • 2017
  • 2016
  • 2015
  • 2014
  • 2013
  • 2012
  • 2011
  • 2010
• 3. Survey & Overview
• 4. Unsupervised Learning
  • Unsupervised Domain Adaptation
• 5. Self-Supervised Learning
• 6. Transfer Learning
• 7. Multi Task Learning
• 8. Continual Learning
• 9. Other

1. Datasets

• Opportunity [link]
• PAMAP2 [link]

2. Paper with code

2020

• Latent Independent Excitation for Generalizable Sensor-based Cross-Person Activity Recognition [paper] [code] (AAAI 2021)
• Cross-Dataset Activity Recognition via Adaptive Spatial-Temporal Transfer Learning [paper] [code] (IMWUT/ubicomp)
• MARS: Mixed Virtual and Real Wearable Sensors for Human Activity Recognition with Multi-Domain Deep Learning Model [paper] [code] (arXiv)
• Towards Deep Clustering of Human Activities from Wearables [paper] [code] (ISWC/ubicomp)
• [UDA4HAR] A Systematic Study of Unsupervised Domain Adaptation for Robust Human-Activity Recognition [paper] [code] (IMWUT/ubicomp)
• Adversarial Multi-view Networks for Activity Recognition [paper] [code] (IMWUT/ubicomp)
• Weakly Supervised Multi-Task Representation Learning for Human Activity Analysis Using Wearables [paper] [code] (IMWUT/ubicomp)
• [IMUTube] IMUTube: Automatic Extraction of Virtual on-body Accelerometry from Video for Human Activity Recognition [paper] [code] (IMWUT/ubicomp)
• Robust Unsupervised Factory Activity Recognition with Body-worn Accelerometer Using Temporal Structure of Multiple Sensor Data Motifs [paper] [code] (IMWUT/ubicomp)
• Masked reconstruction based self-supervision for human activity recognition [paper] [code] (ISWC/ubicomp)
• Digging deeper: towards a better understanding of transfer learning for human activity recognition with Body-worn Accelerometer Using Temporal Structure of Multiple Sensor Data Motifs [paper] [code] (ISWC/ubicomp)
• IndRNN based long-term temporal recognition in the spatial and frequency domain [paper] [code] (ISWC/ubicomp)
• Tackling the SHL challenge 2020 with person-specific classifiers and semi-supervised learning [paper] [code] (ISWC/ubicomp)
• DenseNetX and GRU for the sussex-huawei locomotion-transportation recognition challenge [paper] [code] (ISWC/ubicomp)

2019

• Transfer Learning with Dynamic Adversarial Adaptation Network [paper] [code] (ICDM 2019)
• A Novel Distribution-Embedded Neural Network for Sensor-Based Activity Recognition [paper] [code] (IJCAI)
• [AttnSense] AttnSense: Multi-level Attention Mechanism For Multimodal Human Activity Recognition [paper] [code] (IJCAI)
• Multi-agent Attentional Activity Recognition [paper] [code] (IJCAI)
• Distribution-based Semi-Supervised Learning for Activity Recognition [paper] [code] (AAAI)
• On the Role of Features in Human Activity Recognition [paper] [code] (ISWC/ubicomp)
• Handling Annotation Uncertainty in Human Activity Recognition [paper] [code] (ISWC/ubicomp)
• Leveraging Active Learning and Conditional Mutual Information to Minimize Data Annotation in Human Activity Recognition [paper] [code] (IMWUT/ubicomp)
• Multi-task Self-Supervised Learning for Human Activity Detection [paper] [code] (IMWUT/ubicomp)
• [Vision2Sensor] Vision2Sensor: Knowledge Transfer Across Sensing Modalities for Human Activity Recognition [paper] [code] (IMWUT/ubicomp)
• How Does a Nation Walk? Interpreting Large-Scale Step Count Activity with Weekly Streak Patterns [paper] [code] (IMWUT/ubicomp)

2018

• Understanding and Improving Recurrent Networks for Human Activity Recognition by Continuous Attention [paper] [code] (ISWC/ubicomp)
• On specialized window lengths and detector based human activity recognition [paper] [code] (ISWC/ubicomp)
• Adding structural characteristics to distribution-based accelerometer representations for activity recognition using wearables [paper] [code] (ISWC/ubicomp)
• On Attention Models for Human Activity Recognition [paper] [code] (ISWC/ubicomp)
• [AROMA] AROMA: A Deep Multi-Task Learning Based Simple and Complex Human Activity Recognition Method Using Wearable Sensors [paper] [code] (IMWUT/ubicomp)

2017

• [EnsemblesLSTM] Ensembles of Deep LSTM Learners for Activity Recognition using Wearables [paper] [code] (IMWUT/ubicomp)
• Deep Learning for Sensor-based Activity Recognition: A Survey [paper] [code] (Pattern Recognition Letters)
• Activity Recognition for Quality Assessment of Batting Shots in Cricket using a Hierarchical Representation [paper] [code] (IMWUT/ubicomp)
• Label Propagation: An Unsupervised Similarity Based Method for Integrating New Sensors in Activity Recognition Systems [paper] [code] (IMWUT/ubicomp)
• CNN-based sensor fusion techniques for multimodal human activity recognition [paper] [code] (ISWC/ubicomp)

2016

• Learning from less for better: semi-supervised activity recognition via shared structure discovery [paper] [code] (ubicomp)
• Wearable sensor based multimodal human activity recognition exploiting the diversity of classifier ensemble [paper] [code] (ubicomp)

2015

• Beyond activity recognition: skill assessment from accelerometer data [paper] [code] (ubicomp)
• I did not smoke 100 cigarettes today!: avoiding false positives in real-world activity recognition [paper] [code] (ubicomp)
• Let's (not) stick together: pairwise similarity biases cross-validation in activity recognition [paper] [code] (ubicomp)
• Improved activity recognition by using enriched acceleration data [paper] [code] (ubicomp)
• A field study comparing approaches to collecting annotated activity data in real-world settings [paper] [code] (ubicomp)
• Personalization revisited: a reflective approach helps people better personalize health services and motivates them to increase physical activity [paper] [code] (ubicomp)

2014

• MONITORING HOUSEHOLD ACTIVITIES AND USER LOCATION WITH A CHEAP, UNOBTRUSIVE THERMAL SENSOR ARRAY [paper] [code] (ubicomp)
• Connecting personal-scale sensing and networked community behavior to infer human activities [paper] [code] (ubicomp)
• Using electrodermal activity to recognize ease of engagement in children during social interactions [paper] [code] (ubicomp)

2013

• Fine-Grained Sharing of Sensed Physical Activity: A Value Sensitive Approach [paper] [code] (ubicomp)
• Towards zero-shot learning for human activity recognition using semantic attribute sequence model [paper] [code] (ubicomp)
• Personalized mobile physical activity recognition [paper] [code] (ubicomp)
• A Hybrid Unsupervised/Supervised Model for Group Activity Recognition [paper] [code] (ubicomp)
• Confidence-based Multiclass AdaBoost for Physical Activity Monitoring [paper] [code] (ubicomp)
• An exploration with online complex activity recognition using cellphone accelerometer [paper] [code] (ubicomp)
• [UniPad] UniPad: Orchestrating collaborative activities through shared tablets and an integrated wall display [paper] [code] (ubicomp)
• Human Activity Recognition Using Heterogeneous Sensors [paper] [code] (ubicomp)
• A probabilistic ontological framework for the recognition of multilevel human activities [paper] [code] (ubicomp)
• Ubiquitous support for midwives to leverage daily activities [paper] [code] (ubicomp)
• Combining Embedded Accelerometers with Computer Vision for Recognizing Food Preparation Activities [paper] [code] (ubicomp)

2012

• A Spark Of Activity: Exploring Information Art As Visualization For Physical Activity [paper] [code] (ubicomp)
• [BodyScope] BodyScope: A Wearable Acoustic Sensor for Activity Recognition [paper] [code] (ubicomp)
• An Integrated Framework for Human Activity Classification [paper] [code] (ubicomp)

2011

• The Place for Ubiquitous Computing in Schools: Lessons Learned from a School-Based Intervention for Youth Physical Activity [paper] [code] (ubicomp)
• [CSN] Enabling Large-scale Human Activity Inference on Smartphones using Community Similarity Networks [paper] [code] (ubicomp)

2010

• Using Wearable Activity Type Detection to Improve Physical Activity Energy Expenditure Estimation [paper] [code] (ubicomp)

3. Survey & Overview

4. Unsupervised Learning

4.1 Unsupervised Domain Adaptation

• A Systematic Study of Unsupervised Domain Adaptation for Robust Human-Activity Recognition [paper] [code] (Ubicomp 2020)

5. Self-Supervised Learning

• Masked Reconstruction Based Self-Supervision for Human Activity Recognition [paper] [code] (Ubicomp 2020)

6. Transfer Learning

• Latent Independent Excitation for Generalizable Sensor-based Cross-Person Activity Recognition [paper] [code] (AAAI 2021)
• XHAR: Deep Domain Adaptation for Human Activity Recognition with Smart Devices [paper] [code] (SECON 2020)
• Incremental Real-Time Personalization in Human Activity Recognition Using Domain Adaptive Batch Normalization [paper] [code] (Arxiv May 2020)
• ActiLabel: A Combinatorial Transfer Learning Framework for Activity Recognition [paper] [code] (Arxiv March 2020)
• Digging Deeper: Towards a Better Understanding of Transfer Learning for Human Activity Recognition [paper] [code] (Ubicomp 2020)
• Cross-Dataset Activity Recognition via Adaptive Spatial-Temporal Transfer Learning [paper] [code] (Ubicomp 2020)
• Transferring Activity Recognition Models for New Wearable Sensors with Deep Generative Domain Adaptation [paper] [code] (IPSN 2019)
• Scaling Human Activity Recognition via Deep Learning-based Domain Adaptation [paper] [code] (PerCom 2018)
• Deep transfer learning for cross-domain activity recognition [paper] [code] (ICCSE 2018)
• Label Propagation: An Unsupervised Similarity Based Method for Integrating New Sensors in Activity Recognition Systems [paper] [code] (IMWUT/ubicomp 2017)
• Deep convolutional feature transfer across mobile activity recognition domains, sensor modalities and locations [paper] [code] (ISWC 2016)

7. Multi Task Learning

• METIER: A Deep Multi-Task Learning Based Activity and User Recognition Model Using Wearable Sensors [paper] [code] (Ubicomp 2020)

8. Continual Learning

• Continual Learning in Human Activity Recognition: an Empirical Analysis of Regularization [paper] [code] (ICML Continual Learning Workshop 2020)

9. Other

• Robust Unsupervised Factory Activity Recognition with Body-worn Accelerometer Using Temporal Structure of Multiple Sensor Data Motifs [paper] [code] (Ubicomp 2020)
• DeepMV: Multi-View Deep Learning for Device-Free Human Activity Recognition [paper] [code] (Ubicomp 2020)
• AuraRing: Precise Electromagnetic Finger Tracking [paper] [code] (Ubicomp 2020)
• Adversarial Multi-view Networks for Activity Recognition [paper] [code] (Ubicomp 2020)
• Weakly Supervised Multi-Task Representation Learning for Human Activity Analysis Using Wearables [paper] [code] (Ubicomp 2020)