Do we need early exit networks in human activity recognition?
Authors:
- Emanuele LattanziEmanuele Lattanzi
- Chiara ContoliCCChiara Contoli
- Valerio FreschiVFValerio Freschi
Open Access
- 26 February 2023
- journal article
- research article
- Published by Elsevier in Engineering Applications of Artificial Intelligence
- Vol. 121
Abstract
No abstract availableKeywords
Funding Information
- European Commission
This publication has 38 references indexed in Scilit:
- Deep Convolutional and LSTM Recurrent Neural Networks for Multimodal Wearable Activity RecognitionSensors, 2016
- Transition-Aware Human Activity Recognition Using SmartphonesNeurocomputing, 2016
- Smart Devices are Different2015
- Deep learningNature, 2015
- Window Size Impact in Human Activity RecognitionSensors, 2014
- The largest inertial sensor-based gait database and performance evaluation of gait-based personal authenticationPattern Recognition, 2014
- CoPoMo: a context‐aware power consumption model for LTE user equipmentTransactions on Emerging Telecommunications Technologies, 2013
- The McNemar test for binary matched-pairs data: mid-p and asymptotic are better than exact conditionalBMC Medical Research Methodology, 2013
- Activity recognition using cell phone accelerometersACM SIGKDD Explorations Newsletter, 2011
- A systematic analysis of performance measures for classification tasksInformation Processing & Management, 2009