Search Results for author:
Found 10 papers, 4 papers with code
Fall Detection using Knowledge Distillation Based Long short-term memory for Offline Embedded and Low Power Devices
This paper presents a cost-effective, low-power approach to unintentional fall detection using knowledge distillation-based LSTM (Long Short-Term Memory) models to significantly improve accuracy.
DeepActsNet: Spatial and Motion features from Face, Hands, and Body Combined with Convolutional and Graph Networks for Improved Action Recognition
Existing action recognition methods mainly focus on joint and bone information in human body skeleton data due to its robustness to complex backgrounds and dynamic characteristics of the environments.
SSHFD: Single Shot Human Fall Detection with Occluded Joints Resilience
First, we present a human pose based fall representation which is invariant to appearance characteristics.
Ensemble Knowledge Distillation for Learning Improved and Efficient Networks
Ensemble models comprising of deep Convolutional Neural Networks (CNN) have shown significant improvements in model generalization but at the cost of large computation and memory requirements.
Ranked #7 on
Knowledge Distillation
on ImageNet
PubLayNet: largest dataset ever for document layout analysis
Deep neural networks that are developed for computer vision have been proven to be an effective method to analyze layout of document images.
Ranked #11 on
Document Layout Analysis
on PubLayNet val
SeizureNet: Multi-Spectral Deep Feature Learning for Seizure Type Classification
Automatic classification of epileptic seizure types in electroencephalograms (EEGs) data can enable more precise diagnosis and efficient management of the disease.
Seizure Type Classification using EEG signals and Machine Learning: Setting a benchmark
On that note, in this paper, we explore the application of machine learning algorithms for multi-class seizure type classification.
Densely Supervised Grasp Detector (DSGD)
At the pixel-level, DSGD uses a fully convolutional network and predicts a grasp and its confidence at every pixel.
Improving classification accuracy of feedforward neural networks for spiking neuromorphic chips
We achieve this by training directly a binary hardware crossbar that accommodates the TrueNorth axon configuration constrains and we propose a different neuron model.
Improving energy efficiency and classification accuracy of neuromorphic chips by learning binary synaptic crossbars
Previous work has achieved this by training a network to learn continuous probabilities and deployment to a neuromorphic architecture by random sampling these probabilities.
