Section: New Results

Introduction

This year Stars has proposed new results related to its three main research axes: (i) perception for activity recognition, (ii) action recognition and (iii) semantic activity recognition.

• Handling the Speed-Accuracy Trade-off in Deep Learning based Pedestrian Detection (see 6.2)

• Deep Learning applied on Embedded Systems for People Tracking (see 6.3)

• Partition and Reunion: A Two-Branch Neural Network for Vehicle Re- identification (see 6.4)

• Improving Face Sketch Recognition via Adversarial Sketch-Photo Transformation (see 6.5)

• Impact and Detection of Facial Beautification in Face Recognition: An Overview (see 6.6)

• Computer Vision and Deep Learning applied to Facial analysis in the invisible spectra (see 6.7)

• ImaGINator: Conditional Spatio-Temporal GAN for Video Generation (see 6.8)

• Characterizing the State of Apathy with Facial Expression and Motion Analysis (see 6.9)

• Dual-threshold Based Local Patch Construction Method for Manifold Approximation And Its Application to Facial Expression Analysis (see 6.10)

• A Weakly Supervised Learning Technique for Classifying Facial Expressions (see 6.11)

• Robust Remote Heart Rate Estimation from Face Utilizing Spatial- temporal Attention (see 6.12)

• Quantified Analysis for Epileptic Seizure Videos (see 6.13)

• Toyota Smarthome: Real-World Activities of Daily Living (see 6.15)

• Looking deeper into Time for Activities of Daily Living Recognition (see 6.15.1)

• Self-Attention Temporal Convolutional Network for Long-Term Daily Living Activity Detection (see 6.16)

• DeepSpa Project (see 6.17)

• Store Connect and Solitaria (see 6.18)

• Synchronous Approach to Activity Recognition (see 6.19)

• Probabilistic Activity Modeling (see 6.20)