SeeForMe on TechCrunch Real-time Wearable Computer Vision System

SeeForMe. Wearable Computer Vision System

Our demo paper “Real-time Wearable Computer Vision System for Improved Museum Experience” at ACM Multimedia 2016 was reported on TechCrunch as worth highlighting!

Read the paper!

SeeForMe is a mobile application which runs on a mobile wearable device and perform real-time object classification and artwork recognition using a wearable device. SeeForMe improves user experience during a museum visit by providing contextual information and performing user profiling.

In the demo paper we propose the use of a compact CNN network that performs object classification and artwork localization and, using the same CNN features, we perform a robust artwork recognition.

Shape based filtering, artwork tracking and temporal filtering further improve recognition accuracy.

My Kieu, Andrew D. Bagdanov, Marco Bertini, Alberto del Bimbo, Task-conditioned Domain Adaptation for Pedestrian Detection in Thermal Imagery

ECCV 2020 Paper

Domain Adaptation for Pedestrian Detection

Arnold Smeulders at MICC

Computer Vision in 2015

Lecture by Arnold Smeulders at MICC

Wolmer Bigi, Claudio Baecchi, Alberto Del Bimbo, Automatic Interest Recognition from Posture and Behaviour

ACM MM 2020 Paper

Interest Recognition from Posture and Behaviour

Lamberto Ballan

Sharing Knowledge

for Large Scale Visual Recognition