VL/HCC 2022
Mon 12 - Fri 16 September 2022 Rome, Italy
Tue 13 Sep 2022 10:30 - 17:30 at Corridor of San Francesco Room - Poster Presentation

Recent developments have resulted in multiple techniques trying to explain how deep neural networks achieve their predictions. The explainability maps provided by such techniques are useful to understand what the network has learned and increase user confidence in critical applications such as the medical field or autonomous driving. Nonetheless, they typically have very low resolutions, severely limiting their capability of identifying finer details or multiple subjects. In this paper we employ an encoder-decoder architecture with skip connection known as U-Net, originally developed for segmenting medical images, as an image classifier and we show that state of the art explainable techniques applied to U-Net can generate pixel level explanation maps for images of any resolution.

Tue 13 Sep

Displayed time zone: Amsterdam, Berlin, Bern, Rome, Stockholm, Vienna change

10:30 - 17:30
Poster PresentationPosters and Showpieces / Graduate Consortium at Corridor of San Francesco Room

Authors will attend only during breaks.

10:30
7h
Poster
Dear Diary: On Documenting Novices' Development ProcessPoster
Posters and Showpieces
Juan Pablo Sáenz Politecnico di Torino, Luigi De Russis Politecnico di Torino
DOI
10:30
7h
Poster
High Resolution Explanation Maps for CNNs using Segmentation NetworksPoster
Posters and Showpieces
Alessio Mascolini Politecnico di Torino, Francesco Ponzio Politecnico di Torino, Enrico Macii Politecnico DI Torino, Elisa Ficarra Università di Modena e Reggio Emilia, Santa Di Cataldo Politecnico Di Torino
DOI
10:30
7h
Poster
Early Design of a Conversational AI Development Platform for Middle SchoolersPoster
Posters and Showpieces
Amit Kumar University of Florida, Xiaoyi Tian University of Florida, Mehmet Celepkolu University of Florida, Maya Israel University of Florida, Kristy Elizabeth Boyer University of Florida
DOI
10:30
7h
Poster
fableBlocks: Toward Mitigating Programming Anxiety with Storytelling-based Tangible Block Programming EnvironmentsPoster
Posters and Showpieces
Alexandre Gomes de Siqueira University of Florida, Pedro Feijóo-García University of Florida, Stephanie Carnell University of Central Florida, Eduardo Gabriel Queiroz Palmeira Santa Catarina State University, Andrew Maxim University of Florida
DOI
10:30
7h
Constructionism, Ethics, and Creativity: Developing Tools for the Future of Education with AIGC Poster
Graduate Consortium
Randi Williams Massachusetts Institute of Technology
DOI
10:30
7h
Improving Real-time Collaborative Data Science Through Context-Aware MechanismsGC Poster
Graduate Consortium
April Wang University of Michigan
DOI
10:30
7h
Time-Travel Debugging with Visualization of Data-Structures Based on InstrumentationGC Poster
Graduate Consortium
Kim Mönch Bundeswehr University Munich
DOI
10:30
7h
The Role of Artificial Intelligence in Human-Computer Interaction: Using a Smart Topic Extraction SystemGC Poster
Graduate Consortium
Parinaz Tabari University of Salerno
DOI