Oral session 4

Oral session 4

• A Robust Ensemble of ResNets for Character Level End-to-end Text Detection in Natural Scene Images, Jinsu Kim, Yoonhyung Kim, Changick Kim
• Improving Hierarchical Image Classification with Merged CNN Architectures, Georges Quénot, Anuvabh Dutt, Denis Pellerin
• FuseMe: Classification of sMRI images by fusion of Deep CNNs in 2D+epsilon projections, Karim Aderghal, Jenny Benois-Pineau, Karim Afdel, Gwenaëlle Catheline
• Question Part Relevance and Editing for Cooperative and Context-Aware VQA (C2VQA), Andeep S. Toor, Harry Wechsler, Michele Nappi
• Automatic Cartoon Colorization Based on Convolutional Neural Network, Domonkos Varga, Csaba Szabo, Tamas Sziranyi

Session chair: Werner Bailer, Joanneum Research