VIP_P2: Learning-based audiovisual processing |
Session Type: Poster |
Time: Thursday, September 1, 11:00 - 12:40 |
Location: Poster Area 2 |
Session Chair: Federica Battisti, University of Padova
|
|
VIP_P2.1: TOWARDS AN IMAGE UTILITY ASSESSMENT FRAMEWORK FOR MACHINE PERCEPTION |
Zohaib Amjad Khan, Giuseppe Valenzise, Frederic Dufaux, Université Paris-Saclay, France; Aladine Chetouani, Université d’Orléans, France |
|
VIP_P2.2: RECTIFYING ADVERSARIAL INPUTS USING XAI TECHNIQUES |
Ching-Yu Kao, Fraunhofer Institute for Applied and Integrated Security, Germany; Junhao Chen, Karlsruher Institut für Technologie, China; Karla Markert, Konstantin Böttinger, Fraunhofer Institute for Applied and Integrated Security AISEC, Germany |
|
VIP_P2.3: INTRINSIC IMAGE DECOMPOSITION UNDER MULTIPLE COLORED LIGHTING CONDITIONS USING A SINGLE IMAGE |
Kakeru Hara, Hiromitsu Isobe, Takao Jinno, Osaka Institute of Technology, Japan |
|
VIP_P2.4: COLORED-QRNET: FAST QR CODE COLOR IMAGE EMBEDDING |
Karelia Pena-Pena, Gonzalo Arce, University of Delaware, United States; Daniel Lau, University of Kentucky, United States |
|
VIP_P2.5: SIMILARITY ANALYSIS OF SIMULATED SAR TARGET IMAGES |
Ganggang Dong, Ziyi yu, Xidian University, China |
|
VIP_P2.6: TRANSFORMER NETWORK FOR SEMANTICALLY-AWARE AND SPEECH-DRIVEN UPPER-FACE GENERATION |
Mireille Fares, Catherine Pelachaud, Nicolas Obin, Sorbonne Université, France |
|
VIP_P2.7: ASSISLT: COMPUTER-AIDED SPEECH THERAPY TOOL |
Zuzana Bilkova, Michal Bartos, Adam Dominec, Simon Gresko, Adam Novozamsky, Barbara Zitova, Marketa Paroubkova, Czech Academy of Sciences, Czech Republic |
|
VIP_P2.8: GABOR-BASED AUDIOVISUAL FUSION FOR MANDARIN CHINESE SPEECH RECOGNITION |
Yan Xu, Hongce Wang, Zhongping Dong, Yuexuan Li, Xi’an Jiaotong-Liverpool University, China; Andrew Abel, University Of Strathclyde, United Kingdom |
|