Technical Program

MMSP-L1: Multimodal Signal Processing I

Session Type: Lecture
Time: Thursday, May 16, 08:00 - 10:00
Location: Syndicate 4
Session Chair: Andrea Cavallaro, Queen Mary University of London
 
MMSP-L1.1: ACCURATE TARGET ANNOTATION IN 3D FROM MULTIMODAL STREAMS
Manuscript Link:  Click here to view manuscript on IEEE Xplore
         Oswald Lanz; Fondazione Bruno Kessler
         Alessio Brutti; Fondazione Bruno Kessler
         Alessio Xompero; Queen Mary University of London
         Xinyuan Qian; Queen Mary University of London
         Maurizio Omologo; Fondazione Bruno Kessler
         Andrea Cavallaro; Queen Mary University of London
 
MMSP-L1.2: MULTI-FEATURE FUSION BASED ON SUPERVISED MULTI-VIEW MULTI-LABEL CANONICAL CORRELATION PROJECTION
Manuscript Link:  Click here to view manuscript on IEEE Xplore
         Keisuke Maeda; Hokkaido University
         Sho Takahashi; Hokkaido University
         Takahiro Ogawa; Hokkaido University
         Miki Haseyama; Hokkaido University
 
MMSP-L1.3: DENSE MULTIMODAL FUSION FOR HIERARCHICALLY JOINT REPRESENTATION
Manuscript Link:  Click here to view manuscript on IEEE Xplore
         Di Hu; Northwestern Polytechnical University
         Chengze Wang; Northwestern Polytechnical University
         Feiping Nie; Northwestern Polytechnical University
         Xuelong Li; Northwestern Polytechnical University
 
MMSP-L1.4: CONTEXT-AWARE DEEP LEARNING FOR MULTI-MODAL DEPRESSION DETECTION
Manuscript Link:  Click here to view manuscript on IEEE Xplore
         Genevieve Wen Qi Lam; Nanyang Technological University
         Dong-Yan Huang; Institute for Infocomm Research
         Weisi Lin; Nanyang Technological University
 
MMSP-L1.5: LEARNING SHARED VECTOR REPRESENTATIONS OF LYRICS AND CHORDS IN MUSIC
Manuscript Link:  Click here to view manuscript on IEEE Xplore
         Timothy Greer; University of Southern California
         Karan Singla; University of Southern California
         Benjamin Ma; University of Southern California
         Shrikanth Narayanan; University of Southern California
 
MMSP-L1.6: AUDIO FEATURE GENERATION FOR MISSING MODALITY PROBLEM IN VIDEO ACTION RECOGNITION
Manuscript Link:  Click here to view manuscript on IEEE Xplore
         Hu-Cheng Lee; National Taiwan University
         Chih-Yu Lin; National Taiwan University
         Pin-Chun Hsu; National Taiwan University
         Winston H. Hsu; National Taiwan University