Technical Program
MMSP-L3: Multimodal Media Analysis |
Session Type: Lecture |
Time: Thursday, March 24, 13:30 - 15:30 |
Location: Room 3E |
Session Chairs: Fabrice Labeau, McGill University and Hsin-Min Wang, Academia Sinica |
MMSP-L3.1: EIGEN AND MULTIMODAL ANALYSIS FOR LOCALIZING MOVING SOUNDING OBJECTS |
Shreya Khare; Indian Institute of Technology Madras |
Akshay Bhandari; Indian Institute of Technology Madras |
Hema A. Murthy; Indian Institute of Technology Madras |
MMSP-L3.2: AGREEMENT AND DISAGREEMENT CLASSIFICATION OF DYADIC INTERACTIONS USING VOCAL AND GESTURAL CUES |
Hossein Khaki; Koç University |
Elif Bozkurt; Koç University |
Engin Erzin; Koç University |
MMSP-L3.3: LIGHTLY-SUPERVISED UTTERANCE-LEVEL EMOTION IDENTIFICATION USING LATENT TOPIC MODELING OF MULTIMODAL WORDS |
Zhaojun Yang; University of Southern California |
Shrikanth Narayanan; University of Southern California |
MMSP-L3.4: DEMV-MATCHMAKER: EMOTIONAL TEMPORAL COURSE REPRESENTATION AND DEEP SIMILARITY MATCHING FOR AUTOMATIC MUSIC VIDEO GENERATION |
Jen-Chun Lin; Academia Sinica |
Wen-Li Wei; Academia Sinica |
Hsin-Min Wang; Academia Sinica |
MMSP-L3.5: OPENING BIG IN BOX OFFICE? TRAILER CONTENT CAN HELP |
Adarsh Tadimari; Indian Institute of Technology Madras |
Naveen Kumar; University of Southern California |
Tanaya Guha; Indian Institute of Technology Kanpur |
Shrikanth S. Narayanan; University of Southern California |
MMSP-L3.6: WIFI ACTION RECOGNITION VIA VISION-BASED METHODS |
Jen-Yin Chang; National Taiwan University |
Kuan-Ying Lee; National Taiwan University |
Kate Ching-Ju Lin; Academia Sinica |
Winston Hsu; National Taiwan University |