IVMSP-L15: Multi-modal / Cross-modal Image and Video Processing
Oral
Fri, 8 May, 09:00 - 11:00
Location: Room 120+121
Session Type: Oral
Track: Image, Video and Multidimensional Signal Processing [IV]
Click the to view the manuscript on IEEE Xplore Open Preview
Fri, 8 May, 09:00 - 09:20

IVMSP-L15.1: GRNet: Graph Reconstruction Network for Robust Multimodal Sentiment Analysis
Zhaopan Xu, Lulu Tian, Harbin Institute of Technology, China; Panpan Zhang, National University of Singapore, Singapore; Xiaojiang Peng, Shenzhen Technology University, China; Hongxun Yao, Harbin Institute of Technology, China
Fri, 8 May, 09:20 - 09:40

IVMSP-L15.2: FEFusionMap:A LiDAR-Camera Fused Semantic Map Generation Frame Via Multi-modal Feature Enhancement
Tao Zhang, Baoqi Huang, Bing Jia, Lifei Hao, Inner Mongolia university, China
Fri, 8 May, 09:40 - 10:00

IVMSP-L15.3: DEMONET: DEGRADATION-AWARE MODALITY INTERACTION FOR MULTI-MODAL OBJECT DETECTION IN CAR CABIN
Yiming Li, Tianyi Liu, Kim-Hui Yap, Nanyang Technological University, Singapore
Fri, 8 May, 10:00 - 10:20

IVMSP-L15.4: PROMPTMAD: CROSS-MODAL PROMPTING FOR MULTI-CLASS VISUAL ANOMALY LOCALIZATION
Duncan McCain, Hossein Kashiani, Fatemeh Afghah, Clemson University, United States of America
Fri, 8 May, 10:20 - 10:40

IVMSP-L15.5: Mouthing-Enhanced Multimodal Hierarchical Contrastive Learning for Gloss-Free Sign Language Translation
Wenfang Wu, University of Göttingen, Germany; Tingting Yuan, IMC University of Applied Sciences Krems, Austria; Yupeng Li, Hong Kong Baptist University, China; Daling Wang, Northeastern University, China; Xiaoming Fu, University of Göttingen, Germany
Fri, 8 May, 10:40 - 11:00

IVMSP-L15.6: MFM-DETR: MISALIGNMENT-FREE MULTIMODAL DETR FOR MARITIME OBJECT DETECTION
Meng Xu, Hongtao Zhang, Shuyu Zhang, Sen Jia, Shenzhen University, China