IVMSP-P5: Applications in Image and Video Processing III
Poster
Tue, 5 May, 14:00 - 16:00
Location: Poster Area 19
Session Type: Poster
Track: Image, Video and Multidimensional Signal Processing [IV]
Click the to view the manuscript on IEEE Xplore Open Preview

IVMSP-P5.1: Cross-View Change Detection via Self-Supervised Contrastive Representation Learning
Ghassen Graja, Polytechnic School of Tunisia, Tunisia; Olfa Besbes, ISSATSO, University of Sousse, Tunisia; Takoua Abdellatif, ENISO, University of Sousse, Tunisia

IVMSP-P5.2: UP TO 36X SPEEDUP: MASK-BASED PARALLEL INFERENCE PARADIGM FOR KEY INFORMATION EXTRACTION IN MLLMS
Xinzhong Wang, Shanghai Jiao Tong University, China; Ya Guo, Jing Li, Huan Chen, Yi Tu, Ant Group, China; Yijie Hong, Gongshen Liu, Shanghai Jiao Tong University, China; Huijia Zhu, Ant Group, China

IVMSP-P5.3: RSoRA: Spiking-Inspired Low-Rank Adaptation for Noise-Robust Vision Transformers
Guowei Peng, Yuning Yang, Qirong Yang, Xiurui Xie, Malu Zhang, University of Electronic Science and Technology of China, China

IVMSP-P5.4: ICNET: INPUT-GUIDED CALIBRATION NETWORK FOR HIGH-FIDELITY POINT CLOUD COMPLETION
Zhenyu Zhou, Zhuang Yang, Soochow University, China

IVMSP-P5.5: ATOMU: ARTIFICIAL TEMPLATE OF MARKER UNIT FOR 1/100-PIXEL ACCURACY DISPLACEMENT MEASUREMENT
Shien Ri, Jiaxing Ye, National Institute of Advanced Industrial Science and Technology, Japan

IVMSP-P5.6: HLF: A HIERARCHICAL LOCALIZATION FRAMEWORK FOR JOINT MOMENT RETRIEVAL AND HIGHLIGHT DETECTION
Tianyu Wang, Weize Quan, MAIS, Institute of Automation, CAS, Beijing, China, China; Yunzhen Zhao, Tencent, China; Jian Shi, Dong-Ming Yan, MAIS, Institute of Automation, CAS, Beijing, China, China

IVMSP-P5.7: INTRINSICGRID: GRID-BASED INTRINSIC DECOMPOSITION FOR FAST 3D SCENE RECONSTRUCTION
Zihang Zhang, Fumihiko Ino, The University of Osaka, Japan

IVMSP-P5.8: SPIKING TEMPORAL-ENHANCED NETWORK FOR ZERO-SHOT AUDIO-VISUAL LEARNING
Ziyu Wang, Wenrui Li, Hongtao Chen, Jisheng Chu, Hengyu Man, Xiaopeng Fan, Harbin Institute of Technology, China

IVMSP-P5.9: M 2 REG: UNSUPERVISED MULTI-SCALE REGISTRATION FOR MULTIMODAL MICROSCOPY
Xiaolong Wu, University of Science and Technology of China, China; Yinda Chen, Haiqun Jin, Ruobing Zhang, Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, China; Zhiwei Xiong, University of Science and Technology of China, China

IVMSP-P5.10: M2EA: MULTI-VAE MANIFOLD ENVELOPE ALIGNMENT FOR CHALLENGING AI-GENERATED IMAGE DETECTION
Ruiqi Liu, Institute of Automation, Chinese Academy of Sciences, China; Yi Han, Southwest University, School of Computer and Information Science, School of Software, China; Boyi Sun, Houxin He, Institute of Automation, Chinese Academy of Sciences, China; Yuxuan Zhou, Yan Wang, Tsinghua University, China