MLSP-P47: Generative Models for Multimodal Signal Processing I
Poster
Thu, 7 May, 09:00 - 11:00
Location: Poster Area 7
Session Type: Poster
Track: Machine Learning for Signal Processing [ML]
Click the to view the manuscript on IEEE Xplore Open Preview

MLSP-P47.1: TEXTS-Diff: TEXTS-Aware Diffusion Model for Real-World Text Image Super-Resolution
Haodong He, Xin Zhan, Yancheng Bai, Rui Lan, Lei Sun, Xiangxiang Chu, Amap, Alibaba Group, China

MLSP-P47.2: MaskDiff-Traj: A UNIFIED TRAJECTORY IMPUTATION AND GENERATION FRAMEWORK VIA PATTERN-GUIDED MASKED DIFFUSION
Chao Zhang, Yang Zhang, Ziyi Wang, Yuanxi Peng, Xueqiong Li, Shaowu Yang, College of Computer Science and Technology, National University of Defense Technology, China

MLSP-P47.3: EXTREMOPROMPT: ADVANCING MIXTURE OF SOFT PROMPTS TO THE LIMIT
Shaojian Qiu, Haiyang Liu, SCAU, China; Zeyu Wang, HIT, China; Shunpeng Li, Yun Liang, SCAU, China

MLSP-P47.4: PMMD: A POSE-GUIDED MULTI-VIEW MULTI-MODAL DIFFUSION FOR PERSON GENERATION
Ziyu Shang, Harbin Institute of Technology, Shenzhen, China; Haoran Liu, The Chinese University of Hong Kong, Shenzhen, China; Rongchao Zhang, Peking University, China; Zhiqian Wei, City University of Hong Kong, China; Tongtong Feng, Tsinghua University, China

MLSP-P47.5: Dynamic Semantic Path Routing with Learnable Priors for Image Captioning
Wenjing Li, Jiong Yu, School of Computer Science and Technology, Xinjiang University, China; Xue Li, Ziyang Li, Xin Wang, School of Software, Xinjiang University,China, China

MLSP-P47.6: ENHANCING POST-TRAINING QUANTIZATION VIA FUTURE ACTIVATION AWARENESS
Zheqi Lv, Zhenxuan Fan, Zhejiang University, China; Qi Tian, Zhejiang University, Tencent, China; Wenqiao Zhang, Yueting Zhuang, Zhejiang University, China

MLSP-P47.7: SCORENF: SCORE-BASED NORMALIZING FLOWS FOR SAMPLING UNNORMALIZED DISTRIBUTIONS
Vikas Kanaujia, IIT Kanpur, India; Vipul Arora, IIT Kanpur, KU Leuven, Belgium

MLSP-P47.8: CMCFAE: CLOUD MODEL CHARACTERISTIC FUNCTION AUTO-ENCODER FOR STRUCTURE-AWARE GENERATIVE MODELING
Biao Hu, Guoyin Wang, Chongqing University of Posts and Telecommunications, China

MLSP-P47.9: TOWARDS SEMANTICALLY FAITHFUL TEXT-TO-TIME SERIES GENERATION VIA AGENTS AND SPECTRAL CONDITIONING
Wu Ziwei, Lu Lina, Zheng Caiming, Liu Yirui, Zhang Wanpeng, National University of Defense Technology, China

MLSP-P47.10: VMSP: Video-to-Music Generation with Two-Stage Alignment and Synthesis
Xin Gu, Wei Jiang, Yujian Jiang, Zhibin Su, Ming Yan, Communication University of China, China