IVMSP-P22: Machine Learning for Image and Video Processing
Poster
Wed, 6 May, 14:00 - 16:00
Location: Poster Area 42
Session Type: Poster
Track: Image, Video and Multidimensional Signal Processing [IV]
Click the to view the manuscript on IEEE Xplore Open Preview

IVMSP-P22.1: CLIP-Guided Unsupervised Semantic-Aware Exposure Correction
Puzhen Wu, Chinese Academy of Sciences, China; Han Weng, University College Dublin, Ireland; Quan Zheng, Chinese Academy of Sciences, China; Yi Zhan, Peking University, China; Hewei Wang, Yiming Li, Jiahui Han, University College Dublin, Ireland; Rui Xu, Peking University, China

IVMSP-P22.2: ForkNet: Direction-Aware and Wavelet-Guided Dual-Encoder Network for Image Fusion
Xiaoxiao Yan, China University of Geosciences, Wuhan 430074, China, China; Zuheng Wang, China Mobile Group Design Institute Co., Ltd., Beijing 100089, China, China; Yun Shuai, Jun Hu, China University of Geosciences, Wuhan 430074, China, China; Zhihao Deng, Gandong University, Fuzhou 344000, China, China; Guanyu Chen, Quanyu Wang, China University of Geosciences, Wuhan 430074, China, China

IVMSP-P22.3: GMAMBAFLOW: GLOBAL-AWARE MAMBA BASED COST VOLUME AGGREGATION FOR OPTICAL FLOW
Yuhao Yang, Yining Miao, Wenming Yang, Tsinghua University, China

IVMSP-P22.4: A Dynamic Dual-Backbone Model for Adaptive Vehicle-Pedestrian Detection
Wenbo Liu, Haoran Liu, Chunyu Zhao, Tao Deng, Fei Yan, Southwest Jiaotong University, China

IVMSP-P22.5: IGCNet: Dual-Branch Implicit Feature and Global Context Network for Agricultural Parcel Delineation
Ye Li, Liruizhi Jia, Chao Liu, Kong Bo, Yuan Liu, Shengquan Liu, Xinjiang University, China

IVMSP-P22.6: ASTMNET: ADAPTIVE SPECTRAL TOKEN MIXER WITH SELECTIVE FEATURE ENHANCEMENT FOR PANSHARPENING
Meng Xu, Jiayou Mao, Ziqian Mo, Yuxi Sun, Shenzhen University, China

IVMSP-P22.7: IESGN-OCC: An Instance-Enhanced Sparse Guidance Network for Vision-based Occupancy Prediction
Biao Xu, Northeastern University, China; Zuotao Ning, Neusoft Reach Automotive Technology (Shenyang) Co., Ltd., China; Wei Liu, Northeastern University, China

IVMSP-P22.8: QP-SAM: Query-based Prompt Generation for Segment Anything Model in Urban Village Identification
Xinyuan Guo, Huijie Zhang, Northeast Normal University, China

IVMSP-P22.9: Classifier-Centric Adaptive Framework for Open-Vocabulary Camouflaged Object Segmentation
Hanyu Zhang, Yiming Zhou, Jinxia Zhang, Southeast University, China

IVMSP-P22.10: CLASS DIFFICULTY-AWARE REAL-TIME INSTANCE SEGMENTATION
Yaochi Zhao, Liujun Zhou, He Zhang, Fan Tong, Zhuhua Hu, Hainan University, China

IVMSP-P22.11: STABILIZING RED USING THE KOOPMAN OPERATOR
Shraddha Chavan, Kunal N. Chaudhury, Indian Institute of Science, Bengaluru, India, India

IVMSP-P22.12: Tuning-Free Online Robust Principal Component Analysis through Implicit Regularization
Lakshmi Jayalal, IIT Madras, India; Gokularam Muthukrishnan, India Urban Data Exchange, India; Sheetal Kalyani, IIT Madras, India

IVMSP-P22.13: A BENCHMARK DATASET AND BASELINE FRAMEWORK FOR ACTION RECOGNITION IN POWER CONSTRUCTION SAFETY
Shuo Zhang, Xiaoqing Zheng, Weibin Zhang, Yaguang Kong, Hangzhou Dianzi University, China

IVMSP-P22.14: MULTI-VIEW CROWD COUNTING WITH SELF-SUPERVISED LEARNING
Hong Mo, Hubei University of Arts and Science, China; Xiong Zhang, Neolix Autonomous Vehicle, China; Tengfei Shi, Zhongbo Wu, Hubei University of Arts and Science, China

IVMSP-P22.15: ADVERSE EFFECT REMOVAL NETWORK VIA UNSUPERVISED WEATHER TYPE TRANSFER
Yunyi Tang, Bowei Fang, Chunyu Zhao, Haoran Liu, Fei Yan, Tao Deng, Southwest Jiaotong University, China

IVMSP-P22.16: HCTPOSE: HYBRID CNN-TRANSFORMER NETWORK FOR SELF-SUPERVISED MULTI-VIEW 3D HUMAN POSE ESTIMATION
Jucheng Song, Xu Yang, Yapeng Wang, Jie Zhang, Sio-Kei Im, Macao Polytechnic University, China