IEEE ICASSP 2022

2022 IEEE International Conference on Acoustics, Speech and Signal Processing

7-13 May 2022
  • Virtual (all paper presentations)
22-27 May 2022
  • Main Venue: Marina Bay Sands Expo & Convention Center, Singapore
27-28 October 2022
  • Satellite Venue: Crowne Plaza Shenzhen Longgang City Centre, Shenzhen, China

ICASSP 2022
IVMSP-5: Image and Video Synthesis
Sun, 8 May, 22:00 - 22:45 China Time (UTC +8)
Sun, 8 May, 14:00 - 14:45 UTC
Location: Gather Area I
Session Chair: Yi Zhou, National University of Singapore
Track: Image, Video, and Multidimensional Signal Processing

IVMSP-5.1: REALISTIC MONOCULAR-TO-3D VIRTUAL TRY-ON VIA MULTI-SCALE CHARACTERISTICS CAPTURE
Chenghu Du, Feng Yu, Minghua Jiang, Yaxin Zhao, Xiong Wei, Tao Peng, Xinrong Hu, Wuhan Textile University, China

IVMSP-5.2: Optimizing Latent Space Directions For GAN-based Local Image Editing
Ehsan Pajouheshgar, Tong Zhang, Sabine Süsstrunk, EPFL, Switzerland

IVMSP-5.3: Towards Using Clothes Style Transfer for Scenario-aware Person Video Generation
Jingning Xu, School of Software Engineering, Tongji University, Shanghai, China, China; Benlai Tang, Wenyi Guo, Xiang Yin, Zejun Ma, ByteDance AI Lab, China; Mingjie Wang, School of Computer Science, University of Guelph, ON, Canada, Canada; Siyuan Bian, Department of Computer Science and Engineering, Shanghai Jiao Tong University, China, China

IVMSP-5.4: MULTI-DOMAIN UNSUPERVISED IMAGE-TO-IMAGE TRANSLATION WITH APPEARANCE ADAPTIVE CONVOLUTION
Somi Jeong, NAVER LABS, Korea, Republic of; Jiyoung Lee, NAVER AI Lab, Korea, Republic of; Kwanghoon Sohn, Yonsei University, Korea, Republic of

IVMSP-5.5: VR-FAM: VARIANCE-REDUCED ENCODER WITH NONLINEAR TRANSFORMATION FOR FACIAL ATTRIBUTE MANIPULATION
Yifan Yuan, Siteng Ma, Junping Zhang, Fudan University, China

IVMSP-5.6: WAVELET-BASED UNSUPERVISED LABEL-TO-IMAGE TRANSLATION
George Eskandar, Mohamed Abdelsamad, Karim Armanious, Shuai Zhang, Bin Yang, University of Stuttgart, Germany