IVMSP-L1.5
CHNERV: CONDITION ENHANCED HYBRID NEURAL REPRESENTATION FOR VIDEOS
Tiange Zhang, Peking University Shenzhen Graduate School; Pengcheng Laboratory; National Engineering Research Center of Visual Technology, School of Computer Science, Peking University, China; Haofeng Wang, Peking University Shenzhen Graduate School; National Engineering Research Center of Visual Technology, School of Computer Science, Peking University, China; Xiandong Meng, Pengcheng Laboratory, China; Kai Zhang, Bytedance Inc, United States of America; Xuan Deng, Pengcheng Laboratory; Harbin Institute of Technology, China; Zhimeng Huang, National Engineering Research Center of Visual Technology, School of Computer Science, Peking University, China; Siwei Ma, Peking University Shenzhen Graduate School; Pengcheng Laboratory; National Engineering Research Center of Visual Technology, School of Computer Science, Peking University, China
Session:
IVMSP-L1: Image and Video Coding Oral
Track:
Image, Video and Multidimensional Signal Processing [IV]
Location:
Room 118+119
Presentation Time:
Tue, 5 May, 15:20 - 15:40
Presentation
Discussion
Resources
No resources available.
Session IVMSP-L1
IVMSP-L1.1: OPTIMIZED PARTITIONING ACCELERATION FOR VVC INTER CODING
Tianyi Sun, Yanze Wang, Yuedi Chen, Runkai Chen, Jun Sun, Peking University, China
IVMSP-L1.2: HyperCool: Reducing Encoding Cost in Overfitted Codecs with Hypernetworks
Pep Borrell-Tatché, Till Aczel, ETH Zurich, Switzerland; Théo Ladune, Orange Research, France; Roger Wattenhofer, ETH Zurich, Switzerland
IVMSP-L1.3: STDLC: Video Coding for Machines with Spatial-Temporal Decoupled Latent Composition
Chun Zhang, Waseda University, Japan; Heming Sun, Yokohama National University, Japan; Jiro Katto, Waseda University, Japan
IVMSP-L1.4: Interpolation-Aware Bitrate Ladder Optimization for Variable Framerate Video Streaming
Amritha Premkumar, Christian Herglotz, Brandenburg University of Technology Cottbus-Senftenberg, Germany
IVMSP-L1.5: CHNERV: CONDITION ENHANCED HYBRID NEURAL REPRESENTATION FOR VIDEOS
Tiange Zhang, Peking University Shenzhen Graduate School; Pengcheng Laboratory; National Engineering Research Center of Visual Technology, School of Computer Science, Peking University, China; Haofeng Wang, Peking University Shenzhen Graduate School; National Engineering Research Center of Visual Technology, School of Computer Science, Peking University, China; Xiandong Meng, Pengcheng Laboratory, China; Kai Zhang, Bytedance Inc, United States of America; Xuan Deng, Pengcheng Laboratory; Harbin Institute of Technology, China; Zhimeng Huang, National Engineering Research Center of Visual Technology, School of Computer Science, Peking University, China; Siwei Ma, Peking University Shenzhen Graduate School; Pengcheng Laboratory; National Engineering Research Center of Visual Technology, School of Computer Science, Peking University, China
IVMSP-L1.6: FC-FORMER: EFFICIENT FEATURE CODING FOR MACHINES VIA A HYBRID CNN-TRANSFORMER ARCHITECTURE
Zhengyuan Liu, Zifu Zhang, Shengxi Li, Tao Xu, Mai Xu, Xin Deng, Lai Jiang, Beihang university, China
Contacts