TA1.L2.3
Progressive Learning with Visual Prompt Tuning for Variable-Rate Image Compression
Shiyu Qin, Tsinghua Shenzhen International Graduate School, Tsinghua University, China; Yimin Zhou, Harbin Institute of Technology, Shenzhen, China; Jinpeng Wang, Tsinghua Shenzhen International Graduate School, Tsinghua University, China; Bin Chen, Harbin Institute of Technology, Shenzhen; Peng Cheng Laboratory; Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies, China; Baoyi An, Huawei Technologies Company Ltd, China; Tao Dai, Shenzhen University, China; Shutao Xia, Tsinghua Shenzhen International Graduate School, Tsinghua University, China
Session:
TA1.L2: Neural Image and Video Compression - I Lecture
Track:
Image and Video Communications
Location:
Capital Suite - 16
Presentation Time:
Tue, 29 Oct, 09:06 - 09:24 Gulf Standard Time (UTC +4)
Session Chair:
Elena Alshina, Huawei Munich Research Center
Session TA1.L2
TA1.L2.1: EFFICIENT LEARNED WAVELET IMAGE AND VIDEO CODING
Anna Meyer, Friedrich-Alexander-University Erlangen-Nürnberg, Germany; Srivatsa Prativadibhayankaram, Fraunhofer Institute for Integrated Circuits, Germany; André Kaup, Friedrich-Alexander-University Erlangen-Nürnberg, Germany
TA1.L2.2: MOTION-ADAPTIVE INFERENCE FOR FLEXIBLE LEARNED B-FRAME COMPRESSION
MUSTAFA AKIN YILMAZ, Codeway Studios, Türkiye; OKKES UGUR ULAS, AHMET BILICAN, AHMET MURAT TEKALP, Koc University, Türkiye
TA1.L2.3: Progressive Learning with Visual Prompt Tuning for Variable-Rate Image Compression
Shiyu Qin, Tsinghua Shenzhen International Graduate School, Tsinghua University, China; Yimin Zhou, Harbin Institute of Technology, Shenzhen, China; Jinpeng Wang, Tsinghua Shenzhen International Graduate School, Tsinghua University, China; Bin Chen, Harbin Institute of Technology, Shenzhen; Peng Cheng Laboratory; Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies, China; Baoyi An, Huawei Technologies Company Ltd, China; Tao Dai, Shenzhen University, China; Shutao Xia, Tsinghua Shenzhen International Graduate School, Tsinghua University, China
TA1.L2.4: ADAPTING LEARNED IMAGE CODECS TO SCREEN CONTENT VIA ADJUSTABLE TRANSFORMATIONS
Hasan Burak Dogaroglu, Ahmet Burakhan Koyuncu, Technical University of Munich, Germany; Atanas Boev, Elena Alshina, Huawei Munich Research Center, Germany; Eckehard Steinbach, Technical University of Munich, Germany
TA1.L2.5: End-to-End Learned Scalable Multilayer Feature Compression for Machine Vision Tasks
Qiaoxi Chen, Changsheng Gao, Dong Liu, University of Science and Technology of China, China
Contacts