Martin Benjak
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Martin Benjak has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
Cheng-Wei Chen
Department of Computer Science, National Yang Ming Chiao Tung University, Hsinchu, Taiwan
1 shared publicationHong-Sheng Xie
Department of Computer Science, National Yang Ming Chiao Tung University, Hsinchu, Taiwan
1 shared publicationJorn Ostermann
Leibniz Universität Hannover
1 shared publicationJörn Ostermann
Institut fr Informationsverarbeitung, Leibniz Universitt Hannover, Hannover, Germany
1 shared publication- Wen-Hsiao Peng
National yang Ming Chiao Tung University
1 shared publication - Yi-Hsin Chen
Department of Computer Science, National Yang Ming Chiao Tung University, Hsinchu, Taiwan
1 shared publication
Latest Publications
- 1 October 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 36 (10) , 14478-14490
LANCE: Locally Adaptive Neural Context Estimation for Overfitted Image Compression
- 1 October 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 36 (10) , 14478-14490
LANCE: Locally Adaptive Neural Context Estimation for Overfitted Image Compression
- 12 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 34 (11) , 11980-11992
MaskCRT: Masked Conditional Residual Transformer for Learned Video Compression
Conditional coding has lately emerged as the main-stream approach to learned video compression. However, a recent study shows that it may perform worse than residual coding when the information bottleneck arises. Conditional residual coding was thus proposed, creating a new school of thought to improve on conditional coding. Notably, conditional residual coding relies heavily on the assumption that the residual frame has a lower entropy rate than that of the intra frame. Recognizing that this assumption is not always true due to dis-occlusion phenomena or unreliable motion estimates, we propose a masked conditional residual coding scheme. It learns a soft mask to form a hybrid of conditional coding and conditional residual coding in a pixel adaptive manner. We introduce a Transformer-based conditional autoencoder. Several strategies are investigated with regard to how to condition a Transformer-based autoencoder for inter-frame coding, a topic that is largely under-explored. Additionally, we propose a channel transform module (CTM) to decorrelate the image latents along the channel dimension, with the aim of using the simple hyperprior to approach similar compression performance to the channel-wise autoregressive model. Experimental results confirm the superiority of our masked conditional residual transformer (termed MaskCRT) to both conditional coding and conditional residual coding. On commonly used datasets, MaskCRT shows comparable BD-rate results to VTM-17.0 under the low delay P configuration in terms of PSNR-RGB and outperforms VTM-17.0 in terms of MS-SSIM-RGB. It also opens up a new research direction for advancing learned video compression.
- 12 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 34 (11) , 11980-11992
MaskCRT: Masked Conditional Residual Transformer for Learned Video Compression
Conditional coding has lately emerged as the main-stream approach to learned video compression. However, a recent study shows that it may perform worse than residual coding when the information bottleneck arises. Conditional residual coding was thus proposed, creating a new school of thought to improve on conditional coding. Notably, conditional residual coding relies heavily on the assumption that the residual frame has a lower entropy rate than that of the intra frame. Recognizing that this assumption is not always true due to dis-occlusion phenomena or unreliable motion estimates, we propose a masked conditional residual coding scheme. It learns a soft mask to form a hybrid of conditional coding and conditional residual coding in a pixel adaptive manner. We introduce a Transformer-based conditional autoencoder. Several strategies are investigated with regard to how to condition a Transformer-based autoencoder for inter-frame coding, a topic that is largely under-explored. Additionally, we propose a channel transform module (CTM) to decorrelate the image latents along the channel dimension, with the aim of using the simple hyperprior to approach similar compression performance to the channel-wise autoregressive model. Experimental results confirm the superiority of our masked conditional residual transformer (termed MaskCRT) to both conditional coding and conditional residual coding. On commonly used datasets, MaskCRT shows comparable BD-rate results to VTM-17.0 under the low delay P configuration in terms of PSNR-RGB and outperforms VTM-17.0 in terms of MS-SSIM-RGB. It also opens up a new research direction for advancing learned video compression.