Martin Benjak

12 papers A 1B 1C 7Misc 1Journal 1Unranked 1
YearRankTypeTitle / Venue / Authors
2025 C conf
A Cross-Framework Study of Temporal Information Buffering Strategies for Learned Video Compression.
PCS
Kuan-Wei Ho, Yi-Hsin Chen, Martin Benjak, Jörn Ostermann, Wen-Hsiao Peng
2025 A conf
Conditional Residual Coding with Explicit-Implicit Temporal Buffering for Learned Video Compression.
ICME
Yi-Hsin Chen, Kuan-Wei Ho, Martin Benjak, Jörn Ostermann, Wen-Hsiao Peng
2025 Misc conf
Exploration of Sequence-wise Optimized Parameters for Low Complexity Enhancement Video Coding (LCEVC) on 4K Content.
ICASSP
Martin Benjak, Jörn Ostermann
2025 C conf
Progressive COOL-CHIC: Efficient Decoding for Dual-Resolution Images.
VCIP
Martin Benjak, Yi-Hsin Chen, Wen-Hsiao Peng, Jörn Ostermann
2025 C conf
Scalable COOL-CHIC: Dual-Resolution Images from a Single Bitstream.
PCS
Martin Benjak, Yi-Hsin Chen, Wen-Hsiao Peng, Jörn Ostermann
2024 J jnl
MaskCRT: Masked Conditional Residual Transformer for Learned Video Compression.
IEEE Trans. Circuits Syst. Video Technol.
Yi-Hsin Chen, Hong-Sheng Xie, Cheng-Wei Chen, Zong-Lin Gao, Martin Benjak, Wen-Hsiao Peng, Jörn Ostermann
2024 C conf
On the Rate-Distortion-Complexity Trade-Offs of Neural Video Coding.
MMSP
Yi-Hsin Chen, Kuan-Wei Ho, Martin Benjak, Jörn Ostermann, Wen-Hsiao Peng
2023 C conf
Learning-Based Scalable Video Coding with Spatial and Temporal Prediction.
VCIP
Martin Benjak, Yi-Hsin Chen, Wen-Hsiao Peng, Jörn Ostermann
2023 C conf
Rate Adaptation for Learned Two-layer B-frame Coding without Signaling Motion Information.
VCIP
Hong-Sheng Xie, Yi-Hsin Chen, Wen-Hsiao Peng, Martin Benjak, Jörn Ostermann
2022 C conf
Neural Network-based Error Concealment for B-Frames in VVC.
ISCAS
Martin Benjak, Niklas Aust, Yasser Samayoa, Jörn Ostermann
2021 — conf
Enhanced Machine Learning-based Inter Coding for VVC.
ICAIIC
Martin Benjak, Holger Meuel, Thorsten Laude, Jörn Ostermann
2021 B conf
Neural Network-Based Error Concealment For VVC.
ICIP
Martin Benjak, Yasser Samayoa, Jörn Ostermann