top of page
TV Screens

Intelligent Media Processing Lab

知能メディア処理

Our lab focuses on the algorithms and VLSI architectures for multimedia signal processing. 1) We deal with measurement coding algorithms for compressively sensed visual contents to realize a batteryless video acquisition system.  2) We develop the techniques to realize low-power high-performance VLSI design for video codecs including H.265/HEVC and H.264/AVC. 3) We do research on the machine learning technologies for image/video processing.

​ News

  • 2024    Cheng's paper "DE-MKD: Decoupled Multi-Teacher Knowledge Distillation Based on Entropy". is accepted by Mathematics. (IF2022: 2.3)

  • 2024 Cheng's paper "An Analytical GPU-enabled Framework for the Stacked 3-D IC Layouts". is accepted by the Journal of Circuits, Systems and Computers. (IF2022:1.5)

  • 2024 Shirai's paper "Learned Measurement Interpolation for Scalable Compressive Sensing"is accepted by IJCNN 2024.

  • 2024 Kimishima's paper "High Frequency Feature Distillation Network for Compressive Sensing Reconstruction". is accepted by IJCNN 2024.

  • 2024 Morita's paper "Edge-based Denoising Image Compression". is accepted by European Signal Processing Conference(EUSIPC) 2024.

  • 2024/03 Information for B3 students is updated [Link]

  • 2024 Yang's paper "JVCSR+: Adaptively Learned Video Compressive Sensing Reconstruction with Joint In-loop Reference Enhancement and Out-loop Super-resolution." is accepted by Computational Visual Media2024 (IF2023: 6.9).  

  • 2024 Jinjia's paper "Compressive Sensing in Image/Video Compression: Sampling, Coding, Reconstruction, and Codec Optimization" is accepted by Information 15.2 (2024) (IF2023: 3.1).

  • 2024/1 Jian Yang's paper "ASAUN-CS: Adaptive Stage Activated Unfolding Network for Compressive Sensing" is accepted by ISCAS2024.

  • 2024/1 Cheng's paper "Decoupled Multi-teacher Knowledge Distillation based on Entropy" is accepted by ISCAS2024.

  • 2024/1 Miyamoto's paper "Visual question answering based evaluation metrics for text-to-image generation" is accepted by ISCAS2024.

  • 2024/1 Matano's paper "An Iterative Image Inpainting Method Using Mask Shrinking" is accepted by ISCAS2024.

  • 2024 Hayashi's paper "RPCS v2.0: Object-Detection-Based Recurrent Point Cloud Selection Method for 3D Dense Captioning" is accepted by Neurocomputing 2024 (Impact Factor: 6).

  • 2023 Yang's paper "aVCSR: Adaptive Video Compressive Sensing using Region-of-Interest Detection in the Compressed Domain" is accepted by IEEE MultiMedia,  (IF2022: 3.2).

  • 2023/12 Fu's paper "Dynamic Talking-Head Generation with Speech Emotion Recognition and Intensity Detection" is accepted by CECNet 2023.

  • 2023 Jiayao Xu's paper "Compressive Sensing based Image Codec with Partial Pre-calculation" is accepted by IEEE Transactions on Multimedia, (IF 8.182).

  • 2023/12 Iwama's paper "Block based Adaptive Compressive Sensing with Sampling Rate Control" is accepted by ACM MM Asia.

  • 2023/12 Wang's paper "NuclSeg: nuclei segmentation using semi-supervised stain deconvolution" is accepted by ACM MM Asia.

  • 2023/08 Zhang's paper "TCGIS: Text and Contour Guided controllable Image Synthesis" is accepted by ACM MM Workshop McGE 2023.

  • 2023/08 Morita's paper "BATINet: Background-aware Text to Image Synthesis and Manipulation Network" is accepted by ICIP2023.

  • 2023/08 Zhang's paper "Dynamic Unilateral Dual Learning for Text to Image Synthesis" is accepted by ICIP2023.

  • 2023 Fu's paper "A Highly Pipelined and Highly Parallel VLSI Architecture of CABAC Encoder for UHDTV Applications" is accepted by Sensors 2023 (IF2021: 3.847).

  • 2023/03 Information for B3 students is updated [Link]

  • 2022/03 Our lab is introduced by JST [Link]

  • 2022/12 Yang's paper "VCSL: Video Compressive Sensing with Low-complexity ROI Detection in Compressed Domain" is accepted by DCC2023.

  • 2022/12 Keren's paper "Temporal Down-sampling based Video Coding with Frame-Recurrent Enhancement" is accepted by DCC2023.

  • 2022/12 Jinyao's paper "Zigzag Ordered Walsh for Compressed Sensing Image Sensor" is accepted by DCC2023.

  • 2022/11 Morita's paper "Interactive Image Manipulation with Complex Text Instructions" is accepted by WACV2023.

  • 2022/09 Hayashi's paper "HA Recurrent Point Clouds Selection Method for 3D Dense Captioning" is accepted by ICONIP2022.

  • 2022/09 Wang's paper "Hierarchical down-sampling based ultra high-resolution image inpainting" is accepted by ICONIP2022.

  • 2022/08 Catherine's paper "Object detection and tracking aided SLAM in image sequences for dynamic environment" is accepted by MMSP2022.

  • 2022/08  Fu's paper "Optimizing CABAC architecture with prediction based context model prefetching" is accepted by MMSP2022.

  • 2022/07  Zein's paper "Collaborative Multiple-Student Single-Teacher for Online Learning" is accepted by ICANN2022.

  • 2022/06  Zhiqiang's paper "Text-to-Image Synthesis: Starting Composite from the Foreground Content" is accepted by Information Sciences.

  • 2022/05  Hayashi's paper "Improving descriptive deficiencies with a Random Selection Loop for 3D Dense Captioning based on Point Clouds" is accepted by CVPRW VizWiz 2022.

  • 2022/03 Information for B3 students is updated [Link]

  • 2021/11  Jiayao's paper "Real-time FPGA Design for OMP Targeting 8K Image Reconstruction" is accepted by MMM2022.

  • 2021/11  Yang's paper "JVCSR: Video Compressive Sensing Reconstruction with Joint In-loop Reference Enhancement and Out-loop Super-resolution" is accepted by MMM2022.

  • 2021/07  Ho's paper "SpeedDeblur: A Framework to speed up CNN-based Deblurring for HEVC compressed video" is accepted by MMSP2021.

  • 2021/03 Zhiqiang's paper "Text to Image Synthesis based on Multi-Perspective Fusion" is accepted by IJCNN2021.

  • 2021/03 Chi's paper "Deep Learning based Spatial-Temporal In-loop filtering for Versatile Video Coding" is accepted by CVPRW CLIC 2021

  • 2021/03 Information for B3 students is updated [Link]

  • 2021/03 Our lab is introduced by Hosei HP [Link]

  • 2021/03 Zhiqiang's paper "DrawGAN: Text to Image Synthesis with Drawing Generative Adversarial Networks", and Rentao's paper "Measurement Coding Framework with Adjacent Pixels based Measurement Matrix for Compressively Sensed Images" are accepted by ICASSP2021.

  • 2021/01 Man M. Ho's paper "RR-DnCNN v2.0: Enhanced Restoration-Reconstruction Deep Neural Network for Down-Sampling Based Video Coding" is accpeted by IEEE Transactions on Image Processing (TIP).

  • 2021/01 Man M. Ho's paper "Deep Preset: Blending and Retouching Photos with Color Style Transfer" is accepted by WACV2021.

  • 2021/01 Qirui's paper "DRMS: Dim-light Robust Monocular Simultaneous Localization and Mapping" won the ICCCR2021 Best presentation award

  • 2020/11 Bowen's paper "CS-MCNet: A Video Compressive Sensing Reconstruction Network with Interpretable Motion Compensation" is accepted by ACCV2020.

  • 2020/10 Zhiqiang's paper "Customizable GAN: customizable image synthesis based on adversarial learning" is accepted by ICONIP2020.

  • 2020/09 Thuy's paper "Bi-directional intra prediction based measurement coding for compressive sensing images" is accepted by MMSP2020

  • 2020/08 Jiayao's paper "High-speed Compressed Sensing Reconstruction using Zigzag Ordering based Parallel Processing" win the ICIVP2020 Best presentation award 

  • 2020/04 Trinh M. Hoang's paper “Image Compression with Encoder-Decoder Matched Semantic Segmentation,” and Man M. Ho's paper "SR-CL-DMC: P-frame coding with Super-Resolution, Color Learning, and Deep Motion Compensation" are accepted by 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

  • 2020/01 ​​Man M. Ho's paper "Down-Sampling Based Video Coding with Degradation-aware Restoration-Reconstruction Deep Neural Network" win the MMM2020 Best Paper Runner-Up Award

  • 2019/12 Jiaryu's paper "Temporal Redundancy Reduction in Compressive Video Sensing by using Moving Detection and Inter-Coding," is accepted by DCC2020

  • 2019/10 Man M. Ho's paper "Respecting low-level components of content with skip connections and semantic information in image style transfer," is accepted by ACM SIGGRAPH CVMP2019

  • 2019/08 Trinh M. Hoang's paper “B-DRRN: A Block Information Constrained Deep Recursive Residual Network for Video Compression Artifacts Reduction,” is accepted by PCS2019

  • 2019/08 Pham.D.Chi's paper "Deep Learning-based Luma and Chroma Fractional Interpolation in Video Coding" is accepted by IEEE Access

  • 2018/12 Jiaryu's paper "A Measurement Coding System for Block-based Compressive Sensing Images by Using Pixel-Domain Features" is accepted by DCC2019

 
 
 
 
 
IMG_8311.jpg
bottom of page