Marc Windsheimer, M.Sc.
I am engaged in the development of deep learning methods for image and video coding. The main focus is on machine communication, where the decoded results are evaluated by deep neural networks, e.g. Mask R-CNN. At the same time, however, a human observer should be able to understand the decision of the evaluation network. The goal is to maintain the accuracy of the detection networks while minimizing the required data rate.
Further information can be found at the following link:
Learned Image Compression for Emotion Classification
Thesis in the area of video coding for object detection
RDONet: Rate-Distortion Optimized Learned Image Compression with Variable Depth
2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2022 (New Orleans, LA, USA, 19. June 2022 - 20. June 2022)
In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops 2022
, , , , :
RDONet: Rate-Distortion Optimized Learned Image Compression With Variable Depth
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops (New Orleans, 19. June 2022 - 23. June 2022)
, , , , :