Gen Zhan

TL;DR: This paper reviews the challenge on constrained high dynamic range (HDR) imaging that was part of the New Trends in Image Restoration and Enhancement (NTIRE) workshop, held in conjunction with CVPR 2022, and the competition set-up, datasets, proposed methods and their results.

TL;DR: A sensitive object‐oriented regions of interest‐based coding strategy for preserving the analytical value of surveillance data by considering saliency as a set of characteristics important for object detection and recognition is proposed.

TL;DR: This paper qualitatively analyze the effect of video compression on the performance of video analysis, such as feature similarity and object detection, and proposes an analysis-oriented region of interest (ROI) based coding approach to relieve this problem.

TL;DR: A two-level segment-based rate control for ABR streaming is proposed, which properly allocate the bits to frames depend on their types and content complexity; while in the picture level, the proposed algorithm controls the encoded picture size close to the allocated size by an improved rate prediction model.

TL;DR: A criminal investigation attentive model CIAM is constructed to score the occurrence probabilities of CIAOs in spatial domain and novelly utilize score to represent saliency, thus making CIAO regions more salient than non-CIAO regions, and refine the spatial domain saliency map with the motion information in temporal domain to obtain the spatio-temporal saliencymap.