Zhibo Chen

TL;DR: Wang et al. as mentioned in this paper proposed an end-to-end video compression network for P-frame challenge on CLIC, which combines the advantages of both pixel-level and feature-level residual compression by model ensembling.

TL;DR: In this article, a learned fast intra coding (LFHI) framework is proposed, which takes into account the comprehensive factors of fast intra-coding to reach an improved configurable tradeoff between coding performance and computational complexity.

TL;DR: In this paper, a salience estimation method for object-based visual attention model is proposed, which comprises steps of segmenting the image into a plurality of objects to be estimated, extracting feature maps for each segmented object, calculating the saliences of each instance in a set of circles defined around a centre pixel of the object based on the extracted feature maps, and integrating the salience of each segmenting object in all circles in order to achieve an overall saliency estimation.

TL;DR: This work constructs an automatic processing scheme by combining the detection and location neural networks for the continuous records and applies the method into the field datasets, showing that the time window of a complete event can be detected effectively even though the CNN model is trained with a small number of samples.

TL;DR: The experimental results show that the proposed Quadrangle Affine Square Projection (QASP) method achieves noticeable improvement over traditional methods, and the proposed quality assessment method outperforms the traditional measurements in terms of consistency with subjective evaluation.