Image semantic segmentation is more and more being of interest for computer vision and machine learning researchers. Many applications on the rise need accurate and efficient segmentation mechanisms: autonomous driving, indoor navigation, and even virtual or augmented reality systems to name a few. This demand coincides with the rise of deep learning approaches in almost every field or application target related to computer vision, including semantic segmentation or scene understanding. This paper provides a review on deep learning methods for semantic segmentation applied to various application areas. Firstly, we describe the terminology of this field as well as mandatory background concepts. Next, the main datasets and challenges are exposed to help researchers decide which are the ones that best suit their needs and their targets. Then, existing methods are reviewed, highlighting their contributions and their significance in the field. Finally, quantitative results are given for the described methods and the datasets in which they were evaluated, following up with a discussion of the results. At last, we point out a set of promising future works and draw our own conclusions about the state of the art of semantic segmentation using deep learning techniques.

The ability to predict, anticipate and reason about future outcomes is a key component of intelligent decision-making systems. In light of the success of deep learning in computer vision, deep-learning-based video prediction emerged as a promising research direction. Defined as a self-supervised learning task, video prediction represents a suitable framework for representation learning, as it demonstrated potential capabilities for extracting meaningful representations of the underlying patterns in natural videos. Motivated by the increasing interest in this task, we provide a review on the deep learning methods for prediction in video sequences. We firstly define the video prediction fundamentals, as well as mandatory background concepts and the most used datasets. Next, we carefully analyze existing video prediction models organized according to a proposed taxonomy, highlighting their contributions and their significance in the field. The summary of the datasets and methods is accompanied with experimental results that facilitate the assessment of the state of the art on a quantitative basis. The paper is summarized by drawing some general conclusions, identifying open research challenges and by pointing out future research directions.

No abstract

Genomic diversity among melanoma tumors limits durable control with conventional and targeted therapies. Nevertheless, pathological activation of the ERK1/2 pathway is a linchpin tumorigenic mechanism associated with the majority of primary and recurrent disease. Therefore, we sought to identify therapeutic targets that are selectively required for tumorigenicity in the presence of pathological ERK1/2 signaling. By integration of multi-genome chemical and genetic screens; recurrent architectural variants in melanoma tumor genomes; and patient outcome data; we identified 2 mechanistic subtypes of BRAF(V600) melanoma that inform new cancer cell biology and offer new therapeutic opportunities. Subtype membership defines sensitivity to clinical MEK inhibitors versus TBK1/IKBKE inhibitors. Importantly, subtype membership can be predicted using a robust quantitative 5-feature genetic biomarker. This biomarker, and the mechanistic relationships linked to it, can identify a cohort of best responders to clinical MEK inhibitors and identify a cohort of TBK1/IKBKE inhibitor-sensitive disease among non-responders to current targeted therapy.

The optimal selection of chemical features (molecular descriptors) is an essential pre-processing step for the efficient application of computational intelligence techniques in virtual screening for identification of bioactive molecules in drug discovery. The selection of molecular descriptors has key influence in the accuracy of affinity prediction. In order to improve this prediction, we examined a Random Forest (RF)-based approach to automatically select molecular descriptors of training data for ligands of kinases, nuclear hormone receptors, and other enzymes. The reduction of features to use during prediction dramatically reduces the computing time over existing approaches and consequently permits the exploration of much larger sets of experimental data. To test the validity of the method, we compared the results of our approach with the ones obtained using manual feature selection in our previous study (Perez-Sanchez et al., 2014).The main novelty of this work in the field of drug discovery is the use of RF in two different ways: feature ranking and dimensionality reduction, and classification * Corresponding author: Tel.: +34 610488989; fax: +34 965903681Email addresses: gcano@dtic.ua.es (Gaspar Cano), jgr@ua.es (Jose Garcia-Rodriguez), agarcia@dtic.ua.es (Alberto Garcia-Garcia), hperez@ucam.edu (Horacio Perez-Sanchez), benedikt@hi.is (Jón Atli Benediktsson), anilth@hi.is (Anil Thapa), A.Barr1@westminster.ac.uk (Alastair Barr)