Abstract:This work proposes a complete methodology to colorize images of Fakemon, anime-style monster-like creatures. In addition, we propose algorithms to extract the line art from colorized images as well as to extract color hints. Our work is the first in the literature to use automatic color hint extraction, to train the networks specifically with anime-styled creatures and to combine the Pix2Pix and CycleGAN approaches, two different generative adversarial networks that create a single final result. Visual results of the colorizations are feasible but there is still room for improvement.
Abstract:Recently, Person Re-Identification (Re-ID) has received a lot of attention. Large datasets containing labeled images of various individuals have been released, allowing researchers to develop and test many successful approaches. However, when such Re-ID models are deployed in new cities or environments, the task of searching for people within a network of security cameras is likely to face an important domain shift, thus resulting in decreased performance. Indeed, while most public datasets were collected in a limited geographic area, images from a new city present different features (e.g., people's ethnicity and clothing style, weather, architecture, etc.). In addition, the whole frames of the video streams must be converted into cropped images of people using pedestrian detection models, which behave differently from the human annotators who created the dataset used for training. To better understand the extent of this issue, this paper introduces a complete methodology to evaluate Re-ID approaches and training datasets with respect to their suitability for unsupervised deployment for live operations. This method is used to benchmark four Re-ID approaches on three datasets, providing insight and guidelines that can help to design better Re-ID pipelines in the future.
Abstract:Person Re-Identification (Re-ID) aims to search for a person of interest (query) in a network of cameras. In the classic Re-ID setting the query is sought in a gallery containing properly cropped images of entire bodies. Recently, the live Re-ID setting was introduced to represent the practical application context of Re-ID better. It consists in searching for the query in short videos, containing whole scene frames. The initial live Re-ID baseline used a pedestrian detector to build a large search gallery and a classic Re-ID model to find the query in the gallery. However, the galleries generated were too large and contained low-quality images, which decreased the live Re-ID performance. Here, we present a new live Re-ID approach called TrADe, to generate lower high-quality galleries. TrADe first uses a Tracking algorithm to identify sequences of images of the same individual in the gallery. Following, an Anomaly Detection model is used to select a single good representative of each tracklet. TrADe is validated on the live Re-ID version of the PRID-2011 dataset and shows significant improvements over the baseline.
Abstract:Virtual reality (VR) is an imminent trend in games, education, entertainment, military, and health applications, as the use of head-mounted displays is becoming accessible to the mass market. Virtual reality provides immersive experiences but still does not offer an entirely perfect situation, mainly due to Cybersickness (CS) issues. In this work, we first present a detailed review about possible causes of CS. Following, we propose a novel CS prediction solution. Our system is able to suggest if the user may be entering in the next moments of the application into an illness situation. We use Random Forest classifiers, based on a dataset we have produced. The CSPQ (Cybersickness Profile Questionnaire) is also proposed, which is used to identify the player's susceptibility to CS and the dataset construction. In addition, we designed two immersive environments for empirical studies where participants are asked to complete the questionnaire and describe (orally) the degree of discomfort during their gaming experience. Our data was achieved through 84 individuals on different days, using VR devices. Our proposal also allows us to identify which are the most frequent attributes (causes) in the observed discomfort situations.