scholarly journals Fast Preprocessing for Robust Face Sketch Synthesis

2017 ◽  
Author(s):  
Yibing Song ◽  
Jiawei Zhang ◽  
Linchao Bao ◽  
Qingxiong Yang
Keyword(s):  
State Of The Art ◽  
Computational Cost ◽  
Intensity Difference ◽  
Synthesis Methods ◽  
Local Contrast ◽  
Challenging Problem ◽  
Pixel Intensity ◽  
Lighting Conditions ◽  
Sketch Synthesis ◽  
Face Sketch Synthesis

Exemplar-based face sketch synthesis methods usually meet the challenging problem that input photos are captured in different lighting conditions from training photos. The critical step causing the failure is the search of similar patch candidates for an input photo patch. Conventional illumination invariant patch distances are adopted rather than directly relying on pixel intensity difference, but they will fail when local contrast within a patch changes. In this paper, we propose a fast preprocessing method named Bidirectional Luminance Remapping (BLR), which interactively adjust the lighting of training and input photos. Our method can be directly integrated into state-of-the-art exemplar-based methods to improve their robustness with ignorable computational cost

scholarly journals Bottom-up and Layerwise Domain Adaptation for Pedestrian Detection in Thermal Images

2021 ◽  
Vol 17 (1) ◽  
pp. 1-19
Author(s):  
My Kieu ◽  
Andrew D. Bagdanov ◽  
Marco Bertini
Keyword(s):  
Domain Adaptation ◽  
State Of The Art ◽  
Pedestrian Detection ◽  
Challenging Problem ◽  
Top Down ◽  
Bottom Up ◽  
Security Applications ◽  
Lighting Conditions ◽  
Initial Layers ◽  
Single Modality

Pedestrian detection is a canonical problem for safety and security applications, and it remains a challenging problem due to the highly variable lighting conditions in which pedestrians must be detected. This article investigates several domain adaptation approaches to adapt RGB-trained detectors to the thermal domain. Building on our earlier work on domain adaptation for privacy-preserving pedestrian detection, we conducted an extensive experimental evaluation comparing top-down and bottom-up domain adaptation and also propose two new bottom-up domain adaptation strategies. For top-down domain adaptation, we leverage a detector pre-trained on RGB imagery and efficiently adapt it to perform pedestrian detection in the thermal domain. Our bottom-up domain adaptation approaches include two steps: first, training an adapter segment corresponding to initial layers of the RGB-trained detector adapts to the new input distribution; then, we reconnect the adapter segment to the original RGB-trained detector for final adaptation with a top-down loss. To the best of our knowledge, our bottom-up domain adaptation approaches outperform the best-performing single-modality pedestrian detection results on KAIST and outperform the state of the art on FLIR.

scholarly journals A Joint Training Model for Face Sketch Synthesis

2019 ◽  
Vol 9 (9) ◽  
pp. 1731 ◽  
Author(s):  
Weiguo Wan ◽  
Hyo Jong Lee
Keyword(s):  
Sampling Strategy ◽  
Training Model ◽  
Objective Evaluation ◽  
Synthesis Methods ◽  
Locality Constraint ◽  
Joint Training ◽  
Sketch Synthesis ◽  
Face Sketch Synthesis ◽  
Public Datasets ◽  
High Pass

The exemplar-based method is most frequently used in face sketch synthesis because of its efficiency in representing the nonlinear mapping between face photos and sketches. However, the sketches synthesized by existing exemplar-based methods suffer from block artifacts and blur effects. In addition, most exemplar-based methods ignore the training sketches in the weight representation process. To improve synthesis performance, a novel joint training model is proposed in this paper, taking sketches into consideration. First, we construct the joint training photo and sketch by concatenating the original photo and its sketch with a high-pass filtered image of their corresponding sketch. Then, an offline random sampling strategy is adopted for each test photo patch to select the joint training photo and sketch patches in the neighboring region. Finally, a novel locality constraint is designed to calculate the reconstruction weight, allowing the synthesized sketches to have more detailed information. Extensive experimental results on public datasets show the superiority of the proposed joint training model, both from subjective perceptual and the FaceNet-based face recognition objective evaluation, compared to existing state-of-the-art sketch synthesis methods.

scholarly journals ODIN: ODE-Informed Regression for Parameter and State Inference in Time-Continuous Dynamical Systems

2020 ◽  
Vol 34 (04) ◽  
pp. 6364-6371
Author(s):  
Philippe Wenk ◽  
Gabriele Abbati ◽  
Michael A. Osborne ◽  
Bernhard Schölkopf ◽  
Andreas Krause ◽  
...  
Keyword(s):  
Applied Sciences ◽  
Dynamical Systems ◽  
Model Selection ◽  
State Of The Art ◽  
Computational Cost ◽  
Challenging Problem ◽  
Parameter Inference ◽  
Current State ◽  
Generative Modeling ◽  
State Inference

Parameter inference in ordinary differential equations is an important problem in many applied sciences and in engineering, especially in a data-scarce setting. In this work, we introduce a novel generative modeling approach based on constrained Gaussian processes and leverage it to build a computationally and data efficient algorithm for state and parameter inference. In an extensive set of experiments, our approach outperforms the current state of the art for parameter inference both in terms of accuracy and computational cost. It also shows promising results for the much more challenging problem of model selection.

scholarly journals Deep Graphical Feature Learning for Face Sketch Synthesis

2017 ◽  
Author(s):  
Mingrui Zhu ◽  
Nannan Wang ◽  
Xinbo Gao ◽  
Jie Li
Keyword(s):  
State Of The Art ◽  
Synthesis Method ◽  
Feature Learning ◽  
Deep Convolutional Neural Networks ◽  
Learning Framework ◽  
Optimal Weights ◽  
Recognition Ability ◽  
Optimal Reconstruction ◽  
Sketch Synthesis ◽  
Face Sketch Synthesis

The exemplar-based face sketch synthesis method generally contains two steps: neighbor selection and reconstruction weight representation. Pixel intensities are widely used as features by most of the existing exemplar-based methods, which lacks of representation ability and robustness to light variations and clutter backgrounds. We present a novel face sketch synthesis method combining generative exemplar-based method and discriminatively trained deep convolutional neural networks (dCNNs) via a deep graphical feature learning framework. Our method works in both two steps by using deep discriminative representations derived from dCNNs. Instead of using it directly, we boost its representation capability by a deep graphical feature learning framework. Finally, the optimal weights of deep representations and optimal reconstruction weights for face sketch synthesis can be obtained simultaneously. With the optimal reconstruction weights, we can synthesize high quality sketches which is robust against light variations and clutter backgrounds. Extensive experiments on public face sketch databases show that our method outperforms state-of-the-art methods, in terms of both synthesis quality and recognition ability.

scholarly journals The Role of Global Appearance of Omnidirectional Images in Relative Distance and Orientation Retrieval

Sensors ◽  
2021 ◽  
Vol 21 (10) ◽  
pp. 3327
Author(s):  
Vicente Román ◽  
Luis Payá ◽  
Adrián Peidró ◽  
Mónica Ballesta ◽  
Oscar Reinoso
Keyword(s):  
Mobile Robotics ◽  
A Priori ◽  
Computational Cost ◽  
Relevant Information ◽  
Local Features ◽  
New Family ◽  
Lighting Conditions ◽  
Omnidirectional Images ◽  
Great Development

Over the last few years, mobile robotics has experienced a great development thanks to the wide variety of problems that can be solved with this technology. An autonomous mobile robot must be able to operate in a priori unknown environments, planning its trajectory and navigating to the required target points. With this aim, it is crucial solving the mapping and localization problems with accuracy and acceptable computational cost. The use of omnidirectional vision systems has emerged as a robust choice thanks to the big quantity of information they can extract from the environment. The images must be processed to obtain relevant information that permits solving robustly the mapping and localization problems. The classical frameworks to address this problem are based on the extraction, description and tracking of local features or landmarks. However, more recently, a new family of methods has emerged as a robust alternative in mobile robotics. It consists of describing each image as a whole, what leads to conceptually simpler algorithms. While methods based on local features have been extensively studied and compared in the literature, those based on global appearance still merit a deep study to uncover their performance. In this work, a comparative evaluation of six global-appearance description techniques in localization tasks is carried out, both in terms of accuracy and computational cost. Some sets of images captured in a real environment are used with this aim, including some typical phenomena such as changes in lighting conditions, visual aliasing, partial occlusions and noise.

Face sketch synthesis: a survey

2021 ◽  
Author(s):  
Hongbo Bi ◽  
Ziqi Liu ◽  
Lina Yang ◽  
Kang Wang ◽  
Ning Li
Keyword(s):  
Sketch Synthesis ◽  
Face Sketch Synthesis

App2Vec: Context-Aware Application Usage Prediction

2021 ◽  
Vol 15 (6) ◽  
pp. 1-21
Author(s):  
Huandong Wang ◽  
Yong Li ◽  
Mu Du ◽  
Zhenhui Li ◽  
Depeng Jin
Keyword(s):  
Dirichlet Process ◽  
Service Providers ◽  
State Of The Art ◽  
Representation Learning ◽  
Context Aware ◽  
Challenging Problem ◽  
Performance Gap ◽  
Bayesian Mixture Model ◽  
Bayesian Mixture ◽  
Spatio Temporal

Both app developers and service providers have strong motivations to understand when and where certain apps are used by users. However, it has been a challenging problem due to the highly skewed and noisy app usage data. Moreover, apps are regarded as independent items in existing studies, which fail to capture the hidden semantics in app usage traces. In this article, we propose App2Vec, a powerful representation learning model to learn the semantic embedding of apps with the consideration of spatio-temporal context. Based on the obtained semantic embeddings, we develop a probabilistic model based on the Bayesian mixture model and Dirichlet process to capture when , where , and what semantics of apps are used to predict the future usage. We evaluate our model using two different app usage datasets, which involve over 1.7 million users and 2,000+ apps. Evaluation results show that our proposed App2Vec algorithm outperforms the state-of-the-art algorithms in app usage prediction with a performance gap of over 17.0%.

scholarly journals Generative adversarial learning for detail-preserving face sketch synthesis

2021 ◽  
Vol 438 ◽  
pp. 107-121
Author(s):  
Weiguo Wan ◽  
Yong Yang ◽  
Hyo Jong Lee
Keyword(s):  
Adversarial Learning ◽  
Sketch Synthesis ◽  
Face Sketch Synthesis

A State-of-the-Art Review

1977 ◽  
Vol 86 (6_suppl) ◽  
pp. 1-20 ◽  
Author(s):  
Juergen Tonndorf
Keyword(s):  
Auditory System ◽  
Functional State ◽  
Electronic Device ◽  
State Of The Art ◽  
Cochlear Nerve ◽  
Challenging Problem ◽  
Clinical Tests ◽  
Efficient Manner ◽  
Auditory Rehabilitation ◽  
Engineering Problems

Work on cochlear prostheses for the auditory rehabilitation of the profoundly deaf represents a challenging problem. Some early, but perhaps premature, surgical attempts have helped to bring the entire issue into focus. Systemic studies are now under way in many different places. Although the purely engineering problems as well as the surgical ones appear solvable at this time, the remaining unsolved problems lie in two areas: 1) the bioengineering interfacing, i.e., the search for methods needed to connect an engineering (electronic) device to the neural auditory system in an efficient manner; and 2) clinical tests for the assessment of the functional state of the cochlear nerve.

Sign in / Sign up

Export Citation Format

Share Document