Search

Image aesthetic quality assessment (AQA) aims to assign numerical aesthetic ratings to images whilst image aesthetic captioning (IAC) aims to generate textual descriptions of the aesthetic aspects of images. In this paper, we study image AQA and IAC together and present a new IAC method termed Aesthetically Relevant Image Captioning (ARIC). Based on the observation that most textual comments of an image are about objects and their interactions rather than aspects of aesthetics, we first introduce the concept of Aesthetic Relevance Score (ARS) of a sentence and have developed a model to automatically label a sentence with its ARS. We then use the ARS to design the ARIC model which includes an ARS weighted IAC loss function and an ARS based diverse aesthetic caption selector (DACS). We present extensive experimental results to show the soundness of the ARS concept and the effectiveness of the ARIC model by demonstrating that texts with higher ARS's can predict the aesthetic ratings more accurately and that the new ARIC model can generate more accurate, aesthetically more relevant and more diverse image captions. Furthermore, a large new research database containing 510K images with over 5 million comments and 350K aesthetic scores, and code for implementing ARIC are available at https://github.com/PengZai/ARIC., Comment: Aceepted by AAAI2023. Code and results available at https://github.com/PengZai/ARIC

Acceleration of urbanisation is posing great challenges to sustainable development. Growing accessibility to big data and artificial intelligence (AI) technologies have revolutionised many fields and offered great potential for addressing pressing urban problems. However, using these technologies without explicitly considering responsibilities would bring new societal and environmental issues. To fully harness the potential of big data and AI without creating new problems, we envisage a conceptual framework of Responsible Urban Intelligence (RUI) and advocate an agenda for action. We first define RUI as consisting of three major components including urban problems, enabling technologies, and responsibilities; then introduce transparency, fairness, and eco-friendliness as the three dimensions of responsibilities which naturally link with the human, space, and time dimensions of cities; and further develop a four-stage implementation framework for responsibilities as consisting of solution design, data preparation, model building, and practical application; and finally present a research agenda for RUI addressing challenging issues including data and model transparency, tension between performance and fairness, and solving urban problems in an eco-friendly manner.

There are large amount of valuable video archives in Video Home System (VHS) format. However, due to the analog nature, their quality is often poor. Compared to High-definition television (HDTV), VHS video not only has a dull color appearance but also has a lower resolution and often appears blurry. In this paper, we focus on the problem of translating VHS video to HDTV video and have developed a solution based on a novel unsupervised multi-task adversarial learning model. Inspired by the success of generative adversarial network (GAN) and CycleGAN, we employ cycle consistency loss, adversarial loss and perceptual loss together to learn a translation model. An important innovation of our work is the incorporation of super-resolution model and color transfer model that can solve unsupervised multi-task problem. To our knowledge, this is the first work that dedicated to the study of the relation between VHS and HDTV and the first computational solution to translate VHS to HDTV. We present experimental results to demonstrate the effectiveness of our solution qualitatively and quantitatively., Comment: MMM2020 final version

Weighted Gaussian Curvature is an important measurement for images. However, its conventional computation scheme has low performance, low accuracy and requires that the input image must be second order differentiable. To tackle these three issues, we propose a novel discrete computation scheme for the weighted Gaussian curvature. Our scheme does not require the second order differentiability. Moreover, our scheme is more accurate, has smaller support region and computationally more efficient than the conventional schemes. Therefore, our scheme holds promise for a large range of applications where the weighted Gaussian curvature is needed, for example, image smoothing, cartoon texture decomposition, optical flow estimation, etc.

Camera localization is a fundamental requirement in robotics and computer vision. This paper introduces a pose-to-image translation framework to tackle the camera localization problem. We present PoseGANs, a conditional generative adversarial networks (cGANs) based framework for the implementation of pose-to-image translation. PoseGANs feature a number of innovations including a distance metric based conditional discriminator to conduct camera localization and a pose estimation technique for generated camera images as a stronger constraint to improve camera localization performance. Compared with learning-based regression methods such as PoseNet, PoseGANs can achieve better performance with model sizes that are 70% smaller. In addition, PoseGANs introduce the view synthesis technique to establish the correspondence between the 2D images and the scene, \textit{i.e.}, given a pose, PoseGANs are able to synthesize its corresponding camera images. Furthermore, we demonstrate that PoseGANs differ in principle from structure-based localization and learning-based regressions for camera localization, and show that PoseGANs exploit the geometric structures to accomplish the camera localization task, and is therefore more stable than and superior to learning-based regressions which rely on local texture features instead. In addition to camera localization and view synthesis, we also demonstrate that PoseGANs can be successfully used for other interesting applications such as moving object elimination and frame interpolation in video sequences.

Estimating depth from RGB images can facilitate many computer vision tasks, such as indoor localization, height estimation, and simultaneous localization and mapping (SLAM). Recently, monocular depth estimation has obtained great progress owing to the rapid development of deep learning techniques. They surpass traditional machine learning-based methods by a large margin in terms of accuracy and speed. Despite the rapid progress in this topic, there are lacking of a comprehensive review, which is needed to summarize the current progress and provide the future directions. In this survey, we first introduce the datasets for depth estimation, and then give a comprehensive introduction of the methods from three perspectives: supervised learning-based methods, unsupervised learning-based methods, and sparse samples guidance-based methods. In addition, downstream applications that benefit from the progress have also been illustrated. Finally, we point out the future directions and conclude the paper.

One of the methods for stratifying different molecular classes of breast cancer is the Nottingham Prognostic Index Plus (NPI+) which uses breast cancer relevant biomarkers to stain tumour tissues prepared on tissue microarray (TMA). To determine the molecular class of the tumour, pathologists will have to manually mark the nuclei activity biomarkers through a microscope and use a semi-quantitative assessment method to assign a histochemical score (H-Score) to each TMA core. Manually marking positively stained nuclei is a time consuming, imprecise and subjective process which will lead to inter-observer and intra-observer discrepancies. In this paper, we present an end-to-end deep learning system which directly predicts the H-Score automatically. Our system imitates the pathologists' decision process and uses one fully convolutional network (FCN) to extract all nuclei region (tumour and non-tumour), a second FCN to extract tumour nuclei region, and a multi-column convolutional neural network which takes the outputs of the first two FCNs and the stain intensity description image as input and acts as the high-level decision making mechanism to directly output the H-Score of the input TMA image. To the best of our knowledge, this is the first end-to-end system that takes a TMA image as input and directly outputs a clinical score. We will present experimental results which demonstrate that the H-Scores predicted by our model have very high and statistically significant correlation with experienced pathologists' scores and that the H-Score discrepancy between our algorithm and the pathologists is on par with the inter-subject discrepancy between the pathologists.

The microwave-absorption properties and microstructures of Fe-Ni and Fe-Ni-Cr alloys prepared by mechanical alloying were investigated in the frequency range 2–18 GHz. Other properties were studied by scanning electron microscopy, x-ray diffractometry, vibrating sample magnetometry, and transmission line theory. Dependence of reflection loss (RL), electromagnetic properties (permeability μ and permittivity e), magnetic and dielectric loss tangent, impedance matching, and absorber thickness (d) on milling time is discussed. The alloy powders had excellent microwave-absorption properties in the frequency range 7 to 14 GHz. The minimum RL, the frequency at which the RL is minimum, and the bandwidth (RL

In this paper, we introduce deep learning technology to tackle two traditional low-level image processing problems, companding and inverse halftoning. We make two main contributions. First, to the best knowledge of the authors, this is the first work that has successfully developed deep learning based solutions to these two traditional low-level image processing problems. This not only introduces new methods to tackle well-known image processing problems but also demonstrates the power of deep learning in solving traditional signal processing problems. Second, we have developed an effective deep learning algorithm based on insights into the properties of visual quality of images and the internal representation properties of a deep convolutional neural network (CNN). We train a deep CNN as a nonlinear transformation function to map a low bit depth image to higher bit depth or from a halftone image to a continuous tone image. We also employ another pretrained deep CNN as a feature extractor to derive visually important features to construct the objective function for the training of the mapping CNN. We present experimental results to demonstrate the effectiveness of the new deep learning based solutions., Comment: 12 pages

We present a method for discovering and exploiting object specific deep learning features and use face detection as a case study. Motivated by the observation that certain convolutional channels of a Convolutional Neural Network (CNN) exhibit object specific responses, we seek to discover and exploit the convolutional channels of a CNN in which neurons are activated by the presence of specific objects in the input image. A method for explicitly fine-tuning a pre-trained CNN to induce an object specific channel (OSC) and systematically identifying it for the human face object has been developed. Based on the basic OSC features, we introduce a multi-resolution approach to constructing robust face heatmaps for fast face detection in unconstrained settings. We show that multi-resolution OSC can be used to develop state of the art face detectors which have the advantage of being simple and compact.

Both pixel-based scale saliency (PSS) and basis project methods focus on multiscale analysis of data content and structure. Their theoretical relations and practical combination are previously discussed. However, no models have ever been proposed for calculating scale saliency on basis-projected descriptors since then. This paper extend those ideas into mathematical models and implement them in the wavelet-based scale saliency (WSS). While PSS uses pixel-value descriptors, WSS treats wavelet sub-bands as basis descriptors. The paper discusses different wavelet descriptors: discrete wavelet transform (DWT), wavelet packet transform (DWPT), quaternion wavelet transform (QWT) and best basis quaternion wavelet packet transform (QWPTBB). WSS saliency maps of different descriptors are generated and compared against other saliency methods by both quantitative and quanlitative methods. Quantitative results, ROC curves, AUC values and NSS values are collected from simulations on Bruce and Kootstra image databases with human eye-tracking data as ground-truth. Furthermore, qualitative visual results of saliency maps are analyzed and compared against each other as well as eye-tracking data inclusive in the databases., Comment: Partly published in ACIIDS 2013 - Kuala Lumpur Malaysia