Xin Li

Xin Li
Capital Normal University · College of Education

About

192
Publications
45,725
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
5,130
Citations
Citations since 2016
158 Research Items
4710 Citations
201620172018201920202021202202004006008001,000
201620172018201920202021202202004006008001,000
201620172018201920202021202202004006008001,000
201620172018201920202021202202004006008001,000
Introduction
Skills and Expertise

Publications

Publications (192)
Article
Full-text available
Background Unlike autosomal tumor suppressors, X-linked tumor suppressors can be inactivated by a single hit due to X-chromosome inactivation (XCI). Here, we argue that targeted reactivation of the non-mutated allele from XCI offers a potential therapy for female breast cancers. Methods Towards this goal, we developed a dual CRISPR interference an...
Article
With the increasing demand for resources, the opening and stability of the key mineral industry chain have become a key area of national security. As an important key mineral, copper is widely used in the national economic construction and defense industry. This leads to fierce competition and a complex flow relationship between copper resource tra...
Article
Full-text available
Cobalt recycling is important for solving environmental problems such as resource shortage and pollution emissions. This paper quantifies the positive significance of cobalt recycling on resource replenishment and pollution emission by using the substance flow analysis and life cycle analysis. The results show that the proportion of recycled cobalt...
Chapter
We propose a novel image retouching method by modeling the retouching process as performing a sequence of newly introduced trainable neural color operators. The neural color operator mimics the behavior of traditional color operators and learns pixelwise color transformation while its strength is controlled by a scalar. To reflect the homomorphism...
Chapter
Reference-based image super-resolution (RefSR) is a promising SR branch and has shown great potential in overcoming the limitations of single image super-resolution. While previous state-of-the-art RefSR methods mainly focus on improving the efficacy and robustness of reference feature transfer, it is generally overlooked that a well reconstructed...
Preprint
Full-text available
Reference-based image super-resolution (RefSR) is a promising SR branch and has shown great potential in overcoming the limitations of single image super-resolution. While previous state-of-the-art RefSR methods mainly focus on improving the efficacy and robustness of reference feature transfer, it is generally overlooked that a well reconstructed...
Article
As a metal raw material for developing emerging industries, many countries have increased the competition and storage of indium. As the country with the largest reserves and supply of indium resources, China's indium supply affects the development of global emerging industries. The current study of indium upstream of the chain is not comprehensive...
Article
Full-text available
With the rapid development of urbanization, many housing constructions are being built in southwest China, which resulted in tremendous use of building materials, posing a potential threat to the environment. In order to formulate policies for low-carbon, green and sustainable development of buildings, it is necessary to explore the driving factors...
Chapter
Coronary CT Angiography (CCTA) is susceptible to various distortions (e.g., artifacts and noise), which severely compromise the exact diagnosis of cardiovascular diseases. The appropriate CCTA Vessel-level Image Quality Assessment (CCTA VIQA) algorithm can be used to reduce the risk of error diagnosis. The primary challenges of CCTA VIQA are that t...
Article
Full-text available
Hydrogen sulfide (H2S) is one of most important gas transmitters. H2S modulates many physiological and pathological processes such as inflammation, oxidative stress and cell apoptosis that play a critical role in vascular function. Recently, solid evidence show that H2S is closely associated to various vascular diseases. However, specific function...
Article
Titanium is vital to daily life and national security. And titanium sponge is the most important raw material in the production of titanium industry. Therefore, understanding the material cycle flow of titanium sponge in China can help to understand the future use of titanium at global and national levels. This paper traces titanium sponge flows, s...
Preprint
Deep neural networks (DNNs) have shown great potential in non-reference image quality assessment (NR-IQA). However, the annotation of NR-IQA is labor-intensive and time-consuming, which severely limits their application especially for authentic images. To relieve the dependence on quality annotation, some works have applied unsupervised domain adap...
Article
Full-text available
In the era of economic globalization, product trading markets are strongly impacted. The comprehensive utilization of e-waste is an important way to integrate green supply chains and improve resource utilization efficiency. Based on retailers and e-commerce platforms as mobile phone recycling entities, this paper constructs a dual-channel green sup...
Preprint
Full-text available
We propose a novel image retouching method by modeling the retouching process as performing a sequence of newly introduced trainable neural color operators. The neural color operator mimics the behavior of traditional color operators and learns pixelwise color transformation while its strength is controlled by a scalar. To reflect the homomorphism...
Preprint
Existing learning-based methods for blind image quality assessment (BIQA) are heavily dependent on large amounts of annotated training data, and usually suffer from a severe performance degradation when encountering the domain/distribution shift problem. Thanks to the development of unsupervised domain adaptation (UDA), some works attempt to transf...
Article
Full-text available
Resources are essential for human survival and development, and resource security occupies an important position in national security. With the increasing resource shortage problem, ecological stability is facing severe challenges. All countries are actively seeking new sustainable development ways to deal with various issues and shocks caused by t...
Preprint
Image compression has raised widespread interest recently due to its significant importance for multimedia storage and transmission. Meanwhile, a reliable image quality assessment (IQA) for compressed images can not only help to verify the performance of various compression algorithms but also help to guide the compression optimization in turn. In...
Article
Full-text available
Berberine, as a natural alkaloid compound, is characterized by a diversity of pharmacological effects. In recent years, many researches focused on the role of berberine in central nervous system diseases. Among them, the effect of berberine on neurodegenerative diseases has received widespread attention, for example Alzheimer’s disease, Parkinson’s...
Article
Full-text available
A major type of serious mood disorder, depression is currently a widespread and easily overlooked psychological illness. With the low side effects of natural products in the treatment of diseases becoming the pursuit of new antidepressants, natural Chinese medicine products have been paid more and more attention for their unique efficacy in improvi...
Article
Trackers based on the IoU prediction network (IoU-Net) have shown superior performance, which refines a coarse bounding box to an accurate one by maximizing the IoU between the target and the coarse box. However, the traditional IoU-Net is less effective in exploiting the limited but crucial supervision information contained in the initial frame, i...
Preprint
Full-text available
Deep learning based single image super-resolution models have been widely studied and superb results are achieved in upscaling low-resolution images with fixed scale factor and downscaling degradation kernel. To improve real world applicability of such models, there are growing interests to develop models optimized for arbitrary upscaling factors....
Article
Image style transfer aims at synthesizing an image with the content from one image and the style from another. User studies have revealed that the semantic correspondence between style and content greatly affects subjective perception of style transfer results. While current studies have made great progress in improving the visual quality of styliz...
Article
Full-text available
The feature models used by existing Thermal InfraRed (TIR) tracking methods are usually learned from RGB images due to the lack of a large-scale TIR image training dataset. However, these feature models are less effective in representing TIR objects and they are difficult to effectively distinguish distractors because they do not contain fine-grain...
Article
The image distortions are complex and dynamically changing in the real-world scenario, due to the fast development of the image processing system. The blind image quality assessment (BIQA) models may encounter the challenge of processing images with distortion types never seen before deployment. However, existing BIQA models generally cannot evolve...
Article
The current Siamese network based on region proposal network (RPN) has attracted great attention in visual tracking due to its excellent accuracy and high efficiency. However, the design of the RPN involves the selection of the number, scale, and aspect ratios of anchor boxes, which will affect the applicability and convenience of the model. Furthe...
Article
Unsupervised single image restoration approach, Deep Image Prior (DIP), aims to restore images by learning enough raw image statistic priors from the corrupted observation. However, it is not uncommon that an image is contaminated by the multiple unknown distortions. Thus it is hard to disentangle the clean and the hybrid distortion signals by sole...
Preprint
Full-text available
Along with the rapid progress of visual tracking, existing benchmarks become less informative due to redundancy of samples and weak discrimination between current trackers, making evaluations on all datasets extremely time-consuming. Thus, a small and informative benchmark, which covers all typical challenging scenarios to facilitate assessing the...
Preprint
Data augmentation (DA) has been widely investigated to facilitate model optimization in many tasks. However, in most cases, data augmentation is randomly performed for each training sample with a certain probability, which might incur content destruction and visual ambiguities. To eliminate this, in this paper, we propose an effective approach, dub...
Article
Full-text available
Critical metals are indispensable to a world seeking to transition away from carbon. Yet their extraction, processing, and application leave an unsustainable global environment and climate change footprint. To capture the development dynamics and research emphases of critical metals throughout their life cycle, this paper adopts bibliometrics to an...
Preprint
Full-text available
Confounders in deep learning are in general detrimental to model's generalization where they infiltrate feature representations. Therefore, learning causal features that are free of interference from confounders is important. Most previous causal learning based approaches employ back-door criterion to mitigate the adverse effect of certain specific...
Preprint
Collecting large clean-distorted training image pairs in real world is non-trivial, which seriously limits the practical applications of these supervised learning based image restoration (IR) methods. Previous works attempt to address this problem by leveraging unsupervised learning technologies to alleviate the dependency for paired training sampl...
Article
Recent works on learned image compression perform encoding and decoding processes in a full-resolution manner, resulting in two problems when deployed for practical applications. First, parallel acceleration of the autoregressive entropy model cannot be achieved due to serial decoding. Second, full-resolution inference often causes the out-of-memor...
Article
Full-text available
Glioma is a life-threatening malignant tumor. Resistance to traditional treatments and tumor recurrence present major challenges in treating and managing this disease, consequently, new therapeutic strategies must be developed. Crossing the blood-brain barrier (BBB) is another challenge for most drug vectors and therapy medications. Filamentous bac...
Preprint
Unlike autosomal tumor suppressors, which must be inactivated by a two-hit Knudson mechanism, X-linked tumor suppressors can be inactivated by a single hit due to X-chromosome inactivation (XCI). Here, we argue that targeted reactivation of the non-mutated allele from XCI offers a potential therapy for female breast cancers. Towards this goal, we d...
Preprint
Full-text available
Most existing trackers based on deep learning perform tracking in a holistic strategy, which aims to learn deep representations of the whole target for localizing the target. It is arduous for such methods to track targets with various appearance variations. To address this limitation, another type of methods adopts a part-based tracking strategy w...
Article
Full-text available
To explore the impact of promotion of electric vehicles on carbon emissions in China, this paper used the principal component analysis (PCA)-logistic regression model to predict the demand for traditional vehicles, and used the scenario analysis method to analyze the proportion of electric vehicles in traditional vehicles qualitatively. Then this p...
Article
Temporal and spatial contexts, characterizing target appearance variations and target-background differences, respectively, are crucial for improving the online adaptive ability and instance-level discriminative ability of object tracking. However, most existing trackers focus on either the temporal context or the spatial context during tracking an...
Preprint
Full-text available
While deep-learning based methods for visual tracking have achieved substantial progress, these schemes entail large-scale and high-quality annotated data for sufficient training. To eliminate expensive and exhaustive annotation, we study self-supervised learning for visual tracking. In this work, we develop the Crop-Transform-Paste operation, whic...
Article
In visual tracking, it is challenging to distinguish the target from similar objects called noises in the background. As deep trackers use convolutional neural networks for image classification as feature extractors, the extracted features are insensitive to different instances in the same class, which is prone to make prediction models confuse the...
Article
Traditional single image super-resolution (SISR) methods that focus on solving single and uniform degradation (i.e., bicubic down-sampling), typically suffer from poor performance when applied into real-world low-resolution (LR) images due to the complicated realistic degradations. The key to solving this more challenging real image super-resolutio...
Preprint
Existing blind image quality assessment (BIQA) methods are mostly designed in a disposable way and cannot evolve with unseen distortions adaptively, which greatly limits the deployment and application of BIQA models in real-world scenarios. To address this problem, we propose a novel Lifelong blind Image Quality Assessment (LIQA) approach, targetin...
Preprint
Full-text available
The current Siamese network based on region proposal network (RPN) has attracted great attention in visual tracking due to its excellent accuracy and high efficiency. However, the design of the RPN involves the selection of the number, scale, and aspect ratios of anchor boxes, which will affect the applicability and convenience of the model. Furthe...
Article
Full-text available
Existing trackers usually exploit robust features or online updating mechanisms to deal with target variations which is a key challenge in visual tracking. However, the features being robust to variations remain little spatial information, and existing online updating methods are prone to overfitting. In this paper, we propose a dual-margin model f...
Article
This paper aims to study how to achieve a win–win scenario between distribution cost and customer satisfaction; and propose a reasonable scheme for the terminal distribution of cold chain logistics. The paper focuses on the customers’ time requirements and establishes the penalty costs incurred when service time requirements are not met. In additio...
Chapter
Single image super-resolution (SISR) aims to recover the high-resolution (HR) image from its low-resolution (LR) input image. With the development of deep learning, SISR has achieved great progress. However, It is still a challenge to restore the real-world LR image with complicated authentic degradations. Therefore, we propose FAN, a frequency agg...
Article
Full-text available
Accurately identifying the local structural heterogeneity of complex, disordered amorphous materials such as amorphous silicon is crucial for accelerating technology development. However, short-range atomic ordering quantification and nanoscale spatial resolution over a large area on a-Si have remained major challenges and practically unexplored. W...
Article
Full-text available
Recent years have witnessed significant improvements of ensemble trackers based on independent models. However, existing ensemble trackers only combine the responses of independent models and pay less attention to the learning process, which hinders their performance from further improvements. To this end, we propose an interactive learning framewo...
Preprint
Learned image compression based on neural networks have made huge progress thanks to its superiority in learning better representation through non-linear transformation. Different from traditional hybrid coding frameworks, that are commonly block-based, existing learned image codecs usually process the images in a full-resolution manner thus not su...
Preprint
Traditional single image super-resolution (SISR) methods that focus on solving single and uniform degradation (i.e., bicubic down-sampling), typically suffer from poor performance when applied into real-world low-resolution (LR) images due to the complicated realistic degradations. The key to solving this more challenging real image super-resolutio...
Article
The dynamics of protein self-assembly on the inorganic surface and the resultant geometric patterns are visualized using high-speed atomic force microscopy. The time dynamics of the classical macroscopic descriptors such as 2D fast Fourier transforms, correlation, and pair distribution functions are explored using the unsupervised linear unmixing,...
Chapter
Most existing image restoration networks are designed in a disposable way and catastrophically forget previously learned distortions when trained on a new distortion removal task. To alleviate this problem, we raise the novel lifelong image restoration problem for blended distortions. We first design a base fork-join model in which multiple pre-tra...
Article
Full-text available
Existing regression based tracking methods built on correlation filter model or convolution modeldo not take both accuracy and robustness into account at the same time. In this paper, we pro-pose a dual regression framework comprising a discriminative fully convolutional module and a fine-grained correlation filter component for visual tracking. Th...
Chapter
Hybrid-distorted image restoration (HD-IR) is dedicated to restore real distorted image that is degraded by multiple distortions. Existing HD-IR approaches usually ignore the inherent interference among hybrid distortions which compromises the restoration performance. To decompose such interference, we introduce the concept of Disentangled Feature...
Preprint
Single image super-resolution (SISR) aims to recover the high-resolution (HR) image from its low-resolution (LR) input image. With the development of deep learning, SISR has achieved great progress. However, It is still a challenge to restore the real-world LR image with complicated authentic degradations. Therefore, we propose FAN, a frequency agg...
Preprint
Full-text available
This paper introduces the real image Super-Resolution (SR) challenge that was part of the Advances in Image Manipulation (AIM) workshop, held in conjunction with ECCV 2020. This challenge involves three tracks to super-resolve an input image for $\times$2, $\times$3 and $\times$4 scaling factors, respectively. The goal is to attract more attention...
Preprint
Full-text available
In this paper, we present a Large-Scale and high-diversity general Thermal InfraRed (TIR) Object Tracking Benchmark, called LSOTBTIR, which consists of an evaluation dataset and a training dataset with a total of 1,400 TIR sequences and more than 600K frames. We annotate the bounding box of objects in every frame of all sequences and generate over...
Conference Paper
Full-text available
In this paper, we present a Large-Scale and high-diversity general Thermal InfraRed (TIR) Object Tracking Benchmark, called LSOTB-TIR, which consists of an evaluation dataset and a training dataset with a total of 1,400 TIR sequences and more than 600K frames. We annotate the bounding box of objects in every frame of all sequences and generate over...
Article
Titanium dioxide is a significant white inorganic pigment used in coating, plastic, rubber, ink, paper, etc. Material flow analysis of TiO2 can help to analyze the relationship among inflows, outflows and stocks throughout the whole titanium life-cycle in China. This paper divides the whole material flow of TiO2 into four stages by using MFA, inclu...
Article
Full-text available
Existing deep Thermal InfraRed (TIR) trackers only use semantic features to represent the TIR object, which lack the sufficient discriminative capacity for handling distractors. This becomes worse when the feature extraction network is only trained on RGB images. To address this issue, we propose a multi-level similarity model under a Siamese frame...
Article
Full-text available
Recent developments in (scanning) transmission electron microscopy (S)TEM have enabled in-situ investigations of nanoscale transformations. However, understanding the physical and chemical process defining matter transformations via the analysis of large-scale in-situ (S)TEM imaging data remains challenging. Here, we experimentally investigated a r...
Article
China is actively taking measures to guide the household energy‐saving consumption pattern because the total household indirect energy consumption and CO2 emissions have rapidly multiplied from 2002 to 2017 with an annual growth rate of 5.95%, and 5.56%, respectively. This paper calculates indirect energy consumption and CO2 emissions by four energ...
Article
Full-text available
An amendment to this paper has been published and can be accessed via a link at the top of the paper.