396 results on '"Tian Zhu"'
Search Results
2. Feasibility of Recycling the Filtrate from Acidified Black Liquor for Alkaline Pulping of Golden Bamboo Grass
- Author
-
Jin-hui Wang, Tian Zhu, Yi-jing Li, Qian Wang, Yi-kai Ling, Meng-meng Chen, and Guang-zai Nong
- Subjects
black liquor ,fiber materials ,filtrate ,pulp ,recirculation ,Biotechnology ,TP248.13-248.65 - Abstract
To reduce energy consumption, a new pulping process called A-D-E-RC (acidification/desalination/electrolysis/recycle-cooking) was developed by a research group in Guangxi University of China. The present work focuses on the step of recycle cooking (RC) to further investigate the technical feasibility of A-D-E-RC methods. Golden bamboo grass was considered as fiber source material for pulp, and it was cooked with the acidic treating of wastewater from black liquor. Then, the pulp obtained from each cooking was made into paper to test the changes in its physical properties. As a result, the pulp yield increased from 43.9% to 50.2%, after re-using acidified black liquor, and the paper's tear index and tensile index were improved. Therefore, this study demonstrated the feasibility of recycle cooking (RC) fiber materials for pulp applied the acidic treating wastewater from black liquor, and thereby, it further identifies the technical feasibility of A-D-E-RC pulping methods.
- Published
- 2024
3. Preparation of Fiber Raw Materials by Cooking Golden Bamboo Grass (Arundo donax) with Calcified Regenerated Alkali Solution
- Author
-
Qian Wang, Tian Zhu, Yi-jing Li, Jin-hui Wang, Yi-kai Ling, Meng-meng Chen, Liu-ting Mo, and Guang-zai Nong
- Subjects
fibrous materials ,alkali recovery ,cyclic-cooked ,Biotechnology ,TP248.13-248.65 - Abstract
The increasing consumption of paper products has led to a shortage of paper fiber raw materials. It is necessary to develop new plant materials to alleviate the shortage of fiber suitable for papermaking. In this study, the fast-growing plant golden bamboo grass (Arundo donax), which is cultivated and planted in Guangxi province of China, was used as a new material for pulping. The average pulp yield by cyclic-cooking method averaged 48.6%, being 4.1% greater than the pulp yield by the ordinary caustic soda method. Much of the increased yield was attributable to the reprecipitation of lignin onto the fibers. The paper properties of the pulp prepared by cycle-cooked method did not decrease significantly, compared with the pulp prepared by the usual single-cooked method. Therefore, the pulp met the requirements of national standards of many kinds of papers. However, the pulp was not suitable for bleaching, due to its high consumption of oxidizing agents to reach the required brightness. Therefore, this research demonstrates that the fast-growing plant, Arundo donax is a good raw material for pulp, and the innovative method of cycle-cooking method can significantly improve the pulp yield.
- Published
- 2024
4. SARC-F, SARC-CalF, and SARC-F+EBM as practical predictive tools for the risk of pneumonia in patients with stable schizophrenia—a prospective study
- Author
-
Sha Huang, Ming Chen, Tian Zhu, Xiuping Lei, Qiuxia Li, Youguo Tan, and Xiaoyan Chen
- Subjects
Sarcopenia ,SARC-F+EBM ,SARC-CalF ,SARC-F ,Schizophrenia ,Pneumonia ,Science (General) ,Q1-390 ,Social sciences (General) ,H1-99 - Abstract
Objectives: Individuals diagnosed with schizophrenia have a high incidence and fatality rates due to pneumonia. Sarcopenia is a contributing factor to the development of pneumonia in patients with schizophrenia. In this study, we examine the effectiveness of three simple screening questionnaires, namely SARC-F, SARC-CalF, and SARC-F + EBM, in predicting the occurrence of pneumonia in stable patients with schizophrenia who are experiencing sarcopenia. Design: A prospective study. Setting: Patients with stable schizophrenia patients aged ≥50 years in two psychiatric hospitals in western China. Methods: Medical data from patients were collected from September 1 to September 30, 2020. Data specifically from patients diagnosed with pneumonia were collected for a period of one year, from October 2020 to October 2021. Three hundred thirty-five stable schizophrenia patients, among whom 229 were males (68.36 %.), were enrolled in the prospective study. The risk of sarcopenia was evaluated using the SARC-F, SARC-CalF, and SARC-F + EBM scores, with values of ≥4, 11, and 12 indicating an elevated risk of sarcopenia. The collected data were analyzed using logistic regression analysis to establish the association between the scores of these screening tools and the risk of pneumonia in individuals with stable schizophrenia. Results: The rate of pneumonia in stable schizophrenia individuals was 24.48 %. Among the included stable schizophrenia patients, the incidence of pneumonia in individuals with SARC-CalF scores ≥11 was higher than in those with SARC-CalF scores less than 11 (29.91 % vs 14.88 %, P = 0.002). In individuals with SARC-F + EBM scores ≥12, the pneumonia occurrence was higher than that in those with SARC-F + EBM scores less than 12 (37.33 % vs 20.77 %, P = 0.003). However, this pattern was not found in patients with stable schizophrenia who had SARC-F scores of 4 or above and less than 4. Following the implementation of logistic regression data analysis, it has been discovered that persons with SARC-CalF scores greater than or equal to 11 were at a significantly increased risk of having pneumonia compared to patients with SARC-CalF scores less than 11 (OR = 2.441, 95 % CI: 1.367–4.36). After adjusting the possible confounders, patients with SARC-CalF scores ≥11 had a greater danger of pneumonia (OR = 2.518, 95%CI: 1.36–4.665). As a result, it was found that individuals with SACR-F+EBM scores ≥12 were more likely to acquire pneumonia (OR = 2.273, 95%CI: 1.304–3.961) when compared to those with scores
- Published
- 2024
- Full Text
- View/download PDF
5. An impressive case of Rowell syndrome with extensive mucosal involvement successfully treated with anifrolumab
- Author
-
Daniel R. Antohi, BA, Anitha Ramu, MD, Tian Zhu, MD, Shudan Wang, MD, Michael Occidental, MD, Bijal Amin, MD, Benedict Wu, DO, PhD, and Jeanie Lee, MD
- Subjects
anifrolumab ,discoid lupus erythematosus ,malar rash ,Rowell syndrome ,systemic lupus erythematosus ,type 1 interferon ,Dermatology ,RL1-803 - Published
- 2024
- Full Text
- View/download PDF
6. The effects of quercetin and taxifolin on gut microbes, digestion enzymes, antioxidant and inflammatory-related gene expression in the Chinese sucker (Myxocyprinus asiaticus)
- Author
-
Tian Zhu, Mingming Han, Xiankun Gu, Ye Liang, Chenxi Zhu, Zihan Zhou, Qichen Jiang, and Shengkai Tang
- Subjects
Quercetin ,Taxifolin ,Myxocyprinus asiaticus ,Intestinal microorganisms ,Digestive enzyme ,Antioxidant ,Aquaculture. Fisheries. Angling ,SH1-691 - Abstract
We aimed to investigate the effects of quercetin and taxifolin on gut health in the Chinese sucker (Myxocyprinus asiaticus). Short-term exposure (96 h) was conducted by exposing Chinese sucker to 2.5 mg/L of quercetin (Q2.5), 5 mg/L of quercetin (Q5), 10 mg/L of quercetin (Q10), 2.5 mg/L of taxifolin (T2.5), 5 mg/L of taxifolin (T5), 10 mg/L of taxifolin (T10), and their combination (quercetin and taxifolin: 5 mg/L+5 mg/L, QT). Then, we analyzed intestinal microorganisms, fat composition, digestive enzyme activities, and antioxidant and inflammatory-related gene expression. Both quercetin and taxifolin had an inhibitory effect on the intestinal flora, and the higher the quercetin concentration, the better the inhibitory effect. When compared to quercetin, taxifolin inhibited harmful bacteria more efficiently and maintained the abundance of probiotics. T5 and QT reduced the content of total cholesterol (T-CHO), and QT reduced the content of triglycerides (TG) in intestinal tissues. Q5 inhibited trypsin activity, while T5 increased amylase (AMS) activity in intestinal tissues. Q5, T5, and QT increased the expression of GST, GPx4, SOD1 and CAT in the intestine. The expression levels of GST and CAT in T5 were higher than in the Q5 and QT groups. Q5, T5, and QT inhibited the expression of IL1β, IL6, IL8, TNF-α, and TNF-β, and increased the expression levels of IL10. In summary, using taxifolin alone would be more beneficial with regards to maintaining homeostasis of the intestinal flora and increasing the antioxidant and anti-inflammatory capacity of the intestinal tract. The optimal application rate of taxifolin was 5 mg/L.
- Published
- 2024
- Full Text
- View/download PDF
7. Student management model of college student associations based on ant colony Algorithm
- Author
-
Tian Zhu, Li Weixuan, and Nie Yuanyuan
- Subjects
ant colony algorithm ,mass organizations ,management model ,90b50 ,Mathematics ,QA1-939 - Abstract
In order to improve the management efficiency of college students' associations, the author combined with ant colony algorithm to study the student management model of college student associations. Firstly, based on the study of the basic idea, principle, process and application scope of ant colony algorithm under the framework of swarm intelligence, several improved versions of the well-known ant colony algorithm are studied in depth, it provides a basis and reference for the research work of core theory and practical engineering application, secondly, the author will introduce the theoretical framework of the diagnosis and evaluation of college student associations. Through extensive literature review, documents, conducted a questionnaire survey in the student associations of colleges and universities in Dalian, and collected a large number of detailed first-hand materials. The model obtained by using ant colony algorithm plays an important role in management.
- Published
- 2023
- Full Text
- View/download PDF
8. The success rate model of college students’ new entrepreneurship based on nonlinear differential equations
- Author
-
Nie Yuanyuan, Tian Zhu, and Li Weixuan
- Subjects
nonlinear differential equation ,college students start businesses ,success rate of start-ups ,34b15 ,Mathematics ,QA1-939 - Abstract
In order to evaluate the success rate of students’ entrepreneurship more effectively based on a nonlinear differential equation, the author proposes a model for evaluating the success rate of students’ entrepreneurship based on a nonlinear differential equation. These models allow for a score set on the cost of higher education entrepreneurship and determine all higher education entrepreneurship based on it, realizing the cost optimization of higher education entrepreneurship. The simulation results show that the model has scoring and improved student entrepreneurship.
- Published
- 2023
- Full Text
- View/download PDF
9. Innovation and entrepreneurship model of higher vocational college students based on probability theory statistics
- Author
-
Li Weixuan, Nie Yuanyuan, and Tian Zhu
- Subjects
probability theory statistics ,innovation and entrepreneurship ,business model ,62c10 ,Mathematics ,QA1-939 - Abstract
In order to understand the current achievements of vocational students' entrepreneurship, the author creates a model of university students' innovativeness and entrepreneurship. This study analyzes the quality requirements of stakeholders, such as schools and students, for higher education innovation and entrepreneurship education based on research and practical results obtained in Finland and abroad. With the help of probability theory statistics, the relevant indicators are classified, the innovation and entrepreneurship system of vocational educational institutions is built, and the evaluation standards for each indicator are presented. Based on this, the weight of each index is determined and the innovation and entrepreneurship education model of vocational colleges is built. Through the analysis of index scores and total scores at all levels of X Vocational and Technical College and J Vocational College, the total score for innovation and entrepreneurship education at X Vocational College is 3.307 and the total score for innovation and entrepreneurship is 3.307. The education of the J vocational and technical college is 2.743, so the applicability of the model is good.
- Published
- 2023
- Full Text
- View/download PDF
10. Nano-plastics and gastric health: Decoding the cytotoxic mechanisms of polystyrene nano-plastics size
- Author
-
Mingming Han, Tian Zhu, Ji Liang, Hong Wang, Chenxi Zhu, Anisah Lee Binti Abdullah, James Rubinstein, Richard Worthington, Andrew George, Yiming Li, Wei Qin, and Qichen Jiang
- Subjects
Nano-plastics size ,Gastric health ,Cellular death ,Mitochondrial membrane potential ,Calcium channel ,Environmental sciences ,GE1-350 - Abstract
Gastrointestinal diseases exert a profound impact on global health, leading to millions of healthcare interventions and a significant number of fatalities annually. This, coupled with escalating healthcare expenditures, underscores the need for identifying and addressing potential exacerbating factors. One emerging concern is the pervasive presence of microplastics and nano-plastics in the environment, largely attributed to the indiscriminate usage of disposable plastic items. These nano-plastics, having infiltrated our food chain, pose a potential threat to gastrointestinal health. To understand this better, we co-cultured human gastric fibroblasts (HGF) with polystyrene nano-plastics (PS-NPs) of diverse sizes (80, 500, 650 nm) and meticulously investigated their cellular responses over a 24-hour period. Our findings revealed PS particles were ingested by the cells, with a notable increase in ingestion as the particle size decreased. The cellular death induced by these PS particles, encompassing both apoptosis and necrosis, showcased a clear dependence on both the particle size and its concentration. Notably, the larger PS particles manifested more potent cytotoxic effects. Further analysis indicated a concerning reduction in cellular membrane potential, alongside a marked increase in ROS levels upon PS particles exposure. This suggests a significant disruption of mitochondrial function and heightened oxidative stress. The larger PS particles were especially detrimental in causing mitochondrial dysfunction. In-depth exploration into the PS particles impact on genes linked with the permeability transition pore (PTP) elucidated that these PS particles instigated an internal calcium rush. This surge led to a compromise in the mitochondrial membrane potential, which in tandem with raised ROS levels, further catalyzed DNA damage and initiated cell death pathways. In essence, this study unveils the intricate mechanisms underpinning cell death caused by PS particles in gastric epithelial cells and highlighting the implications of PS particles on gastrointestinal health. The revelations from this research bear significant potential to shape future healthcare strategies and inform pertinent environmental policies.
- Published
- 2024
- Full Text
- View/download PDF
11. Optimal strategy of the simultaneous dice game Pig for multiplayers: when reinforcement learning meets game theory
- Author
-
Tian Zhu, Merry Ma, Lu Chen, and Zhenhua Liu
- Subjects
Medicine ,Science - Abstract
Abstract In this work, we focus on using reinforcement learning and game theory to solve for the optimal strategies for the dice game Pig, in a novel simultaneous playing setting. First, we derived analytically the optimal strategy for the 2-player simultaneous game using dynamic programming, mixed-strategy Nash equilibrium. At the same time, we proposed a new Stackelberg value iteration framework to approximate the near-optimal pure strategy. Next, we developed the corresponding optimal strategy for the multiplayer independent strategy game numerically. Finally, we presented the Nash equilibrium for simultaneous Pig game with infinite number of players. To help promote the learning of and interest in reinforcement learning, game theory and statistics, we have further implemented a website where users can play both the sequential and simultaneous Pig game against the optimal strategies derived in this work.
- Published
- 2023
- Full Text
- View/download PDF
12. Interference and secrecy analysis based on randomly spacial model in clustered WSNs
- Author
-
Fei Tong, Tian Zhu, and Yuyang Peng
- Subjects
Telecommunication ,TK5101-6720 - Abstract
Abstract Clustering and layering are widely employed in large‐scale wireless sensor networks (WSNs) to alleviate data implosion, reduce transmission delay and improve energy efficiency. It is vital to conduct performance analysis in clustered WSNs for better defining and designing networks. Here, a general analytical framework based on a randomly spacial model is proposed to conduct inter‐cluster interference analysis and physical‐layer security analysis for clustered WSNs. It is assumed that two adjacent cluster heads exchange confidential massage with a passive eavesdropper and the non‐head nodes in clusters could be selected as cooperative jamming (CJ) nodes to disturb the eavesdropper. All mentioned nodes are randomly located in their specific areas. Under the above settings, three scenarios, namely interference, eavesdropping and CJ are considered, and a stochastic geometry tool based on kinematic measure is employed for analysis. Comparing to existing stochastic geometry methods, the proposed analytical framework can handle arbitrarily shaped, disjoint and tiered networks. The results obtained from extensive simulations have verified the rationality of the framework and demonstrated the impact of different parameters on the performance metrics of interest. The comparison with PPP also shows the advantages of this proposed model.
- Published
- 2022
- Full Text
- View/download PDF
13. Deriving the Optimal Strategy for the Two Dice Pig Game via Reinforcement Learning
- Author
-
Tian Zhu and Merry H. Ma
- Subjects
dynamic programming ,game theory ,Markov decision process ,optimization ,two-dice pig game ,value iteration ,Statistics ,HA1-4737 - Abstract
Games of chance have historically played a critical role in the development and teaching of probability theory and game theory, and, in the modern age, computer programming and reinforcement learning. In this paper, we derive the optimal strategy for playing the two-dice game Pig, both the standard version and its variant with doubles, coined “Double-Trouble”, using certain fundamental concepts of reinforcement learning, especially the Markov decision process and dynamic programming. We further compare the newly derived optimal strategy to other popular play strategies in terms of the winning chances and the order of play. In particular, we compare to the popular “hold at n” strategy, which is considered to be close to the optimal strategy, especially for the best n, for each type of Pig Game. For the standard two-player, two-dice, sequential Pig Game examined here, we found that “hold at 23” is the best choice, with the average winning chance against the optimal strategy being 0.4747. For the “Double-Trouble” version, we found that the “hold at 18” is the best choice, with the average winning chance against the optimal strategy being 0.4733. Furthermore, time in terms of turns to play each type of game is also examined for practical purposes. For optimal vs. optimal or optimal vs. the best “hold at n” strategy, we found that the average number of turns is 19, 23, and 24 for one-die Pig, standard two-dice Pig, and the “Double-Trouble” two-dice Pig games, respectively. We hope our work will inspire students of all ages to invest in the field of reinforcement learning, which is crucial for the development of artificial intelligence and robotics and, subsequently, for the future of humanity.
- Published
- 2022
- Full Text
- View/download PDF
14. Quantitative Trading through Random Perturbation Q-Network with Nonlinear Transaction Costs
- Author
-
Tian Zhu and Wei Zhu
- Subjects
deep reinforcement learning ,Markov decision process ,quantitative finance ,random perturbation algorithm ,transaction costs model ,Statistics ,HA1-4737 - Abstract
In recent years, reinforcement learning (RL) has seen increasing applications in the financial industry, especially in quantitative trading and portfolio optimization when the focus is on the long-term reward rather than short-term profit. Sequential decision making and Markov decision processes are rather suited for this type of application. Through trial and error based on historical data, an agent can learn the characteristics of the market and evolve an algorithm to maximize the cumulative returns. In this work, we propose a novel RL trading algorithm utilizing random perturbation of the Q-network and account for the more realistic nonlinear transaction costs. In summary, we first design a new near-quadratic transaction cost function considering the slippage. Next, we develop a convolutional deep Q-learning network (CDQN) with multiple price input based on this cost functions. We further propose a random perturbation (rp) method to modify the learning network to solve the instability issue intrinsic to the deep Q-learning network. Finally, we use this newly developed CDQN-rp algorithm to make trading decisions based on the daily stock prices of Apple (AAPL), Meta (FB), and Bitcoin (BTC) and demonstrate its strengths over other quantitative trading methods.
- Published
- 2022
- Full Text
- View/download PDF
15. Deep Learning with Automatic Data Augmentation for Segmenting Schisis Cavities in the Optical Coherence Tomography Images of X-Linked Juvenile Retinoschisis Patients
- Author
-
Xing Wei, Hui Li, Tian Zhu, Wuyi Li, Yamei Li, and Ruifang Sui
- Subjects
optical coherence tomography ,X-linked juvenile retinoschisis ,image segmentation ,deep learning ,deep reinforcement learning ,Medicine (General) ,R5-920 - Abstract
X-linked juvenile retinoschisis (XLRS) is an inherited disorder characterized by retinal schisis cavities, which can be observed in optical coherence tomography (OCT) images. Monitoring disease progression necessitates the accurate segmentation and quantification of these cavities; yet, current manual methods are time consuming and result in subjective interpretations, highlighting the need for automated and precise solutions. We employed five state-of-the-art deep learning models—U-Net, U-Net++, Attention U-Net, Residual U-Net, and TransUNet—for the task, leveraging a dataset of 1500 OCT images from 30 patients. To enhance the models’ performance, we utilized data augmentation strategies that were optimized via deep reinforcement learning. The deep learning models achieved a human-equivalent accuracy level in the segmentation of schisis cavities, with U-Net++ surpassing others by attaining an accuracy of 0.9927 and a Dice coefficient of 0.8568. By utilizing reinforcement-learning-based automatic data augmentation, deep learning segmentation models demonstrate a robust and precise method for the automated segmentation of schisis cavities in OCT images. These findings are a promising step toward enhancing clinical evaluation and treatment planning for XLRS.
- Published
- 2023
- Full Text
- View/download PDF
16. Association of Ishii test scores with pneumonia in stable schizophrenic subjects
- Author
-
Qin Yang, Sha Huang, Ming Chen, Tian Zhu, Qiuxia Li, and Xiaoyan Chen
- Subjects
Ishii test ,sarcopenia ,schizophrenia ,pneumonia ,risk ,Psychiatry ,RC435-571 - Abstract
AimWe investigated the relationship between the sarcopenia-indicating Ishii test scores and pneumonia risk in stable schizophrenia patients.MethodsThis prospective investigation involves schizophrenic inpatients from two mental health centers in western China. Patient baseline information was gathered over 1 month from September 1 to 30 in 2020. All pneumonia-related patient information, including diagnosis and treatment, was acquired over 1 year between October 2020 and October 2021. Patients with schizophrenia were screened for sarcopenia utilizing a threshold value established by Ishii et al. Using regression analysis, the link between Ishii test scores and pneumonia risk in schizophrenia patients was investigated.ResultThis study recruited 232 males and 107 females with schizophrenia over the age of 50 and older. During a 1-year follow-up period, four patients (3 males and 1 female) acquired pneumonia within 1 week of relapse in schizophrenia; therefore, these patients were excluded from the study. Finally, data were collected for 335 patients. The pneumonia incidences were 29.3% in males and 14.2% in females. Our analysis confirmed that compared to the male schizophrenia patients with Ishii test scores < 105 (non-sarcopenia), those with Ishii test scores ≥ 105 (sarcopenia) exhibited an elevated pneumonia risk (OR = 2.739, 95%CI: 1.406–5.333). Following confounders adjustment, Ishii test scores ≥ 105 remained a risk factor for pneumonia (OR = 2.064, 95%CI: 1.029–4.143). Among females with schizophrenia, the Ishii test scores were not associated with pneumonia risk.ConclusionIn conclusion, our results demonstrated that the Ishii test scores ≥ 105 were strongly associated with pneumonia risk in stable schizophrenic male patients.
- Published
- 2022
- Full Text
- View/download PDF
17. Association between the mid-upper arm circumference (MUAC) and calf circumference (CC) screening indicators of sarcopenia with the risk of pneumonia in stable patients diagnosed with schizophrenia
- Author
-
Silan Ren, Sha Huang, Ming Chen, Tian Zhu, Qiuxia Li, and Xiaoyan Chen
- Subjects
MUAC ,mid-upper arm circumference ,CC ,calf circumference ,schizophrenia ,pneumonia ,Psychiatry ,RC435-571 - Abstract
AimHere, we investigate the relationship between mid-upper arm circumference (MUAC) and calf circumference (CC) screening indicators of sarcopenia and the risk of pneumonia in stable patients diagnosed with schizophrenia.MethodThe study is prospective and includes inpatients with schizophrenia from two mental health centers in Western China. The studied screening indicators, MUAC and CC were assessed in standing patients. The relationship between MUAC and CC as sarcopenia screening indicators with the risk of pneumonia in patients with schizophrenia was analyzed by performing a statistical logistic regression analysis.ResultFor this study, 339 patients with schizophrenia, aged 50 years and over were recruited. Moreover, four patients with pneumonia that occurred within 1 week of the relapse of schizophrenia were excluded. As a result, only 335 patients were included in the analysis. Pneumonia has been reported in 82 (24.5%) of all included patients with schizophrenia. Our data analysis confirmed that in the male patients, the higher CC was associated with a lower risk of pneumonia (odds ratio [OR] = 0.751, 95% CI: 0.635–0.889). We have divided men into two cohorts following the values of CC. Our analysis further showed that the patients with CC ≥ 34 cm had a lower risk of pneumonia in men (OR = 0.36, 95% CI: 0.163–0.795).ConclusionWe demonstrate that CC is associated with pneumonia risk in stable men with schizophrenia.
- Published
- 2022
- Full Text
- View/download PDF
18. Generation of a human induced pluripotent stem cell line PUMCHi019-A from a dominant optic atrophy patient with an OPA1 mutation
- Author
-
Zixi Sun, Shijing Wu, Tian Zhu, Xing Wei, Xiaoxu Han, Xuan Zou, and Ruifang Sui
- Subjects
Biology (General) ,QH301-705.5 - Abstract
Dominant optic atrophy (DOA) is one of the most common type of hereditary optic atrophy. Here, we describe the generation and characterization of a human induced pluripotent stem cell (hiPSC) line of DOA patient with an OPA1 mutation. The reprogramming of this iPSC line was performed from peripheral blood mononuclear cells (PBMCs) using the non-integrative Sendai virus. The established hiPSC line retained the disease-associated mutation and showed normal karyotype, pluripotency, and differentiation capacity.
- Published
- 2022
- Full Text
- View/download PDF
19. Generation of a human induced pluripotent stem cell line PUMCHi017-A from a Choroideremia patient with CHM mutation
- Author
-
Xiaoxu Han, Shijing Wu, Zixi Sun, Tian Zhu, Xing Wei, Xuan Zou, and Ruifang Sui
- Subjects
Biology (General) ,QH301-705.5 - Abstract
Choroideremia (CHM) is a rare monogenic, X-linked recessive inherited chorioretinal dystrophy caused by loss of function variants in the CHM gene. We successfully generated a novel human induced pluripotent stem cell (hiPSC) line from a CHM patient with CHM variant using the Sendai-virus based approach. These cells will provide a disease model for further studies on the disease pathogenesis and potential interventions.
- Published
- 2022
- Full Text
- View/download PDF
20. Generation of a human induced pluripotent stem cell line (PUMCHi018-A) from an early-onset severe retinal dystrophy patient with RDH12 mutations
- Author
-
Xuan Zou, Shijing Wu, Tian Zhu, Zixi Sun, Xing Wei, Wuyi Li, and Ruifang Sui
- Subjects
Biology (General) ,QH301-705.5 - Abstract
RDH12 mutations have been identified in patients diagnosed with severe early-onset retinal dystrophy, including Leber congenital amaurosis (LCA) and early-onset severe retinal dystrophy (EOSRD). Here, we describe the generation and characterization of a human induced pluripotent stem cell (hiPSC) line of a patient with RDH12 mutations. Blood sample was obtained, and peripheral blood mononuclear cells (PBMCs) were reprogrammed using the non-integrative Sendai virus to generate the iPSC line. The hiPSCs were characterized according to standard protocols including karyotyping, pluripotency marker expression and differentiation towards the three germ layers.
- Published
- 2022
- Full Text
- View/download PDF
21. Hierarchical Graph Interaction Transformer with Dynamic Token Clustering for Camouflaged Object Detection
- Author
-
Yao, Siyuan, Sun, Hao, Xiang, Tian-Zhu, Wang, Xiao, and Cao, Xiaochun
- Subjects
Computer Science - Computer Vision and Pattern Recognition - Abstract
Camouflaged object detection (COD) aims to identify the objects that seamlessly blend into the surrounding backgrounds. Due to the intrinsic similarity between the camouflaged objects and the background region, it is extremely challenging to precisely distinguish the camouflaged objects by existing approaches. In this paper, we propose a hierarchical graph interaction network termed HGINet for camouflaged object detection, which is capable of discovering imperceptible objects via effective graph interaction among the hierarchical tokenized features. Specifically, we first design a region-aware token focusing attention (RTFA) with dynamic token clustering to excavate the potentially distinguishable tokens in the local region. Afterwards, a hierarchical graph interaction transformer (HGIT) is proposed to construct bi-directional aligned communication between hierarchical features in the latent interaction space for visual semantics enhancement. Furthermore, we propose a decoder network with confidence aggregated feature fusion (CAFF) modules, which progressively fuses the hierarchical interacted features to refine the local detail in ambiguous regions. Extensive experiments conducted on the prevalent datasets, i.e. COD10K, CAMO, NC4K and CHAMELEON demonstrate the superior performance of HGINet compared to existing state-of-the-art methods. Our code is available at https://github.com/Garyson1204/HGINet., Comment: Accepted by IEEE Transactions on Image Processing
- Published
- 2024
22. Developing an Efficient Processing System Treatment for the High Concentration of Eucalyptus Chemical Mechanical Pulp Wastewater
- Author
-
Zaiheng Huang, Xiang Qin, Tian Zhu, Xiang Yu, Mengyu Liu, Guangzai Nong, Qifeng Yang, and Shuangfei Wang
- Subjects
chlorine dioxide ,wastewater ,treatment ,DPAT treatment ,Organic chemistry ,QD241-441 - Abstract
The current wastewater treatment method shows low efficiency in treating wastewater with high concentrations of chemical mechanical pulp (CMP). Therefore, a chlorine dioxide Pretreatment Anaerobic Treatment (DPAT) was developed and applied to treat the CMP wastewater to obtain higher efficiency, obtaining the following results: The biodegradability of CMP wastewater improved after chlorine dioxide pretreatment. The COD of wastewater treated with chlorine dioxide was reduced from 5634 mg/L to 660 mg/L. The removal rate for chemical oxygen demand (COD) was 88.29%, 29.13% higher than the common anaerobic treatment. The reasons for the high efficiency of the DPAT treatment were that chlorine dioxide pretreatment removed the toxic substances in the original wastewater and thereby promoted the proliferation and growth of the anaerobe. The results show that pretreatment with chlorine dioxide can effectively enhance the biodegradability of high-concentration CMP wastewater. Therefore, DPAT treatment of high-concentration CMP wastewater is beneficial to environmental protection.
- Published
- 2022
- Full Text
- View/download PDF
23. Characterization of Calpain and Caspase-6-Generated Glial Fibrillary Acidic Protein Breakdown Products Following Traumatic Brain Injury and Astroglial Cell Injury
- Author
-
Zhihui Yang, Rawad Daniel Arja, Tian Zhu, George Anis Sarkis, Robert Logan Patterson, Pammela Romo, Disa S. Rathore, Ahmed Moghieb, Susan Abbatiello, Claudia S. Robertson, William E. Haskins, Firas Kobeissy, and Kevin K. W. Wang
- Subjects
astroglial injury ,GFAP ,calpain ,caspase ,biomarkers ,traumatic brain injury ,Biology (General) ,QH301-705.5 ,Chemistry ,QD1-999 - Abstract
Glial fibrillary acidic protein (GFAP) is the major intermediate filament III protein of astroglia cells which is upregulated in traumatic brain injury (TBI). Here we reported that GFAP is truncated at both the C- and N-terminals by cytosolic protease calpain to GFAP breakdown products (GBDP) of 46-40K then 38K following pro-necrotic (A23187) and pro-apoptotic (staurosporine) challenges to primary cultured astroglia or neuron-glia mixed cells. In addition, with another pro-apoptotic challenge (EDTA) where caspases are activated but not calpain, GFAP was fragmented internally, generating a C-terminal GBDP of 20 kDa. Following controlled cortical impact in mice, GBDP of 46-40K and 38K were formed from day 3 to 28 post-injury. Purified GFAP protein treated with calpain-1 and -2 generates (i) major N-terminal cleavage sites at A-56*A-61 and (ii) major C-terminal cleavage sites at T-383*Q-388, producing a limit fragment of 38K. Caspase-6 treated GFAP was cleaved at D-78/R-79 and D-225/A-226, where GFAP was relatively resistant to caspase-3. We also derived a GBDP-38K N-terminal-specific antibody which only labels injured astroglia cell body in both cultured astroglia and mouse cortex and hippocampus after TBI. As a clinical translation, we observed that CSF samples collected from severe human TBI have elevated levels of GBDP-38K as well as two C-terminally released GFAP peptides (DGEVIKES and DGEVIKE). Thus, in addition to intact GFAP, both the GBDP-38K as well as unique GFAP released C-terminal proteolytic peptides species might have the potential in tracking brain injury progression.
- Published
- 2022
- Full Text
- View/download PDF
24. Adaptive Guidance Learning for Camouflaged Object Detection
- Author
-
Chen, Zhennan, Zhang, Xuying, Xiang, Tian-Zhu, and Tai, Ying
- Subjects
Computer Science - Computer Vision and Pattern Recognition - Abstract
Camouflaged object detection (COD) aims to segment objects visually embedded in their surroundings, which is a very challenging task due to the high similarity between the objects and the background. To address it, most methods often incorporate additional information (e.g., boundary, texture, and frequency clues) to guide feature learning for better detecting camouflaged objects from the background. Although progress has been made, these methods are basically individually tailored to specific auxiliary cues, thus lacking adaptability and not consistently achieving high segmentation performance. To this end, this paper proposes an adaptive guidance learning network, dubbed \textit{AGLNet}, which is a unified end-to-end learnable model for exploring and adapting different additional cues in CNN models to guide accurate camouflaged feature learning. Specifically, we first design a straightforward additional information generation (AIG) module to learn additional camouflaged object cues, which can be adapted for the exploration of effective camouflaged features. Then we present a hierarchical feature combination (HFC) module to deeply integrate additional cues and image features to guide camouflaged feature learning in a multi-level fusion manner.Followed by a recalibration decoder (RD), different features are further aggregated and refined for accurate object prediction. Extensive experiments on three widely used COD benchmark datasets demonstrate that the proposed method achieves significant performance improvements under different additional cues, and outperforms the recent 20 state-of-the-art methods by a large margin. Our code will be made publicly available at: \textcolor{blue}{{https://github.com/ZNan-Chen/AGLNet}}.
- Published
- 2024
25. ZoomNeXt: A Unified Collaborative Pyramid Network for Camouflaged Object Detection
- Author
-
Pang, Youwei, Zhao, Xiaoqi, Xiang, Tian-Zhu, Zhang, Lihe, and Lu, Huchuan
- Subjects
Computer Science - Computer Vision and Pattern Recognition - Abstract
Recent camouflaged object detection (COD) attempts to segment objects visually blended into their surroundings, which is extremely complex and difficult in real-world scenarios. Apart from the high intrinsic similarity between camouflaged objects and their background, objects are usually diverse in scale, fuzzy in appearance, and even severely occluded. To this end, we propose an effective unified collaborative pyramid network that mimics human behavior when observing vague images and videos, \ie zooming in and out. Specifically, our approach employs the zooming strategy to learn discriminative mixed-scale semantics by the multi-head scale integration and rich granularity perception units, which are designed to fully explore imperceptible clues between candidate objects and background surroundings. The former's intrinsic multi-head aggregation provides more diverse visual patterns. The latter's routing mechanism can effectively propagate inter-frame differences in spatiotemporal scenarios and be adaptively deactivated and output all-zero results for static representations. They provide a solid foundation for realizing a unified architecture for static and dynamic COD. Moreover, considering the uncertainty and ambiguity derived from indistinguishable textures, we construct a simple yet effective regularization, uncertainty awareness loss, to encourage predictions with higher confidence in candidate regions. Our highly task-friendly framework consistently outperforms existing state-of-the-art methods in image and video COD benchmarks. Our code can be found at {https://github.com/lartpang/ZoomNeXt}., Comment: Extensions to the conference version accepted by TPAMI 2024. Fixed value errors. arXiv admin note: substantial text overlap with arXiv:2203.02688
- Published
- 2023
- Full Text
- View/download PDF
26. Collaborative Camouflaged Object Detection: A Large-Scale Dataset and Benchmark
- Author
-
Zhang, Cong, Bi, Hongbo, Xiang, Tian-Zhu, Wu, Ranwan, Tong, Jinghui, and Wang, Xiufang
- Subjects
Computer Science - Computer Vision and Pattern Recognition - Abstract
In this paper, we provide a comprehensive study on a new task called collaborative camouflaged object detection (CoCOD), which aims to simultaneously detect camouflaged objects with the same properties from a group of relevant images. To this end, we meticulously construct the first large-scale dataset, termed CoCOD8K, which consists of 8,528 high-quality and elaborately selected images with object mask annotations, covering 5 superclasses and 70 subclasses. The dataset spans a wide range of natural and artificial camouflage scenes with diverse object appearances and backgrounds, making it a very challenging dataset for CoCOD. Besides, we propose the first baseline model for CoCOD, named bilateral-branch network (BBNet), which explores and aggregates co-camouflaged cues within a single image and between images within a group, respectively, for accurate camouflaged object detection in given images. This is implemented by an inter-image collaborative feature exploration (CFE) module, an intra-image object feature search (OFS) module, and a local-global refinement (LGR) module. We benchmark 18 state-of-the-art models, including 12 COD algorithms and 6 CoSOD algorithms, on the proposed CoCOD8K dataset under 5 widely used evaluation metrics. Extensive experiments demonstrate the effectiveness of the proposed method and the significantly superior performance compared to other competitors. We hope that our proposed dataset and model will boost growth in the COD community. The dataset, model, and results will be available at: https://github.com/zc199823/BBNet--CoCOD., Comment: Accepted by IEEE Transactions on Neural Networks and Learning Systems (TNNLS)
- Published
- 2023
27. A Unified Query-based Paradigm for Camouflaged Instance Segmentation
- Author
-
Dong, Bo, Pei, Jialun, Gao, Rongrong, Xiang, Tian-Zhu, Wang, Shuo, and Xiong, Huan
- Subjects
Computer Science - Computer Vision and Pattern Recognition - Abstract
Due to the high similarity between camouflaged instances and the background, the recently proposed camouflaged instance segmentation (CIS) faces challenges in accurate localization and instance segmentation. To this end, inspired by query-based transformers, we propose a unified query-based multi-task learning framework for camouflaged instance segmentation, termed UQFormer, which builds a set of mask queries and a set of boundary queries to learn a shared composed query representation and efficiently integrates global camouflaged object region and boundary cues, for simultaneous instance segmentation and instance boundary detection in camouflaged scenarios. Specifically, we design a composed query learning paradigm that learns a shared representation to capture object region and boundary features by the cross-attention interaction of mask queries and boundary queries in the designed multi-scale unified learning transformer decoder. Then, we present a transformer-based multi-task learning framework for simultaneous camouflaged instance segmentation and camouflaged instance boundary detection based on the learned composed query representation, which also forces the model to learn a strong instance-level query representation. Notably, our model views the instance segmentation as a query-based direct set prediction problem, without other post-processing such as non-maximal suppression. Compared with 14 state-of-the-art approaches, our UQFormer significantly improves the performance of camouflaged instance segmentation. Our code will be available at https://github.com/dongbo811/UQFormer., Comment: This paper has been accepted by ACM MM2023
- Published
- 2023
28. Diffusion Model for Camouflaged Object Detection
- Author
-
Chen, Zhennan, Gao, Rongrong, Xiang, Tian-Zhu, and Lin, Fan
- Subjects
Computer Science - Computer Vision and Pattern Recognition - Abstract
Camouflaged object detection is a challenging task that aims to identify objects that are highly similar to their background. Due to the powerful noise-to-image denoising capability of denoising diffusion models, in this paper, we propose a diffusion-based framework for camouflaged object detection, termed diffCOD, a new framework that considers the camouflaged object segmentation task as a denoising diffusion process from noisy masks to object masks. Specifically, the object mask diffuses from the ground-truth masks to a random distribution, and the designed model learns to reverse this noising process. To strengthen the denoising learning, the input image prior is encoded and integrated into the denoising diffusion model to guide the diffusion process. Furthermore, we design an injection attention module (IAM) to interact conditional semantic features extracted from the image with the diffusion noise embedding via the cross-attention mechanism to enhance denoising learning. Extensive experiments on four widely used COD benchmark datasets demonstrate that the proposed method achieves favorable performance compared to the existing 11 state-of-the-art methods, especially in the detailed texture segmentation of camouflaged objects. Our code will be made publicly available at: https://github.com/ZNan-Chen/diffCOD., Comment: Accepted by ECAI2023
- Published
- 2023
29. Feature Shrinkage Pyramid for Camouflaged Object Detection with Transformers
- Author
-
Huang, Zhou, Dai, Hang, Xiang, Tian-Zhu, Wang, Shuo, Chen, Huai-Xin, Qin, Jie, and Xiong, Huan
- Subjects
Computer Science - Computer Vision and Pattern Recognition - Abstract
Vision transformers have recently shown strong global context modeling capabilities in camouflaged object detection. However, they suffer from two major limitations: less effective locality modeling and insufficient feature aggregation in decoders, which are not conducive to camouflaged object detection that explores subtle cues from indistinguishable backgrounds. To address these issues, in this paper, we propose a novel transformer-based Feature Shrinkage Pyramid Network (FSPNet), which aims to hierarchically decode locality-enhanced neighboring transformer features through progressive shrinking for camouflaged object detection. Specifically, we propose a nonlocal token enhancement module (NL-TEM) that employs the non-local mechanism to interact neighboring tokens and explore graph-based high-order relations within tokens to enhance local representations of transformers. Moreover, we design a feature shrinkage decoder (FSD) with adjacent interaction modules (AIM), which progressively aggregates adjacent transformer features through a layer-bylayer shrinkage pyramid to accumulate imperceptible but effective cues as much as possible for object information decoding. Extensive quantitative and qualitative experiments demonstrate that the proposed model significantly outperforms the existing 24 competitors on three challenging COD benchmark datasets under six widely-used evaluation metrics. Our code is publicly available at https://github.com/ZhouHuang23/FSPNet., Comment: CVPR 2023. Project webpage at: https://tzxiang.github.io/project/COD-FSPNet/index.html
- Published
- 2023
30. The m6A reader HNRNPC promotes glioma progression by enhancing the stability of IRAK1 mRNA through the MAPK pathway
- Author
-
Chen, Jun-Jun, Lu, Tian-Zhu, Wang, Tao, Yan, Wen-Hui, Zhong, Fang-Yan, Qu, Xin-Hui, Gong, Xiao-Chang, Li, Jin-Gao, Tou, Fang-Fang, Jiang, Li-Ping, and Han, Xiao-Jian
- Published
- 2024
- Full Text
- View/download PDF
31. Memory-aided Contrastive Consensus Learning for Co-salient Object Detection
- Author
-
Zheng, Peng, Qin, Jie, Wang, Shuo, Xiang, Tian-Zhu, and Xiong, Huan
- Subjects
Computer Science - Computer Vision and Pattern Recognition - Abstract
Co-Salient Object Detection (CoSOD) aims at detecting common salient objects within a group of relevant source images. Most of the latest works employ the attention mechanism for finding common objects. To achieve accurate CoSOD results with high-quality maps and high efficiency, we propose a novel Memory-aided Contrastive Consensus Learning (MCCL) framework, which is capable of effectively detecting co-salient objects in real time (~150 fps). To learn better group consensus, we propose the Group Consensus Aggregation Module (GCAM) to abstract the common features of each image group; meanwhile, to make the consensus representation more discriminative, we introduce the Memory-based Contrastive Module (MCM), which saves and updates the consensus of images from different groups in a queue of memories. Finally, to improve the quality and integrity of the predicted maps, we develop an Adversarial Integrity Learning (AIL) strategy to make the segmented regions more likely composed of complete objects with less surrounding noise. Extensive experiments on all the latest CoSOD benchmarks demonstrate that our lite MCCL outperforms 13 cutting-edge models, achieving the new state of the art (~5.9% and ~6.2% improvement in S-measure on CoSOD3k and CoSal2015, respectively). Our source codes, saliency maps, and online demos are publicly available at https://github.com/ZhengPeng7/MCCL., Comment: AAAI 2023
- Published
- 2023
32. Trichomonas Vaginalis Segmentation in Microscope Images
- Author
-
Li, Lin, Liu, Jingyi, Wang, Shuo, Wang, Xunkun, and Xiang, Tian-Zhu
- Subjects
Computer Science - Computer Vision and Pattern Recognition - Abstract
Trichomoniasis is a common infectious disease with high incidence caused by the parasite Trichomonas vaginalis, increasing the risk of getting HIV in humans if left untreated. Automated detection of Trichomonas vaginalis from microscopic images can provide vital information for the diagnosis of trichomoniasis. However, accurate Trichomonas vaginalis segmentation (TVS) is a challenging task due to the high appearance similarity between the Trichomonas and other cells (e.g., leukocyte), the large appearance variation caused by their motility, and, most importantly, the lack of large-scale annotated data for deep model training. To address these challenges, we elaborately collected the first large-scale Microscopic Image dataset of Trichomonas Vaginalis, named TVMI3K, which consists of 3,158 images covering Trichomonas of various appearances in diverse backgrounds, with high-quality annotations including object-level mask labels, object boundaries, and challenging attributes. Besides, we propose a simple yet effective baseline, termed TVNet, to automatically segment Trichomonas from microscopic images, including high-resolution fusion and foreground-background attention modules. Extensive experiments demonstrate that our model achieves superior segmentation performance and outperforms various cutting-edge object detection models both quantitatively and qualitatively, making it a promising framework to promote future research in TVS tasks. The dataset and results will be publicly available at: https://github.com/CellRecog/cellRecog., Comment: Accepted by MICCAI2022
- Published
- 2022
33. Boundary-Guided Camouflaged Object Detection
- Author
-
Sun, Yujia, Wang, Shuo, Chen, Chenglizhao, and Xiang, Tian-Zhu
- Subjects
Computer Science - Computer Vision and Pattern Recognition - Abstract
Camouflaged object detection (COD), segmenting objects that are elegantly blended into their surroundings, is a valuable yet challenging task. Existing deep-learning methods often fall into the difficulty of accurately identifying the camouflaged object with complete and fine object structure. To this end, in this paper, we propose a novel boundary-guided network (BGNet) for camouflaged object detection. Our method explores valuable and extra object-related edge semantics to guide representation learning of COD, which forces the model to generate features that highlight object structure, thereby promoting camouflaged object detection of accurate boundary localization. Extensive experiments on three challenging benchmark datasets demonstrate that our BGNet significantly outperforms the existing 18 state-of-the-art methods under four widely-used evaluation metrics. Our code is publicly available at: https://github.com/thograce/BGNet., Comment: Accepted by IJCAI2022
- Published
- 2022
34. Zoom In and Out: A Mixed-scale Triplet Network for Camouflaged Object Detection
- Author
-
Pang, Youwei, Zhao, Xiaoqi, Xiang, Tian-Zhu, Zhang, Lihe, and Lu, Huchuan
- Subjects
Computer Science - Computer Vision and Pattern Recognition - Abstract
The recently proposed camouflaged object detection (COD) attempts to segment objects that are visually blended into their surroundings, which is extremely complex and difficult in real-world scenarios. Apart from high intrinsic similarity between the camouflaged objects and their background, the objects are usually diverse in scale, fuzzy in appearance, and even severely occluded. To deal with these problems, we propose a mixed-scale triplet network, \textbf{ZoomNet}, which mimics the behavior of humans when observing vague images, i.e., zooming in and out. Specifically, our ZoomNet employs the zoom strategy to learn the discriminative mixed-scale semantics by the designed scale integration unit and hierarchical mixed-scale unit, which fully explores imperceptible clues between the candidate objects and background surroundings. Moreover, considering the uncertainty and ambiguity derived from indistinguishable textures, we construct a simple yet effective regularization constraint, uncertainty-aware loss, to promote the model to accurately produce predictions with higher confidence in candidate regions. Without bells and whistles, our proposed highly task-friendly model consistently surpasses the existing 23 state-of-the-art methods on four public datasets. Besides, the superior performance over the recent cutting-edge models on the SOD task also verifies the effectiveness and generality of our model. The code will be available at \url{https://github.com/lartpang/ZoomNet}., Comment: Accepted by CVPR2022. This is the arxiv version that contains the appendix section
- Published
- 2022
35. Generation of a competing endogenous RNA network and validation of BNIP1 expression in the lung of irradiated mice
- Author
-
Yu, Qing-hua, Duan, Shu-yan, Xing, Xue-kun, Fan, Xin-ming, Zhang, Nan, Song, Gui-yuan, Hu, Yong-jian, Wang, Fei, Chao, Tian-zhu, Wang, Li-tao, and Xu, Ping
- Published
- 2024
- Full Text
- View/download PDF
36. Expression, purification and characterization of CTP synthase PyrG in Staphylococcusaureus
- Author
-
Liu, Dafeng, Tian, Zhu, Tusong, Kuerban, Mamat, Hayrinsa, and Luo, Yihan
- Published
- 2024
- Full Text
- View/download PDF
37. Scribble-based Boundary-aware Network for Weakly Supervised Salient Object Detection in Remote Sensing Images
- Author
-
Huang, Zhou, Xiang, Tian-Zhu, Chen, Huai-Xin, and Dai, Hang
- Subjects
Computer Science - Computer Vision and Pattern Recognition - Abstract
Existing CNNs-based salient object detection (SOD) heavily depends on the large-scale pixel-level annotations, which is labor-intensive, time-consuming, and expensive. By contrast, the sparse annotations become appealing to the salient object detection community. However, few efforts are devoted to learning salient object detection from sparse annotations, especially in the remote sensing field. In addition, the sparse annotation usually contains scanty information, which makes it challenging to train a well-performing model, resulting in its performance largely lagging behind the fully-supervised models. Although some SOD methods adopt some prior cues to improve the detection performance, they usually lack targeted discrimination of object boundaries and thus provide saliency maps with poor boundary localization. To this end, in this paper, we propose a novel weakly-supervised salient object detection framework to predict the saliency of remote sensing images from sparse scribble annotations. To implement it, we first construct the scribble-based remote sensing saliency dataset by relabelling an existing large-scale SOD dataset with scribbles, namely S-EOR dataset. After that, we present a novel scribble-based boundary-aware network (SBA-Net) for remote sensing salient object detection. Specifically, we design a boundary-aware module (BAM) to explore the object boundary semantics, which is explicitly supervised by the high-confidence object boundary (pseudo) labels generated by the boundary label generation (BLG) module, forcing the model to learn features that highlight the object structure and thus boosting the boundary localization of objects. Then, the boundary semantics are integrated with high-level features to guide the salient object detection under the supervision of scribble labels., Comment: 33 pages, 10 figures
- Published
- 2022
38. Research trends and hotspots of neoadjuvant therapy in pancreatic cancer: a bibliometric analysis based on the Web of Science Core Collection
- Author
-
Wu, Hong-yu, Liu, Tao, Zhong, Tao, Zheng, Si-yuan, Zhai, Qi-long, Du, Chang-jie, Wu, Tian-zhu, and Li, Jin-zheng
- Published
- 2023
- Full Text
- View/download PDF
39. CarbonNovo: Joint Design of Protein Structure and Sequence Using a Unified Energy-based Model.
- Author
-
Milong Ren, Tian Zhu, and Haicang Zhang
- Published
- 2024
40. Antibody Design Using a Score-based Diffusion Model Guided by Evolutionary, Physical and Geometric Constraints.
- Author
-
Tian Zhu, Milong Ren, and Haicang Zhang
- Published
- 2024
41. Investigating the use of pixel scrambling and diffusion in secure radiographic inspections
- Author
-
He, Qing-Hua, Dou, Xiao-Min, Lu, Kai-Kai, He, Xiao-Suo, Wang, Sheng-Kai, Mo, Tian-Zhu, Xia, Li-Qian, Wang, Xiang-Yu, and He, Xiao-Tao
- Published
- 2024
- Full Text
- View/download PDF
42. Formation mechanism, environmental sensitivity and functional characteristics of succinylated ovalbumin/ε-polylysine electrostatic complexes: The roles of succinylation modification and ε-polylysine combination
- Author
-
Zhang, Ru-yi, Zhang, Hui-min, Guan, Tian-zhu, Wang, Zhi-rong, Li, Hua-xiang, Yuan, Lei, Yang, Yan-jun, and Rao, Sheng-qi
- Published
- 2024
- Full Text
- View/download PDF
43. Correlation of functional magnetic resonance imaging features of primary central nervous system lymphoma with vasculogenic mimicry and reticular fibers
- Author
-
Qi, Huaiju, Zheng, Yu, Li, Jiansheng, Chen, Kaixuan, Zhou, Li, Luo, Dilin, Huang, Shan, Zhang, Jiahui, Lv, Yongge, and Tian, Zhu
- Published
- 2024
- Full Text
- View/download PDF
44. The Elk-3 target Abhd10 ameliorates hepatotoxic injury and fibrosis in alcoholic liver disease
- Author
-
Li, Tian-Zhu, Bai, Chun-Ying, Wu, Bao, Zhang, Cong-Ying, Wang, Wen-Tao, Shi, Tie-Wei, and Zhou, Jing
- Published
- 2023
- Full Text
- View/download PDF
45. Diffusion Model for Camouflaged Object Detection
- Author
-
Chen, Zhennan, primary, Gao, Rongrong, additional, Xiang, Tian-Zhu, additional, and Lin, Fan, additional
- Published
- 2023
- Full Text
- View/download PDF
46. Alkaloid uptake pathways in renal tubular epithelial cells from different processed products of Phellodendri chinensis Cortex
- Author
-
Ge, Xiu-tong, Zhao, Jia-hui, Ren, Wen-jing, Zhou, Yue, Chen, Yang, Jiang, Shi-ru, Jia, Tian-zhu, Gao, Hui, and Zhang, Fan
- Published
- 2024
- Full Text
- View/download PDF
47. Diffusion Model for Camouflaged Object Detection.
- Author
-
Zhennan Chen, Rongrong Gao, Tian-Zhu Xiang, and Fan Lin
- Published
- 2023
- Full Text
- View/download PDF
48. Feature Shrinkage Pyramid for Camouflaged Object Detection with Transformers.
- Author
-
Zhou Huang, Hang Dai, Tian-Zhu Xiang, Shuo Wang, Huai-Xin Chen, Jie Qin, and Huan Xiong
- Published
- 2023
- Full Text
- View/download PDF
49. A Unified Query-based Paradigm for Camouflaged Instance Segmentation.
- Author
-
Bo Dong, Jialun Pei, Rongrong Gao, Tian-Zhu Xiang, Shuo Wang 0010, and Huan Xiong
- Published
- 2023
- Full Text
- View/download PDF
50. Scene-level Point Cloud Colorization with Semantics-and-geometry-aware Networks.
- Author
-
Rongrong Gao, Tian-Zhu Xiang, Chenyang Lei, Jaesik Park, and Qifeng Chen
- Published
- 2023
- Full Text
- View/download PDF
Catalog
Discovery Service for Jio Institute Digital Library
For full access to our library's resources, please sign in.