Search

Your search keyword '"WANG, TAN"' showing total 2,124 results
Start Over Author "WANG, TAN"
2,124 results on '"WANG, TAN"'

59. Deciphering the molecular landscape: integrating single-cell transcriptomics to unravel myofibroblast dynamics and therapeutic targets in clear cell renal cell carcinomas

Author

Wenqian Zhou, Zhiheng Lin, and Wang Tan

Subjects
HMGA1+ myofibroblasts, ccRCCs, ScRNA-seq, bulk RNA-seq, experiment validation, Immunologic diseases. Allergy, RC581-607
Abstract

BackgroundClear cell renal cell carcinomas (ccRCCs) epitomize the most formidable clinical subtype among renal neoplasms. While the impact of tumor-associated fibroblasts on ccRCC progression is duly acknowledged, a paucity of literature exists elucidating the intricate mechanisms and signaling pathways operative at the individual cellular level.MethodsEmploying single-cell transcriptomic analysis, we meticulously curated UMAP profiles spanning substantial ccRCC populations, delving into the composition and intrinsic signaling pathways of these cohorts. Additionally, Myofibroblasts were fastidiously categorized into discrete subpopulations, with a thorough elucidation of the temporal trajectory relationships between these subpopulations. We further probed the cellular interaction pathways connecting pivotal subpopulations with tumors. Our endeavor also encompassed the identification of prognostic genes associated with these subpopulations through Bulk RNA-seq, subsequently validated through empirical experimentation.ResultsA notable escalation in the nFeature and nCount of Myofibroblasts and EPCs within ccRCCs was observed, notably enriched in oxidation-related pathways. This phenomenon is postulated to be closely associated with the heightened metabolic activities of Myofibroblasts and EPCs. The Myofibroblasts subpopulation, denoted as C3 HMGA1+ Myofibroblasts, emerges as a pivotal subset, displaying low differentiation and positioning itself at the terminal point of the temporal trajectory. Intriguingly, these cells exhibit a high degree of interaction with tumor cells through the MPZ signaling pathway network, suggesting that Myofibroblasts may facilitate tumor progression via this pathway. Prognostic genes associated with C3 were identified, among which TUBB3 is implicated in potential resistance to tumor recurrence. Finally, experimental validation revealed that the knockout of the key gene within the MPZ pathway, MPZL1, can inhibit tumor activity, proliferation, invasion, and migration capabilities.ConclusionThis investigation delves into the intricate mechanisms and interaction pathways between Myofibroblasts and ccRCCs at the single-cell level. We propose that targeting MPZL1 and the oxidative phosphorylation pathway could serve as potential key targets for treating the progression and recurrence of ccRCC. This discovery paves the way for new directions in the treatment and prognosis diagnosis of ccRCC in the future.

Published
2024
Full Text
View/download PDF

60. Analyzing the relationship between the efficiency and safety of a turbo roundabout by the factor analysis method

Author

Qinghua He, Yuanying Meng, Wang Tan, Xin Tian, Shangru Liu, Hang Yang, Yang Shao, and Binghong Pan

Subjects
Five-way intersection, Turbo roundabout, Efficiency and safety analysis, VISSIM, Factor analysis method (FAM), Science (General), Q1-390, Social sciences (General), H1-99
Abstract

The construction of cities and economic development lead to more and more serious environmental pollution, and the concept of green and low-carbon city has been proposed. Therefore, a series of requirements have been put forward for transportation. CO and other pollutants will be produced in the exhaust of conventional fuel vehicles, which will seriously affect the urban environment, especially at intersections with large passenger and vehicle flows. When multiple roads, especially more than 4 roads, intersect on urban roads, traffic organization can usually be achieved by using a roundabout. However, due to the limited capacity of the conventional roundabout, with the rapid increase of the traffic volume, and there are many vehicles in the circle lane change and interweaving behavior. This has caused serious congestion at the roundabout, the significantly increase in pollutants emissions and the decline in air quality. As an unconventional design, the turbo roundabouts use canalized traffic to allowed drivers to select the appropriate lanes in advance depending on their destinations so that different lanes within the circle do not interfere with one another, which improves the safety of the intersection while ensuring capacity. The main purpose of this paper is to analyze the traffic efficiency and safety of the conventional roundabout scheme and turbo roundabout scheme for five-way intersections. Using VISSIM to simulate different forms of roundabout and analyzing the six selected evaluation indicators. The number of vehicles in different entrance lanes and the diameter of the circle are selected as sensitivity factors for sensitivity analysis. Finally, the factor analysis method (FAM) is used to classify the six indicators into two categories: traffic efficiency and traffic safety, so as to comprehensively evaluate the different schemes. The results show that the difference in performance between the two schemes was not significant at low traffic volumes. At high traffic volumes, the turbo roundabout was better than the conventional roundabout in terms of emissions, safety and throughput efficiency. CO emissions from vehicles on conventional roundabout are generally higher than those on turbo roundabout, up to 53.62%. Therefore, the turbo roundabout is more appropriate for heavy traffic conditions.

Published
2024
Full Text
View/download PDF

61. Burden of Uncontrolled Severe Asthma With and Without Elevated Type-2 Inflammatory Biomarkers

Author

del Olmo, Ricardo, Anderson, Gary, Reddel, Helen, Rabahi, Marcelo, McIvor, Andrew, Sadatsafavi, Mohsen, Weinreich, Ulla, Burgel, Pierre-Régis, Devouassoux, Gilles, Papi, Alberto, Inoue, Hiromasa, Rendon, Adrián, van den Berge, Maarten, Beasley, Richard, García-Navarro, Alvar Agusti, Faner, Rosa, Rivera, José Olaguibel, Janson, Christer, Bilińska-Izydorczyk, Magdalena, Fagerås, Malin, Fihn-Wikander, Titti, Franzén, Stefan, Keen, Christina, Ostridge, Kristoffer, Chalmers, James, Harrison, Timothy, Pavord, Ian, Price, David, Azim, Adnan, Belton, Laura, Blé, Francois-Xavier, Erhard, Clement, Gairy, Kerry, Hughes, Rod, Lassi, Glenda, Müllerová, Hana, Rapsomaniki, Eleni, Scott, Ian Christopher, Chipps, Bradley, Christenson, Stephanie, Make, Barry, Tomaszewski, Erin, Benhabib, Gabriel, Ruiz, Xavier Bocca, Lisanti, Raul Eduardo, Marino, Gustavo, Mattarucco, Walter, Nogueira, Juan, Parody, Maria, Pascale, Pablo, Rodriguez, Pablo, Silva, Damian, Svetliza, Graciela, Victorio, Carlos F., Rolon, Roxana Willigs, Yañez, Anahi, Baines, Stuart, Bowler, Simon, Bremner, Peter, Bull, Sheetal, Carroll, Patrick, Chaalan, Mariam, Farah, Claude, Hammerschlag, Gary, Hancock, Kerry, Harrington, Zinta, Katsoulotos, Gregory, Kim, Joshua, Langton, David, Lee, Donald, Peters, Matthew, Prassad, Lakshman, Sajkov, Dimitar, Santiago, Francis, Simpson, Frederick Graham, Tai, Sze, Thomas, Paul, Wark, Peter, Delfini Cançado, José Eduardo, Cunha, Thúlio, Lima, Marina, Cardoso, Alexandre Pinto, FitzGerald, J. Mark, Anees, Syed, Bertley, John, Bell, Alan, Cheema, Amarjit, Chouinard, Guy, Csanadi, Michael, Dhar, Anil, Dhillon, Ripple, Kanawaty, David, Kelly, Allan, Killorn, William, Landry, Daniel, Luton, Robert, Mandhane, Piushkumar, Pek, Bonavuth, Petrella, Robert, Stollery, Daniel, Wang, Chen, Chen, Meihua, Chen, Yan, Gu, Wei, Christopher Hui, Kim Ming, Li, Manxiang, Li, Shiyue, Lijun, Ma, Qin, Guangyue, Song, Weidong, Tan, Wei, Tang, Yijun, Wang, Tan, Wen, Fuqiang, Wu, Feng, Xiang, PingChao, Xiao, Zuke, Xiong, Shengdao, Yang, Jinghua, Yang, Jingping, Zhang, Caiqing, Zhang, Min, Zhang, Ping, Zhang, Wei, Zheng, Xiaohe, Zhu, Dan, Bueno, Carlos Matiz, Grimaldos, Fabio Bolivar, Arboleda, Alejandra Cañas, Molina de Salazar, Dora, Bendstrup, Elisabeth, Hilberg, Ole, Kjellerup, Carsten, Raherison, Chantal, Bonniaud, Philippe, Brun, Olivier, Chouaid, Christos, Couturaud, Francis, de Blic, Jacques, Debieuvre, Didier, Delsart, Dominique, Demaegdt, Axelle, Demoly, Pascal, Deschildre, Antoine, Egron, Carole, Falchero, Lionel, Goupil, François, Kessler, Romain, Le Roux, Pascal, Mabire, Pascal, Mahay, Guillaume, Martinez, Stéphanie, Melloni, Boris, Moreau, Laurent, Riviere, Emilie, Roux-Claudé, Pauline, Soulier, Michel, Vignal, Guillaume, Yaici, Azzedine, Bals, Robert, Aries, Sven Philip, Beck, Ekkehard, Deimling, Andreas, Feimer, Jan, Grimm-Sachs, Vera, Groth, Gesine, Herth, Felix, Hoheisel, Gerhard, Kanniess, Frank, Lienert, Thomas, Mronga, Silke, Reinhardt, Jörg, Schlenska, Christian, Stolpe, Christoph, Teber, Ishak, Timmermann, Hartmut, Ulrich, Thomas, Velling, Peter, Wehgartner-Winkler, Sabina, Welling, Juergen, Winkelmann, Ernst-Joachim, Barbetta, Carlo, Braido, Fulvio, Cardaci, Vittorio, Clini, Enrico Maria, Costantino, Maria Teresa, Cuttitta, Giuseppina, di Gioacchino, Mario, Fois, Alessandro, Foschino-Barbaro, Maria Pia, Gammeri, Enrico, Inchingolo, Riccardo, Lavorini, Federico, Molino, Antonio, Nucera, Eleonora, Patella, Vincenzo, Pesci, Alberto, Ricciardolo, Fabio, Rogliani, Paola, Sarzani, Riccardo, Vancheri, Carlo, Vincenti, Rigoletta, Endo, Takeo, Fujita, Masaki, Hara, Yu, Horiguchi, Takahiko, Hosoi, Keita, Ide, Yumiko, Inomata, Minehiko, Inoue, Koji, Inoue, Sumito, Kato, Motokazu, Kawasaki, Masayuki, Kawayama, Tomotaka, Kita, Toshiyuki, Kobayashi, Kanako, Koto, Hiroshi, Nishi, Koichi, Saito, Junpei, Shimizu, Yasuo, Shirai, Toshihiro, Sugihara, Naruhiko, Takahashi, Ken-ichi, Tashimo, Hiroyuki, Tomii, Keisuke, Yamada, Takashi, Yanai, Masaru, Rendon, Adrian, Javier, Ruth Cerino, Peregrina, Alfredo Domínguez, Corzo, Marco Fernández, Gonzalez, Efraín Montano, Ramírez-Venegas, Alejandra, Boersma, Willem, Djamin, R.S., Eijsvogel, Michiel, Franssen, Frits, Goosens, Martijn, Graat-Verboom, Lidwien, Veen, Johannes in 't, Janssen, Rob, Kuppens, Kim, van de Ven, Mario, Bakke, Per, Brunstad, Ole Petter, Einvik, Gunnar, Høines, Kristian Jong, Khusrawi, Alamdar, Oien, Torbjorn, Yoon, Ho Joo, Chang, Yoon-Seok, Cho, Young Joo, Hwang, Yong Il, Kim, Woo Jin, Koh, Young-Il, Lee, Byung-Jae, Lee, Kwan-Ho, Lee, Sang-Pyo, Lee, Yong Chul, Lim, Seong Yong, Min, Kyung Hun, Oh, Yeon-Mok, Park, Choon-Sik, Park, Hae-Sim, Park, Heung-Woo, Rhee, Chin Kook, Yoon, Hyoung-Kyu, Andújar, Rubén, Anoro, Laura, García, María Buendía, Mozo, Paloma Campo, Campos, Sergio, Maldonado, Francisco Casas, Martínez, Manuel Castilla, Serrano, Carolina Cisneros, Casanova, Lorena Comeche, Corbacho, Dolores, Del Campo Matías, Felix, Echave-Sustaeta, Jose, Corral, Gloria Francisco, Setién, Pedro Gamboa, Clemente, Marta García, Núñez, Ignacio García, Robaina, Jose García, Salmones, Mercedes García, Marín Trigo, Jose Maria, Fernandez, Marta Nuñez, Palomo, Sara Nuñez, Pérez de Llano, Luis, Bastida, Ana Pueyo, Rañó, Ana, González-Moro, José Rodríguez, Reig, Albert Roger, Garrido, José Velasco, Curiac, Dan, Lif-Tiberg, Cornelia, Luts, Anders, Råhlen, Lennart, Rustscheff, Stefan, Adams, Frances, Bradman, Drew, Broughton, Emma, Cosgrove, John, Flood-Page, Patrick, Fuller, Elizabeth, Hartley, David, Hattotuwa, Keith, Jones, Gareth, Lewis, Keir, McGarvey, Lorcan, Morice, Alyn, Pandya, Preeti, Patel, Manish, Roy, Kay, Sathyamurthy, Ramamurthy, Thiagarajan, Swaminathan, Turner, Alice, Vestbo, Jorgen, Wedzicha, Wisia, Wilkinson, Tom, Wilson, Pete, Al-Asadi, Lo’Ay, Anholm, James, Averill, Francis, Bansal, Sandeep, Baptist, Alan, Campbell, Colin, Campos, Michael A., Crook, Gretchen, DeLeon, Samuel, Eid, Alain, Epstein, Ellen, Fritz, Stephen, Harris, Hoadley, Hewitt, Mitzie, Holguin, Fernando, Hudes, Golda, Jackson, Richard, Kaufman, Alan, Kaufman, David, Klapholz, Ari, Krishna, Harshavardhan, Lee, Daria, Lin, Robert, Maselli-Caceres, Diego, Mehta, Vinay, Moy, James N., Nwokoro, Ugo, Parikh, Purvi, Parikh, Sudhir, Perrino, Frank, Ruhlmann, James, Sassoon, Catherine, Settipane, Russell A., Sousa, Daniel, Sriram, Peruvemba, Wachs, Richard, Ding, Bo, Chen, Stephanie, Quinton, Anna, Cook, William, and Reddel, Helen K.

Published
2024
Full Text
View/download PDF

68. Rhizosphere Microbial Community Diversity and Function Analysis of Cut Chrysanthemum During Continuous Monocropping

Author

Wang, Tan, Yang, Kexin, Ma, Qingyun, Jiang, Xu, Zhou, Yiqing, Kong, Delong, Wang, Zhiye, Parales, Rebecca E, Li, Lin, Zhao, Xin, and Ruan, Zhiyong

Subjects
Microbiology, Biological Sciences, Ecology, Life Below Water, cut chrysanthemum, rhizosphere, community structure, soil physical and chemical property decline, continuous cropping barrier, Environmental Science and Management, Soil Sciences, Medical microbiology
Abstract

As an ornamental flower crop, the long-term continuous monocropping of cut chrysanthemum causes frequent occurrence of diseases, seriously affecting the quality of cut chrysanthemum. The rhizosphere microbial community plays an important role in maintaining the healthy growth of plants, whereas the composition and dynamics of rhizosphere microbial community under continuous monocropping of cut chrysanthemum have not been fully revealed. In this study, the Illumina MiSeq high-throughput sequencing platform was used to monitor the dynamic changes of rhizosphere microbial communities in four varieties of cut chrysanthemum during 0-3 years of monocropping, and the soil physicochemical properties were also determined. Results showed that continuous monocropping significantly increased the fungal community richness and altered the profiles of the bacterial and fungal communities, leading to variation of community beta-diversity. With the increase of continuous cropping time, biocontrol bacteria decreased, while some plant pathogenic fungi were enriched in the rhizosphere of cut chrysanthemum. FAPROTAX-based functional prediction showed that the abundance of gene related to nitrogen and sulfur metabolism and chitin lysis was reduced in the rhizosphere of cut chrysanthemum. FUNGuild-based fungal function prediction showed that plant pathogenic fungal taxa were increasing in the rhizosphere of cut chrysanthemum, mainly Acremonium, Plectosphaerellaceae, Fusarium, and Cladosporium. Continuous cropping also reduced the content of ammonium nitrogen and increased soil salinity, resulting in deterioration of soil physical and chemical properties, which, together with the transformation of rhizosphere microbial community, became part of the reasons for the continuous cropping obstacle of cut chrysanthemum.

Published
2022

69. Counterfactual Zero-Shot and Open-Set Visual Recognition

Author

Yue, Zhongqi, Wang, Tan, Zhang, Hanwang, Sun, Qianru, and Hua, Xian-Sheng

Subjects
Computer Science - Computer Vision and Pattern Recognition, Computer Science - Artificial Intelligence
Abstract

We present a novel counterfactual framework for both Zero-Shot Learning (ZSL) and Open-Set Recognition (OSR), whose common challenge is generalizing to the unseen-classes by only training on the seen-classes. Our idea stems from the observation that the generated samples for unseen-classes are often out of the true distribution, which causes severe recognition rate imbalance between the seen-class (high) and unseen-class (low). We show that the key reason is that the generation is not Counterfactual Faithful, and thus we propose a faithful one, whose generation is from the sample-specific counterfactual question: What would the sample look like, if we set its class attribute to a certain class, while keeping its sample attribute unchanged? Thanks to the faithfulness, we can apply the Consistency Rule to perform unseen/seen binary classification, by asking: Would its counterfactual still look like itself? If ``yes'', the sample is from a certain class, and ``no'' otherwise. Through extensive experiments on ZSL and OSR, we demonstrate that our framework effectively mitigates the seen/unseen imbalance and hence significantly improves the overall performance. Note that this framework is orthogonal to existing methods, thus, it can serve as a new baseline to evaluate how ZSL/OSR models generalize. Codes are available at https://github.com/yue-zhongqi/gcm-cf., Comment: Accepted by CVPR 2021

Published
2021

70. NICO Challenge: Out-of-Distribution Generalization for Image Recognition Challenges

Author

Zhang, Xingxuan, He, Yue, Wang, Tan, Qi, Jiaxin, Yu, Han, Wang, Zimu, Peng, Jie, Xu, Renzhe, Shen, Zheyan, Niu, Yulei, Zhang, Hanwang, Cui, Peng, Goos, Gerhard, Founding Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Karlinsky, Leonid, editor, Michaeli, Tomer, editor, and Nishino, Ko, editor

Published
2023
Full Text
View/download PDF

76. The application of body symbols in contemporary art from the perspective of Da Vinci’s theory

Author

Wang Tan

Subjects
da vinci theory, body symbols, rnn, hidden state estimation, behavioral clustering, 91f10, Mathematics, QA1-939
Abstract

Motion recognition methods can distinguish body symbols and play an important role in real-time safety monitoring of pedestrians. In order to solve the problem of lack of data for deep learning-based action recognition models, a human motion synthesis method with hidden state initialization is proposed. Commonly used human motion synthesis methods utilize Recurrent Neural Network (RNN) to automatically generate subsequent motion sequences by taking several frames of motion data as input. In previous work, the initial hidden state of the RNN is usually set to zero or randomly initialized hidden state, resulting in a jump between the end frame of motion input and the first frame of motion synthesis, which affects the quality of the generated motion. To solve this problem, a method for estimating the initial hidden state estimation is proposed, which takes the initial hidden state as the independent variable, uses the objective function of the neural network as the optimization objective, and uses the gradient descent method to optimize the solution to obtain a suitable initial hidden state. The proposed motion model with initial hidden state estimation reduces the prediction error in the first frame by 63.51% and 6.90%, respectively, and the total error in 10 frames by 50.00% and the total errors of 10 frames were reduced by 50.00% and 4.89%, respectively. The experimental results show that the proposed motion model with initial hidden state estimation has better motion synthesis quality and motion prediction accuracy than the method without initial hidden state estimation; the proposed method improves the quality of motion synthesis by accurately estimating the first frame hidden state of the RNN human motion model, which can provide reliable data support for motion recognition models in real-time security monitoring.

Published
2024
Full Text
View/download PDF

77. DeVLBert: Learning Deconfounded Visio-Linguistic Representations

Author

Zhang, Shengyu, Jiang, Tan, Wang, Tan, Kuang, Kun, Zhao, Zhou, Zhu, Jianke, Yu, Jin, Yang, Hongxia, and Wu, Fei

Subjects
Computer Science - Computer Vision and Pattern Recognition, Computer Science - Computation and Language
Abstract

In this paper, we propose to investigate the problem of out-of-domain visio-linguistic pretraining, where the pretraining data distribution differs from that of downstream data on which the pretrained model will be fine-tuned. Existing methods for this problem are purely likelihood-based, leading to the spurious correlations and hurt the generalization ability when transferred to out-of-domain downstream tasks. By spurious correlation, we mean that the conditional probability of one token (object or word) given another one can be high (due to the dataset biases) without robust (causal) relationships between them. To mitigate such dataset biases, we propose a Deconfounded Visio-Linguistic Bert framework, abbreviated as DeVLBert, to perform intervention-based learning. We borrow the idea of the backdoor adjustment from the research field of causality and propose several neural-network based architectures for Bert-style out-of-domain pretraining. The quantitative results on three downstream tasks, Image Retrieval (IR), Zero-shot IR, and Visual Question Answering, show the effectiveness of DeVLBert by boosting generalization ability., Comment: 10 pages, 4 figures, to appear in ACM MM 2020 proceedings

Published
2020
Full Text
View/download PDF

78. Visual Commonsense R-CNN

Author

Wang, Tan, Huang, Jianqiang, Zhang, Hanwang, and Sun, Qianru

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

We present a novel unsupervised feature representation learning method, Visual Commonsense Region-based Convolutional Neural Network (VC R-CNN), to serve as an improved visual region encoder for high-level tasks such as captioning and VQA. Given a set of detected object regions in an image (e.g., using Faster R-CNN), like any other unsupervised feature learning methods (e.g., word2vec), the proxy training objective of VC R-CNN is to predict the contextual objects of a region. However, they are fundamentally different: the prediction of VC R-CNN is by using causal intervention: P(Y|do(X)), while others are by using the conventional likelihood: P(Y|X). This is also the core reason why VC R-CNN can learn "sense-making" knowledge like chair can be sat -- while not just "common" co-occurrences such as chair is likely to exist if table is observed. We extensively apply VC R-CNN features in prevailing models of three popular tasks: Image Captioning, VQA, and VCR, and observe consistent performance boosts across them, achieving many new state-of-the-arts. Code and feature are available at https://github.com/Wangt-CN/VC-R-CNN., Comment: Accepted by CVPR 2020

Published
2020

90. Cluster Analyses From the Real-World NOVELTY Study: Six Clusters Across the Asthma-COPD Spectrum

Author

Olmo, Ricardo del, Anderson, Gary, Reddel, Helen, Rabahi, Marcelo, McIvor, Andrew, Sadatsafavi, Mohsen, Weinreich, Ulla, Burgel, Pierre-Régis, Devouassoux, Gilles, Papi, Alberto, Inoue, Hiromasa, Rendon, Adrián, van den Berge, Maarten, Beasley, Richard, García-Navarro, Alvar Agusti, Faner, Rosa, Olaguibel Rivera, José, Janson, Christer, Bilińska-Izydorczyk, Magdalena, Fagerås, Malin, Fihn-Wikander, Titti, Franzén, Stefan, Keen, Christina, Ostridge, Kristoffer, Chalmers, James, Harrison, Timothy, Pavord, Ian, Price, David, Azim, Adnan, Belton, Laura, Blé, Francois-Xavier, Erhard, Clement, Gairy, Kerry, Hughes, Rod, Lassi, Glenda, Müllerová, Hana, Rapsomaniki, Eleni, Scott, Ian Christopher, Chipps, Bradley, Christenson, Stephanie, Make, Barry, Tomaszewski, Erin, Benhabib, Gabriel, Ruiz, Xavier Bocca, Lisanti, Raul Eduardo, Marino, Gustavo, Mattarucco, Walter, Nogueira, Juan, Parody, Maria, Pascale, Pablo, Rodriguez, Pablo, Silva, Damian, Svetliza, Graciela, Victorio, Carlos F., Rolon, Roxana Willigs, Yañez, Anahi, Baines, Stuart, Bowler, Simon, Bremner, Peter, Bull, Sheetal, Carroll, Patrick, Chaalan, Mariam, Farah, Claude, Hammerschlag, Gary, Hancock, Kerry, Harrington, Zinta, Katsoulotos, Gregory, Kim, Joshua, Langton, David, Lee, Donald, Peters, Matthew, Prassad, Lakshman, Sajkov, Dimitar, Santiago, Francis, Simpson, Frederick Graham, Tai, Sze, Thomas, Paul, Wark, Peter, Cançado, José Eduardo Delfini, Cunha, Thúlio, Lima, Marina, Cardoso, Alexandre Pinto, FitzGerald, J. Mark, Anees, Syed, Bertley, John, Bell, Alan, Cheema, Amarjit, Chouinard, Guy, Csanadi, Michael, Dhar, Anil, Dhillon, Ripple, Kanawaty, David, Kelly, Allan, Killorn, William, Landry, Daniel, Luton, Robert, Mandhane, Piushkumar, Pek, Bonavuth, Petrella, Robert, Stollery, Daniel, Wang, Chen, Chen, Meihua, Chen, Yan, Gu, Wei, Christopher Hui, Kim Ming, Li, Manxiang, Li, Shiyue, Lijun, Ma, Qin, Guangyue, Song, Weidong, Tan, Wei, Tang, Yijun, Wang, Tan, Wen, Fuqiang, Wu, Feng, Xiang, PingChao, Xiao, Zuke, Xiong, Shengdao, Yang, Jinghua, Yang, Jingping, Zhang, Caiqing, Zhang, Min, Zhang, Ping, Zhang, Wei, Zheng, Xiaohe, Zhu, Dan, Bueno, Carlos Matiz, Grimaldos, Fabio Bolivar, Arboleda, Alejandra Cañas, de Salazar, Dora Molina, Bendstrup, Elisabeth, Hilberg, Ole, Kjellerup, Carsten, Raherison, Chantal, Bonniaud, Philippe, Brun, Olivier, Chouaid, Christos, Couturaud, Francis, de Blic, Jacques, Debieuvre, Didier, Delsart, Dominique, Demaegdt, Axelle, Demoly, Pascal, Deschildre, Antoine, Egron, Carole, Falchero, Lionel, Goupil, François, Kessler, Romain, Le Roux, Pascal, Mabire, Pascal, Mahay, Guillaume, Martinez, Stéphanie, Melloni, Boris, Moreau, Laurent, Riviere, Emilie, Roux-Claudé, Pauline, Soulier, Michel, Vignal, Guillaume, Yaici, Azzedine, Bals, Robert, Aries, Sven Philip, Beck, Ekkehard, Deimling, Andreas, Feimer, Jan, Grimm-Sachs, Vera, Groth, Gesine, Herth, Felix, Hoheisel, Gerhard, Kanniess, Frank, Lienert, Thomas, Mronga, Silke, Reinhardt, Jörg, Schlenska, Christian, Stolpe, Christoph, Teber, Ishak, Timmermann, Hartmut, Ulrich, Thomas, Velling, Peter, Wehgartner-Winkler, Sabina, Welling, Juergen, Winkelmann, Ernst-Joachim, Barbetta, Carlo, Braido, Fulvio, Cardaci, Vittorio, Clini, Enrico Maria, Costantino, Maria Teresa, Cuttitta, Giuseppina, di Gioacchino, Mario, Fois, Alessandro, Foschino-Barbaro, Maria Pia, Gammeri, Enrico, Inchingolo, Riccardo, Lavorini, Federico, Molino, Antonio, Nucera, Eleonora, Patella, Vincenzo, Pesci, Alberto, Ricciardolo, Fabio, Rogliani, Paola, Sarzani, Riccardo, Vancheri, Carlo, Vincenti, Rigoletta, Endo, Takeo, Fujita, Masaki, Hara, Yu, Horiguchi, Takahiko, Hosoi, Keita, Ide, Yumiko, Inomata, Minehiko, Inoue, Koji, Inoue, Sumito, Kato, Motokazu, Kawasaki, Masayuki, Kawayama, Tomotaka, Kita, Toshiyuki, Kobayashi, Kanako, Koto, Hiroshi, Nishi, Koichi, Saito, Junpei, Shimizu, Yasuo, Shirai, Toshihiro, Sugihara, Naruhiko, Takahashi, Ken-ichi, Tashimo, Hiroyuki, Tomii, Keisuke, Yamada, Takashi, Yanai, Masaru, Rendon, Adrian, Cerino Javier, Ruth, Domínguez Peregrina, Alfredo, Fernández Corzo, Marco, Montano Gonzalez, Efraín, Ramírez-Venegas, Alejandra, Boersma, Willem, Djamin, R.S., Eijsvogel, Michiel, Franssen, Frits, Goosens, Martijn, Graat-Verboom, Lidwien, Veen, Johannes in 't, Janssen, Rob, Kuppens, Kim, van de Ven, Mario, Bakke, Per, Brunstad, Ole Petter, Einvik, Gunnar, Høines, Kristian Jong, Khusrawi, Alamdar, Oien, Torbjorn, Yoon, Ho Joo, Chang, Yoon-Seok, Cho, Young Joo, Hwang, Yong Il, Kim, Woo Jin, Koh, Young-Il, Lee, Byung-Jae, Lee, Kwan-Ho, Lee, Sang-Pyo, Lee, Yong Chul, Lim, Seong Yong, Min, Kyung Hun, Oh, Yeon-Mok, Park, Choon-Sik, Park, Hae-Sim, Park, Heung-Woo, Rhee, Chin Kook, Yoon, Hyoung-Kyu, García-Navarro, Alvar Agustí, Andújar, Rubén, Anoro, Laura, Buendía García, María, Mozo, Paloma Campo, Campos, Sergio, Casas Maldonado, Francisco, Castilla Martínez, Manuel, Cisneros Serrano, Carolina, Comeche Casanova, Lorena, Corbacho, Dolores, Campo Matías, Felix Del, Echave-Sustaeta, Jose, Corral, Gloria Francisco, Gamboa Setién, Pedro, García Clemente, Marta, Núñez, Ignacio García, García Robaina, Jose, García Salmones, Mercedes, Marín Trigo, Jose Maria, Fernandez, Marta Nuñez, Palomo, Sara Nuñez, Pérez de Llano, Luis, Pueyo Bastida, Ana, Rañó, Ana, Rodríguez González-Moro, José, Reig, Albert Roger, Velasco Garrido, José, Curiac, Dan, Lif-Tiberg, Cornelia, Luts, Anders, Råhlen, Lennart, Rustscheff, Stefan, Adams, Frances, Bradman, Drew, Broughton, Emma, Cosgrove, John, Flood-Page, Patrick, Fuller, Elizabeth, Hartley, David, Hattotuwa, Keith, Jones, Gareth, Lewis, Keir, McGarvey, Lorcan, Morice, Alyn, Pandya, Preeti, Patel, Manish, Roy, Kay, Sathyamurthy, Ramamurthy, Thiagarajan, Swaminathan, Turner, Alice, Vestbo, Jørgen, Wedzicha, Wisia, Wilkinson, Tom, Wilson, Pete, Al-Asadi, Lo’Ay, Anholm, James, Averill, Francis, Bansal, Sandeep, Baptist, Alan, Campbell, Colin, Campos, Michael A., Crook, Gretchen, DeLeon, Samuel, Eid, Alain, Epstein, Ellen, Fritz, Stephen, Harris, Hoadley, Hewitt, Mitzie, Holguin, Fernando, Hudes, Golda, Jackson, Richard, Kaufman, Alan, Kaufman, David, Klapholz, Ari, Krishna, Harshavardhan, Lee, Daria, Lin, Robert, Maselli-Caceres, Diego, Mehta, Vinay, Moy, James N., Nwokoro, Ugo, Parikh, Purvi, Parikh, Sudhir, Perrino, Frank, Ruhlmann, James, Sassoon, Catherine, Settipane, Russell A., Sousa, Daniel, Sriram, Peruvemba, Wachs, Richard, Bansal, Aruna T., Agustí, Alvar, Fageras, Malin, Alacqua, Marianna, and Reddel, Helen K.

Published
2023
Full Text
View/download PDF

95. Matching Images and Text with Multi-modal Tensor Fusion and Re-ranking

Author

Wang, Tan, Xu, Xing, Yang, Yang, Hanjalic, Alan, Shen, Heng Tao, and Song, Jingkuan

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

A major challenge in matching images and text is that they have intrinsically different data distributions and feature representations. Most existing approaches are based either on embedding or classification, the first one mapping image and text instances into a common embedding space for distance measuring, and the second one regarding image-text matching as a binary classification problem. Neither of these approaches can, however, balance the matching accuracy and model complexity well. We propose a novel framework that achieves remarkable matching performance with acceptable model complexity. Specifically, in the training stage, we propose a novel Multi-modal Tensor Fusion Network (MTFN) to explicitly learn an accurate image-text similarity function with rank-based tensor fusion rather than seeking a common embedding space for each image-text instance. Then, during testing, we deploy a generic Cross-modal Re-ranking (RR) scheme for refinement without requiring additional training procedure. Extensive experiments on two datasets demonstrate that our MTFN-RR consistently achieves the state-of-the-art matching performance with much less time complexity. The implementation code is available at https://github.com/Wangt-CN/MTFN-RR-PyTorch-Code., Comment: ACM Multimedia 2019 Oral

Published
2019

Catalog

Books, media, physical & digital resources
See catalog results