Search

Your search keyword '"Huang, Yaping"' showing total 779 results
Start Over Author "Huang, Yaping"
779 results on '"Huang, Yaping"'

1. From Text to CQL: Bridging Natural Language and Corpus Search Engine

Author

Lu, Luming, An, Jiyuan, Wang, Yujie, yang, Liner, Kong, Cunliang, Liu, Zhenghao, Wang, Shuo, Lin, Haozhe, Fang, Mingwei, Huang, Yaping, and Yang, Erhong

Subjects
Computer Science - Computation and Language
Abstract

Natural Language Processing (NLP) technologies have revolutionized the way we interact with information systems, with a significant focus on converting natural language queries into formal query languages such as SQL. However, less emphasis has been placed on the Corpus Query Language (CQL), a critical tool for linguistic research and detailed analysis within text corpora. The manual construction of CQL queries is a complex and time-intensive task that requires a great deal of expertise, which presents a notable challenge for both researchers and practitioners. This paper presents the first text-to-CQL task that aims to automate the translation of natural language into CQL. We present a comprehensive framework for this task, including a specifically curated large-scale dataset and methodologies leveraging large language models (LLMs) for effective text-to-CQL task. In addition, we established advanced evaluation metrics to assess the syntactic and semantic accuracy of the generated queries. We created innovative LLM-based conversion approaches and detailed experiments. The results demonstrate the efficacy of our methods and provide insights into the complexities of text-to-CQL task.

Published
2024

4. Cost-efficient Crowdsourcing for Span-based Sequence Labeling: Worker Selection and Data Augmentation

Author

Wang, Yujie, Huang, Chao, Yang, Liner, Fang, Zhixuan, Huang, Yaping, Liu, Yang, Yu, Jingsi, and Yang, Erhong

Subjects
Computer Science - Computation and Language, Computer Science - Artificial Intelligence
Abstract

This paper introduces a novel crowdsourcing worker selection algorithm, enhancing annotation quality and reducing costs. Unlike previous studies targeting simpler tasks, this study contends with the complexities of label interdependencies in sequence labeling. The proposed algorithm utilizes a Combinatorial Multi-Armed Bandit (CMAB) approach for worker selection, and a cost-effective human feedback mechanism. The challenge of dealing with imbalanced and small-scale datasets, which hinders offline simulation of worker selection, is tackled using an innovative data augmentation method termed shifting, expanding, and shrinking (SES). Rigorous testing on CoNLL 2003 NER and Chinese OEI datasets showcased the algorithm's efficiency, with an increase in F1 score up to 100.04% of the expert-only baseline, alongside cost savings up to 65.97%. The paper also encompasses a dataset-independent test emulating annotation evaluation through a Bernoulli distribution, which still led to an impressive 97.56% F1 score of the expert baseline and 59.88% cost savings. Furthermore, our approach can be seamlessly integrated into Reinforcement Learning from Human Feedback (RLHF) systems, offering a cost-effective solution for obtaining human feedback., Comment: Camera-ready version for CCL 2024

Published
2023

5. Multi Unmanned Aerial Vehicle Collaborative Hunting Task Allocation Method by Improved Consensus-Based Bundle Algorithm

Author

Huang, Yaping, Chang, Min, Chen, Zhiwei, Bai, Junqiang, Angrisani, Leopoldo, Series Editor, Arteaga, Marco, Series Editor, Chakraborty, Samarjit, Series Editor, Chen, Jiming, Series Editor, Chen, Shanben, Series Editor, Chen, Tan Kay, Series Editor, Dillmann, Rüdiger, Series Editor, Duan, Haibin, Series Editor, Ferrari, Gianluigi, Series Editor, Ferre, Manuel, Series Editor, Jabbari, Faryar, Series Editor, Jia, Limin, Series Editor, Kacprzyk, Janusz, Series Editor, Khamis, Alaa, Series Editor, Kroeger, Torsten, Series Editor, Li, Yong, Series Editor, Liang, Qilian, Series Editor, Martín, Ferran, Series Editor, Ming, Tan Cher, Series Editor, Minker, Wolfgang, Series Editor, Misra, Pradeep, Series Editor, Mukhopadhyay, Subhas, Series Editor, Ning, Cun-Zheng, Series Editor, Nishida, Toyoaki, Series Editor, Oneto, Luca, Series Editor, Panigrahi, Bijaya Ketan, Series Editor, Pascucci, Federica, Series Editor, Qin, Yong, Series Editor, Seng, Gan Woon, Series Editor, Speidel, Joachim, Series Editor, Veiga, Germano, Series Editor, Wu, Haitao, Series Editor, Zamboni, Walter, Series Editor, Tan, Kay Chen, Series Editor, Qu, Yi, editor, Gu, Mancang, editor, Niu, Yifeng, editor, and Fu, Wenxing, editor

Published
2024
Full Text
View/download PDF

6. Unpaired Image Dehazing for Real Hazy Images

Author

Zhao, Hongwei, Pei, Yanting, Jin, Yi, Huang, Yaping, Wang, Shengchun, Li, Yidong, Filipe, Joaquim, Editorial Board Member, Ghosh, Ashish, Editorial Board Member, Prates, Raquel Oliveira, Editorial Board Member, Zhou, Lizhu, Editorial Board Member, Zhang, Min, editor, Xu, Bin, editor, Hu, Fuyuan, editor, Lin, Junyu, editor, Song, Xianhua, editor, and Lu, Zeguang, editor

Published
2024
Full Text
View/download PDF

8. The Treasure Beneath Multiple Annotations: An Uncertainty-aware Edge Detector

Author

Zhou, Caixia, Huang, Yaping, Pu, Mengyang, Guan, Qingji, Huang, Li, and Ling, Haibin

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

Deep learning-based edge detectors heavily rely on pixel-wise labels which are often provided by multiple annotators. Existing methods fuse multiple annotations using a simple voting process, ignoring the inherent ambiguity of edges and labeling bias of annotators. In this paper, we propose a novel uncertainty-aware edge detector (UAED), which employs uncertainty to investigate the subjectivity and ambiguity of diverse annotations. Specifically, we first convert the deterministic label space into a learnable Gaussian distribution, whose variance measures the degree of ambiguity among different annotations. Then we regard the learned variance as the estimated uncertainty of the predicted edge maps, and pixels with higher uncertainty are likely to be hard samples for edge detection. Therefore we design an adaptive weighting loss to emphasize the learning from those pixels with high uncertainty, which helps the network to gradually concentrate on the important pixels. UAED can be combined with various encoder-decoder backbones, and the extensive experiments demonstrate that UAED achieves superior performance consistently across multiple edge detection benchmarks. The source code is available at \url{https://github.com/ZhouCX117/UAED}, Comment: CVPR2023

Published
2023

9. Uncertainty-Driven Action Quality Assessment

Author

Zhou, Caixia, Huang, Yaping, and Ling, Haibin

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

Automatic action quality assessment (AQA) has attracted increasing attention due to its wide applications. However, most existing AQA methods employ deterministic models to predict the final score for each action, while overlooking the subjectivity and diversity among expert judges during the scoring process. In this paper, we propose a novel probabilistic model, named Uncertainty-Driven AQA (UD-AQA), to utilize and capture the diversity among multiple judge scores. Specifically, we design a Conditional Variational Auto-Encoder (CVAE)-based module to encode the uncertainty in expert assessment, where multiple judge scores can be produced by sampling latent features from the learned latent space multiple times. To further utilize the uncertainty, we generate the estimation of uncertainty for each prediction, which is employed to re-weight AQA regression loss, effectively reducing the influence of uncertain samples during training. Moreover, we further design an uncertainty-guided training strategy to dynamically adjust the learning order of the samples from low uncertainty to high uncertainty. The experiments show that our proposed method achieves competitive results on three benchmarks including the Olympic events MTL-AQA and FineDiving, and the surgical skill JIGSAWS datasets.

Published
2022

10. Single-cell multi-omics sequencing of human spermatogenesis reveals a DNA demethylation event associated with male meiotic recombination

Author

Huang, Yaping, Li, Lin, An, Geng, Yang, Xinyan, Cui, Manman, Song, Xiuling, Lin, Jing, Zhang, Xiaoling, Yao, Zhaokai, Wan, Cong, Zhou, Cai, Zhao, Jiexiang, Song, Ke, Ren, Shaofang, Xia, Xinyu, Fu, Xin, Lan, Yu, Hu, Xuesong, Wang, Wen, Wang, Mei, Zheng, Yi, Miao, Kai, Bai, Xiaochun, Hutchins, Andrew P., Chang, Gang, Gao, Shuai, and Zhao, Xiao-Yang

Published
2023
Full Text
View/download PDF

11. Interval Prediction of the Safety Risk of Soy Sauce and Pot-Roast Meat Products Based on WPD-ARIMA-GARCH Model

Author

YIN Jia, HUANG Qian, CHEN Xiang, CHEN Chen, CHEN Li, ZHANG Tao, XU Cheng, HUANG Yaping, GUO Pengcheng, WEN Hong

Subjects
marinated meat products, wavelet packet decomposition, autoregressive integrated moving average model, generalized autoregressive conditional heteroskedastic model, interval estimation, Food processing and manufacture, TP368-456
Abstract

In view of the drawback of traditional deterministic prediction that it cannot provide uncertainty information, this study proposed a prediction model that integrates point estimation and interval estimation, and innovatively applied it to the field of food safety risk pre-warning. In the point estimation, wavelet packet decomposition (WPD) was used to decompose the weekly risk level sequence and the autoregressive integrated moving average (ARIMA) model was used for prediction. In the interval estimation, the generalized autoregressive conditional heteroskedastic (GARCH) model was used to predict the residual. The WPD-ARIMA-GARCH model established in this study was applied to the safety risk prediction of soy sauce and pot-roast meat products from a certain region. The results showed that the safety risk of soy sauce and pot-roast meat products from this region was relatively high at the end of March and July in 2019, which was consistent with the actual situation. Meanwhile, in the risk prediction of soy sauce and pot-roast meat products from 10 different regions, the mean square error, mean absolute error, and mean absolute percentage error of the model were 1.626, 0.806, and 20.824, respectively, and the prediction interval normalized average and coverage width-based criterion values at the 90% confidence interval were both 0.024, which could cover all true values. Therefore, the model has high prediction accuracy and low error, is useful for risk control for the quality and safety of soy sauce and pot-roast meat products, and provide technical support for daily food safety supervision.

Published
2024
Full Text
View/download PDF

12. BLCU-ICALL at SemEval-2022 Task 1: Cross-Attention Multitasking Framework for Definition Modeling

Author

Kong, Cunliang, Wang, Yujie, Chong, Ruining, Yang, Liner, Zhang, Hengyuan, Yang, Erhong, and Huang, Yaping

Subjects
Computer Science - Computation and Language
Abstract

This paper describes the BLCU-ICALL system used in the SemEval-2022 Task 1 Comparing Dictionaries and Word Embeddings, the Definition Modeling subtrack, achieving 1st on Italian, 2nd on Spanish and Russian, and 3rd on English and French. We propose a transformer-based multitasking framework to explore the task. The framework integrates multiple embedding architectures through the cross-attention mechanism, and captures the structure of glosses through a masking language model objective. Additionally, we also investigate a simple but effective model ensembling strategy to further improve the robustness. The evaluation results show the effectiveness of our solution. We release our code at: https://github.com/blcuicall/SemEval2022-Task1-DM.

Published
2022

13. EDTER: Edge Detection with Transformer

Author

Pu, Mengyang, Huang, Yaping, Liu, Yuming, Guan, Qingji, and Ling, Haibin

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

Convolutional neural networks have made significant progresses in edge detection by progressively exploring the context and semantic features. However, local details are gradually suppressed with the enlarging of receptive fields. Recently, vision transformer has shown excellent capability in capturing long-range dependencies. Inspired by this, we propose a novel transformer-based edge detector, \emph{Edge Detection TransformER (EDTER)}, to extract clear and crisp object boundaries and meaningful edges by exploiting the full image context information and detailed local cues simultaneously. EDTER works in two stages. In Stage I, a global transformer encoder is used to capture long-range global context on coarse-grained image patches. Then in Stage II, a local transformer encoder works on fine-grained patches to excavate the short-range local cues. Each transformer encoder is followed by an elaborately designed Bi-directional Multi-Level Aggregation decoder to achieve high-resolution features. Finally, the global context and local cues are combined by a Feature Fusion Module and fed into a decision head for edge prediction. Extensive experiments on BSDS500, NYUDv2, and Multicue demonstrate the superiority of EDTER in comparison with state-of-the-arts., Comment: Accepted by CVPR2022

Published
2022

18. Factors Associated With Coronary Angiography Performed Within 6 Months of Randomization to the Conservative Strategy in the ISCHEMIA Trial

Author

Pracoń, Radosław, Spertus, John A., Broderick, Samuel, Bangalore, Sripal, Rockhold, Frank W., Ruzyllo, Witold, Demchenko, Elena, Nageh, Thuraia, Grossman, Gabriel Blacher, Mavromatis, Kreton, Manjunath, Cholenahally N., Smanio, Paola E.P., Stone, Gregg W., Mancini, G.B. John, Boden, William E., Newman, Jonathan D., Reynolds, Harmony R., Hochman, Judith S., Maron, David J., Doan, John, Linefsky, Jason, Lee, Raven, Patel, Risha, Miller, Todd, Yang Cho, So, Milbrandt, Susan, Shelstad, Dawn, Banerjee, Subhash, Kamath, Preeti, Tejani, Ishita, Cobos, Stanley E., Quiles, Kirsten J., Dwyer, Raven R., Donnino, Robert M., Espinosa, Dalisa, Phillips, Lawrence M., Saric, Muhamed, Abdul-Nour, Khaled, Schley, Allison, Golden, Heather, Stone, Peter H., Osseni, Hermine, Wiyarand, Charlene, Douglass, Peter, Pomeroy, Hayley, Craft, Alexandra, Harvey, Bethany, Jang, James J., Anaya, Olivia, Yee, Gennie, Goold, Phoebe, Weitz, Steven, Giovannone, Steven, Pritchard, Lori, Arnold, Suzanne, Gans, Rosann, Henry O’Keefe, Jr, James, Kennedy, Paul, Shapiro, Michael D., Ganesan, Shobana, Schlichting, David, Naher, Aynun, El-Hajjar, Mohammad, Sidhu, Mandeep S., Fein, Steven A., Stewart, Wendy L., Torosoff, Mikhail T., Salmi, Kristin M., Lyubarova, Radmila, Mookherjee, Sulagna, Drzymalski, Krzysztof, McFalls, Edward O., Garcia, Santiago A., Bertog, Stefan C., Johnson, Debra K., Siddiqui, Rizwan A., Herrmann, Rebekah R., Ishani, Areef, Hansen, Ronnell A., Georges Khouri, Michel, Arges, Kristine, LeFevre, Melissa, Tomfohr, Jennifer, Goldberg, Jonathan L., Ann Byrne, Kimberly, Zappernick, Taissa, Goldweit, Richard, Canada, Sallie, Kakade, Meghana, Mieses, Patricia, Cobos, Stanley E., Dwyer, Raven R., Cohen, Ronny A., Espinosa, Dalisa, Mirrer, Brooks, Quiles, Kirsten J., Navarro, Victor, Rantinella, Magdalena, Rodriguez, Jessica, Mancilla, Olivia, Winchester, David E., Stinson, Susan, Kronenberg, Marvin, Weyand, Terry, Rogal, Philip, Crook, Sherron C., McFarren, Christopher, Heitner, John F., Ho, Jean, Khan, Saadat, Mohamed, Mahmoud, Dauber, Ira M., Soltau, Mary R., Rose, Delsa K., Wimmer, Rebecca J., Siegel, Kathy E., Derbyshire, Susan, Cannan, Charles, Dixon, Michelle, Leonard, Gerald, Sudarshan, Sriram, Heard, Ciarra, Gabriel, Viviana, Desire, Sukie, Mehta, Puja K., McDaniel, Michael, Rashid, Fauzia, Lerakis, Stamatios, Asier, Senait, Quyyumi, Arshed, Patel, Keyur, Wenger, Nanette K., Hedgepeth, Chester M., Gillis, Jennifer, Hurlburt, Heather, Manocchia, Megan, Rosen, Alan, Moore, Susan, Congdon, Elizabeth, Sahul, Zakir, Brandt, Gail, Marchelletta, Nora, Wippler, Kristina, Booth, David, Taul, Yvonne, Leung, Steve, Isaacs, Jennifer, Abdel-Latif, Ahmed, Bulkley, Viktoria, Reda, Hassan, Rodgers, Caroline, Ziada, Khaled, Setty, Sampoornima, Halverson, Kimberly E., Roraff, Christine, Thorsen, Jonean, Barua, Rajat S., Ojajuni, Amarachi, Olurinde, Oni, Surineni, Kamalakar, Hage, Fadi, Valaiyapathi, Badhma, Caldeira, Christiano, Davies, James E., Leesar, Massoud, Heo, Jaekyeong, Iskandrian, Amy, Al Solaiman, Firas, Singh, Satinder, Dajani, Khaled, Kartje, Carol M., El-Hajjar, Mohammad, Mesropian, Paul Der, Sacco, Joseph, Rawlins, Michele, McCandless, Brian, Thomson, Jennifer, Orgera, Marisa, Sidhu, Mandeep S., Colleen Rogge, Mary, Arif, Imran, Bunke, Julie, Kerr, Hanan, Unterbrink, Kendra, Fannon, Jacqueline, Burman, Cynthia, Trejo, Jorge F., Dubin, Marcia F., Fletcher, Gerald, Lane, Gary E., Neeson, Lynn M., Parikh, Pragnesh P., Pollak, Peter M., Shapiro, Brian P., Landolfo, Kevin, Gemignani, Anthony, Beaudry, Sarah, O’Rourke, Daniel, Meadows, Judith L., Tirado, Stephanie A., Halliday, Janet, Julian, Pamela, Call, Jason T., Lane, Stephanie M., Stanford, Jennifer L., Hannan, Joseph, Bojar, Robert, Arsenault, Patricia, Kumar, Deepti, Sigel, Pamela, Mukai, John, Martin, Edward T., Brooks, Miriam, Vorobiof, Gabriel, Douangvila, Ladda, Gevorgyan, Rubine, Moorman, Alec, Ranjbaran, Fatima, Smith, Bryn, Ohmart, Carly, Kinlay, Scott, Hamburger, Robert J., Rocco, Thomas P., Ly, Samantha, Bhatt, Deepak L., Quinn, Margot C., Croce, Kevin, Temiyasathit, Sara, Quin, Jacquelyn A, Do, Jacquelyn, Anumpa, Jati, Tobin, Desiree, Zenati, Marco, Faxon, David P, Rayos, Glenn, Langdon, Jennifer, Werner Bayer, Marcia, Seedhom, Ashraf, O’Malley, Amanda, Sullenberger, Lance, Orvis, Erin, Kumkumian, Gregory, Murphy, Mandy, Greenberg, Ann, Iraola, Margaret, Sedlis, Steven P., Maranan, Leandro C., Donnino, Robert M., Lorin, Jeffrey, Tamis-Holland, Jacqueline E., Malinay, Ammy, Kornberg, Robert, Leber, Robert, Saba, Souheil, Edillo, Candice P., Lee, Michael W., Small, Delano R., Nona, Wassim, Alexander, Patrick B., Rehman, Iram, Badami, Umesh, Ostrander, Ann, Wasmiller, Stephanie, Marzo, Kevin, Drewes, Wendy, Patel, Dipti, Robbins, Inga H., Levite, Howard A., White, Jackie M, Shetty, Sanjay, Hallam, Alison, Patel, Mayuri, Hamroff, Glenn S., Spooner, Benjamin J, Hollenweger, Linda M, Little, Raymond W., Little, Holly, Zimbelman, Brandi D., Little, Tiffany, Lui, Charles Y., Eskelson, Nona A, Smith, Brigham R., Vezina, Daniel P., Khor, Lillian L., Abraham, Josephine D., Bull, David A., McKellar, Stephen H., Booth, David, Taul, Yvonne, Kotter, John, Rodgers, Caroline, Abdel-Latif, Ahmed, Isaacs, Jennifer, Bulkley, Viktoria, Hu, Bob, Kaneshiro, Renee, Labovitz, Arthur J., Berlowitz, Michael, Kirby, Bonnie J., Rogal, Philip, Tran, Nhi N., McFarren, Christopher, Jahrsdorfer, Catherine, Matar, Fadi, Caldeira, Christiano, Rodriguez, Fatima, Yunis, Reem, Schnittger, Ingela, Patro, Jhina, Fearon, William F., Deedwania, Prakash, Vega, Antonia, Reddy, Kiran, Sweeny, Joseph, Bloise-Adames, Hugo, Jimenez, Santa, Saint Vrestil, Nicole, Bhandari, Reyna, Spizzieri, Christopher, Schade, Danielle, Yost, Roxanne, Hochberg, Claudia P, Beardsley, Paula, Fine, Denise, Salerno, William D., Tancredi, Jana, Arakelian, Patricia, Mathus, Susan, O’Neill, Deborah, Wyman, Ray, Burkhardt, Joy, Hosino, Suellen, Lubyanaya, Oksana A., Salas, Jose D., Zarka, Amer, Aguirre, Maria, Shah, Anil V., Dhawan, Manu, Parra, Diana, Tran, Tri, Haldis, Thomas, Weick, Catherine, Fowler-Lehman, Katie, Spitzer, Natalie, Riedberger, Casey, Weick, Catherine, Kohn, Jeffrey A., Cobos, Stanley E., Dwyer, Raven R., Espinosa, Dalisa, Quiles, Kirsten J., Girotra, Saket, Drum, Carrie, Miller-Cox, Kimberly, Ollinger, Amy, Almousalli, Omar, Capasso-Gulve, Elizabeth, Melanie Loehr, Alaine, Mosley, Marlowe, Krishnam, Mayil S., Heydari, Shirin, Milliken, Jeffrey C., Lundeen, Andrea M., Patel, Pranav M., Karanjah, Edgar, Seto, Arnold H., Marfori, Wanda C., Harley, Kevin T., Hernandez-Rangel, Eduardo, Gibson, Michael A., Singh, Pam, Allen, Byron J., Coram, Rita, Marie Webb, Anne, Fridell, Ellie, Wilson, Heidi, Thomas, Sabu, Kim, Angela, Schwartz, Ronald G, Wilmot, Patrick, Chen, Wei, El Shahawy, Mahfouz, Stevens, Ramona, Stafford, James, Black, Loriane, Abernethy, William B., Hull, Amber B., Lim, Olivia J., Tucker, Helen C., Putnam, Natasha C., Hall, Linda L., Cauthren, Tia, Tucker, Trish, Zurick, Andrew, Horton, Hollie, Orga, Jan, Meyer, Thomas M., White, Joyce R., Morford, Ronald G., Baumann, Cynthia, Rutkin, Bruce, Seeratan, Vidya, Bokhari, Sabahat, Jimenez, Magnolia, Sokol, Seth I., Schultz, Cidney, Meisner, Jay, Russo, Jeanne, Hamzeh, Ihab, Misra, Arunima, Huda, Zohra, Wall, Matthew, Boan, Araceli, Lenges De Rosen, Veronica, Alam, Mahboob, Turner, Michael C., Hinton, Christine R, Mulhearn, Thomas J., Good, Arnold P., Archer, Beth A., Dionne, Julia S., Allardyce, Cheryl A., Sikora, Lindsey N., Czerniak, Jennifer H., Mull, Jennifer A., Ferguson, Elizabeth, Laube, Frances, Shammas, Nicolas W., Shammas, Gail A, Christensen, Lori, Park, Holly, Chilton, Robert, Hecht, Joan, Nguyen, Patricia K., Vo, Davis, Hirsch, James, Jezior, Matthew, Bindeman, Jody, Salkind, Sara, Espinosa, Dalisa, Desimone, Lori-Ann, Gordon, Paul C., Felix-Stern, Lina, Crain, Thomas, Gomes, Jassira, Gordon, Catherine, Stenberg, Robert, Mann, Aimee, McCreary, Theresa, Pedalino, Ronald P., Cobos, Stanley E., Dwyer, Raven R., Espinosa, Dalisa, Quiles, Kirsten J., Wiesel, Joseph, Cobos, Stanley E., Dwyer, Raven R., Espinosa, Dalisa, Quiles, Kirsten J., Juang, George J., Gopaul, Candace, Hultberg, Karen, Huk, Tauqir, Hussain, Afshan, Al-Amoodi, Mohammed, Zambrano, Yesenia, Medina Rodriguez, Sarah, Milner, Trudie, Wohns, David, Mulder, Abbey, Van Oosterhout, Stacie, Lader, Ellis W., Meyer, Martha, Mumma, Michael, Clapp, Nancy L., Barrentine, Heather, Dharmarajan, Lekshmi, Jose, Jenne M., Cobos, Stanley E., Dwyer, Raven R., Espinosa, Dalisa, Quiles, Kirsten J., Manchery, Jenne, McGarvey Jr, Joseph F.X., McKinney, Vera, Schwarz, Linda, Downes, Thomas R., Kaczkowski, Scott M., Luckasen, Gary J., Jaskowiak, Adam J., Klitch, Joel, Cheong, Benjamin, Dees, Debra, Potluri, Srinivasa, Vasquez, Precilia, Mastouri, Ronald A., Breall, Jeffery A., Hannemann, Elise L., Revtyak, George E., Mae Foltz, Judy, Bazeley, Jonathan W., Li, Dayuan, DeRosa, Emily, Jorgenson, Beth, Riestenberg-Smith, Joyce, Giedd, Kenneth, Old, Wayne, Bariciano, Rebecca, Burt, Francis, Sokhon, Kozhaya, Waldron, Jessica, Mayon, Michelle, Gopal, Deepika, Valeti, Uma S., Ann Peichel, Gretchen, Kobashigawa, Jon, Starks, Brandy, Garcia, Lucilla, Thottam, Maria, Bhargava, Balram, Anand, Anjali, Chakanalil Govindan, Sajeev, Raj, Janitha, Gopalan Nair, Rajesh, Ravindran, Reshma, Rajalekshmi, VS, Nataraj, Nandita, Moorthy, Nagaraja, Nayak, Soundarya, Mylarappa, Mahevamma, Narayanappa, Suryaprakash, Pandit, Neeraj, Bajaj, Sheromani, Kumar Nath, Ranjit, Yadav, Vandana, Mishra, Girish, Dwivedi, S.K., Tewari, Roma, Narain, V.S., Mishra, Meenakshi, Chandra, Sharad, Patel, Shivali, Singh, Suman, Wander, Gurpreet S., Tandon, Rohit, Ralhan, Sarju, Kaur, Baljeet, Aslam, Naved, Gupta, Sonika, Goyal, Abhishek, Bhargava, Balram, Suvarna, Chandini, Karthikeyan, G., Ramakrishnan, S., Seth, Sandeep, Yadav, Rakesh, Singh, Sandeep, Roy, Ambuj, Parakh, Neeraj, Kumar Verma, Sunil, Narang, Rajiv, Mishra, Sundeep, Naik, Nitish, Sharma, Gautam, Kumar Choudhary, Shiv, Patel, Chetan, Gulati, Gurpreet, Sharma, Sanjeev, Bahl, V K, Mathew, Anoop, Mannekkattukudy Kurian, Binoy, Punnoose, Eapen, Avdhoot Gadkari, Milind, Rupesh Karwa, Sheetal, Gadage, Siddharth, Kolhe, Suvarna, Umesh Pillay, Tapan, Satheesh, Santhosh, Vindhya, R. J., Jain, Peeyush, Seth, Ashok, Singh Meharwal, Zile, Mathur, Atul, Verma, Atul, Kaul, Upendra, Bhatia, Mona, Sachdeva, Ankush, Indira Devi, Thounaojam, Jungla, Nungshi, Christopher, Johann, Manjula Rani, K., Menon, Rajeev, Sowjanya Reddy, M., Kumar, Nirmal, Preethi, K., Oomman, Abraham, sidh, Rinu R, Mao, Robert, Ramakrishnan, T., Solomon, Hilda, Francis, Rajesh, Naik, Sudhir, Vamshi, Priya P., Parveen Khan, Sajeeda, Christopher, Johann, Preethi, Kotiboinna, Kumar, Nirmal, Grant, Purvez, Hande, Shweta, Sonawane, Poonam, Kachru, Ranjan, Dubey, Abhishek, Rawat, Kavita, Kumar, Ajit, Ganapathi, Sanjay, K, Jayakumar, CP, Vineeth, Sivadasanpillai, Harikrishnan, Chacko, Manas, Sasidharan, Bijulal, Babu, Suresh, TR, Kapilamoorthy, Christopher, Johann, Reddy, Sowjanya, Polamuri, Praneeth, Rani, Manjula, Kaul, Upendra, Arambam, Priyadarshani, Singh, Bebek, Senior, Roxy, Fox, Keith AA, Young, Grace M., Carruthers, Kathryn, Senior, Roxy, Elghamaz, Ahmed, Gurunathan, Sothinathan, Karogiannis, Nikolaos, Young, Grace M., Shah, Benoy N, Kinsey, Christopher, Trimlett, Richard HJ, Kavalakkat, Raisa, Rubens, Michael B, Evans, Jo, Nicol, Edward D, Hassan, Ikraam, Mittal, Tarun K, Hampson, Reinette, Andreas Gamma, Reto, Williams, Sarah, Holland, Kim, Swan, Karen, de Belder, Mark A, Atkinson, Bev, Thambyrajah, Jeet, Kunhunny, Swapna, Davies, John R, Lindsay, Steven J., Atkinson, Craig, Kurian, John, Krannila, Carita, Jamil, Haqeel, Vinod, Manitha, Raheem, Osama, Hoye, Angela, Chaytor, Lisa, Cox, Leanne, Morrow, Julie, Rowe, Kay, Donnelly, Patrick, Kelly, Stephanie, Valecka, Bernardas, Regan, Susan, Turnbull, Dawn, Chauhan, Anoop, Fleming, Catherine, Ghosh, Arijit, Gratrix, Karen, Preston, Stephen, Barr, Craig, Cartwright, Anne, Alfakih, Khaled, Knighton, Abigail, Byrne, Jonathan, Martin, Katherine, Webb, Ian, Henriksen, Peter, Flint, Laura, Harrison, James, OKane, Peter, Lakeman, Nicki, Ljubez, Anja, de Silva, Ramesh, Conway, Dwayne S. G., Wright, Judith, Exley, Donna, Sirker, Alexander A, Andiapen, Mervyn, Richards, Amy J., Hoole, Stephen P, Wong, Lisa, Witherow, Fraser N., Munro, Melanie J., Johnston, Nicola, Harbinson, Mark, McEvoy, Michelle, Walsh, Simon, Brown, Caroline, Douglas, Hanna, Luckie, Matthew, Charles, Thabitha, Kolakaluri, Laurel, Phillips, Hannah, Sobolewska, Jolanta, Morby, Louise, Hallett, Karen, Corbett, Carolyn, Winstanley, Lynne, Jeetley, Paramjit, Smit, Angelique, Patel, Niket, Kotecha, Tushar, Travill, Christopher, Gent, Susan, Karimullah, Iqbal, Hussain, Nafisa, Al-Bustami, Mahmud, Braganza, Denise, Haines, Fiona, Taaffe, Joanne, Henderson, Robert, Burton, Jane, Pointon, Kate, Colton, Maria, Naik, Surendra, King, Rachel, Mathew, Thomas, Brown, Ammani, Docherty, Andrew, Berry, Colin, McCloy, Lisa, Collison, Damien, Robb, Kate, Roditi, Giles, Paterson, Craig, Crawford, Wenda, Kelly, Joanne, McGregor, Lorraine, Moriarty, Andrew J, Mackin, Anne, Glover, Jason D., Knight, Janet P, Pradhan, Jiwan, Mikhail, Ghada, Bose, Tuhina, Francis, Darrel P., Dzavik, Vladimir, Goodman, Shaun, Gosselin, Gilbert, Gosselin, Gilbert, Proietti, Anna, Brousseau, Myriam, Corfias, Magalie, Blaise, Patricia, Harvey, Luc, Diaz, Ariel, Rheault, Philippe, Barrero, Miguel, Gagné, Carl-Éric, Alarie, Patricia, Pépin-Dubois, Yanek, Arcand, Linda, Costa, Ricardo, Roy, Isabelle, Tung Sia, Ying, Montpetit, Estelle, Lemay, Catherine, Gisbert, Alejandro, Gervais, Pierre, Rheault, Alain, Drouin, Katia, Carl Phaneuf, Denis, Bergeron, Christine, Gosselin, Gilbert, Shelley, Christine, Masson, Christine, Garg, Pallav, Carr, Sandy, Bone, Catherine, Chow, Benjamin J.W., Moga, Ermina, Hessian, Renee C., Kourzenkova, Janetta, Beanlands, Rob S., Walter, Olga, Davies, Richard F., Bainey, Kevin R., Hogg, Norma, Welsh, Suzanne, Cheema, Asim N., Bagai, Akshay, Wald, Ron, Goodman, Shaun, Kushniriuk, Khrystyna, Joseph Graham, John, Hussain, Mohammed, Peterson, Mark, Bello, Olugbenga, Chow, Chi-Ming, Abramson, Beth, Nazir Cheema, Asim, Syed, Ishba, Hussain, Mohammed, Kushniriuk, Khrystyna, Cha, James, Otis, Judy, Otis, Rebecca, Howarth, Andrew G, Seib, Michelle M, Rivest, Sandra M, Sandonato, Rosa, Wong, Graham, Chow, Jackie, Starovoytov, Andrew, Uchida, Naomi, Meadows, Ngaire, Uxa, Amar, Asif, Nadia, Tavares, Suzana, Galiwango, Paul, Bozek, Bev, Kassam, Saleem, Shier, Maria, Mukherjee, Ashok, Larmand, Lori-Ann, Ricci, A. Joseph, Janmohamed, Amir, Hart, Brenda, Lam, Andy, Marucci, Jane, Tai, Sharon, Mehta, Shamir, Brons, Sonya, Beck, Chris, Wong, Glenda, Etherington, Krystal, Arumairajah, Thippeekaa, Udell, Jacob, Aprile, Maria, Karlsson, Sara, Webber, Susan, Généreux, Philippe, Mercure, Chantale, Hameed, Adnan, Aedy, Nancy, Daba, Ledjalem, Farquharson, Fran, Siddiqui, Anam, Carlos Carvalho, Antonio, Lopes, Renato D., Hueb, Whady, Emy Takiuti, Myrthes, Cury Rezende, Paulo, Eustáquio Ribeiro Silva, Expedito, Ciappina Hueb, Alexandre, Pizzol Caetano, Leonardo, Schaan de Quadros, Alexandre, Abdala Karam Kalil, Renato, Peixoto Deiro, Aline, Luiz da Costa Vieira, José, Manica Muller, Alice, Antonieta Pereira de Moraes, Maria, Píccaro de Oliveira, Pedro, Maria Ascoli, Bruna, Bridi, Leonardo, Zottis Poletti, Sílvia, Savaris, Simone, Vitola, João V, Cerci, Rodrigo J, Zier, Sandra S., Farias, Fabio R, Veiga Jr, Vilmar, Fernandes, Miguel M, Antonio Marin-Neto, José, Schmidt, André, de Oliveira Lima Filho, Moysés, Franca da Cunha, Diego, Mendes Oliveira, Ricardo, Reynaldo Abbud Chierice, João, Polanczyk, Carísi A., Rucatti, Guilherme G, Furtado, Mariana V., Igansi, Fernanda, Smidt, Luis F., Haeffner, Mauren P, Carlos Carvalho, Antonio, Almeida, Viviane, Pucci, Gustavo, Sanchez de Souza, Gabriela, Lyra, Flavio, Rabelo Alves Junior, Alvaro, Almeida, Mayana, dos Santos, Viviane, Dracoulakis, Marianna D. A., Oliveira, Natalia S, Lima, Rodolfo G. S. D, Figueiredo, Estevao, Edilena Paulino Azevedo, Bruna, Ricardo Caramori, Paulo, Bizzaro Santos, Marco, Germann, Amanda, Gomes, Vitor, Homem, Rosa, Magedanz, Ellen, Tumelero, Rogerio, Laimer, Rosane, Tognon, Alexandre, Dall’Orto, Frederico, Mesquita, Claudio T., Santos, Roberta P, Colafranseschi, Alexandre S., Oliveira, Amarino C., Carvalho, Luiz A., Palazzo, Isabella C., Sousa, Andre S., Eustáquio Ribeiro da Silva, Expedito, Gabriel Melo de Barros e Silva, Pedro, Yumi Okada, Mariana, de Pádua Silva Baptista, Luciana, Paula Batista, Ana, Jamus Rodrigues, Marcelo, Nogueira Rabaça, Aline, Valério Coimbra de Resende, Marcos, Francisco Saraiva, Jose, Miranda Trama, Larissa, Silva, Talita, Thais de Souza Ormundo, Camila, Vicente, Carla, Costantini, Costantino, Pinheiro, Caroline, Komar, Daniele, Szwed, Hanna, Demkow, Marcin, Kepka, Cezary, Teresinska, Anna, Walesiak, Olga, Kryczka, Karolina, Malinowska, Katarzyna, Henzel, Jan, Solecki, Mateusz, Kaczmarska, Edyta, Mazurek, Tomasz, Maksym, Jakub, Wojtera, Karolina, Fojt, Anna, Szczerba, Ewa, Drozdz, Jaroslaw, Czarniak, Bartosz, Frach, Malgorzata, Szymczyk, Konrad, Niedzwiecka, Iwona, Sobczak, Sebastian, Ciurus, Tomasz, Jakubowski, Piotr, Misztal-Teodorczyk, Magdalena, Teodorczyk, Dawid, Swiderek, Marta, Fratczak, Aleksandra, Wojtala, Ewelina, Szkopiak, Marcin, Lebioda, Patrycja, Wlodarczyk, Michal, Plachcinska, Anna, Kusmierek, Jacek, Miller, Magdalena, Marciniak, Halina, Wojtczak-Soska, Karolina, Łuczak, Katarzyna, Tarchalski, Tomasz, Cichocka-Radwan, Anna, Szwed, Hanna, Karwowski, Jaroslaw, Anna Szulczyk, Grazyna, Witkowski, Adam, Kukuła, Krzysztof, Celińska-Spodar, Małgorzta, Zalewska, Joanna, Gajos, Grzegorz, Bury, Krzysztof, Pruszczyk, Piotr, Łabyk, Andrzej, Roik, Marek, Szramowska, Agnieszka, Zdończyk, Olga, Łoboz-Grudzień, Krystyna, Jaroch, Joanna, Sokalski, Leszek, Brzezińska, Barbara, Lesiak, Maciej, Łanocha, Magdalena, Reczuch, Krzysztof W., Kolodziej, Adam, Kalarus, Zbigniew, Swiatkowski, Andrzej, Szulik, Mariola, Musial, Wlodzimierz J., Marcinkiewicz-Siemion, Marta, Bockeria, Olga, Bockeria, Leo, Bockeria, Olga, Petrosyan, Karen, Kudzoeva, Zalina, Trifonova, Tatiana, Aripova, Nodira, Chernyavskiy, Alexander M., Naryshkin, Ivan A., Kretov, Evgeniy I., Kuleshova, Alena, Grazhdankin, Igor O., Malaev, Dastan, Bershtein, Leonid L., Sayganov, Sergey A., Subbotina, Irina, Kuzmina-Krutetskaya, Anastasia M., Gumerova, Victoria, Zbyshevskaya, Elizaveta V., Katamadze, Nana O., Nikolaeva, Olga B., Kozlov, Pavel S., Kozulin, Vikentiy Y., Lubinskaya, Ekaterina I., Luis Lopez-Sendon, Jose, Castro, Almudena, Lopez-Sendon, Jose, Fernández-Figares, Virginia, Castro, Almudena, Refoyo Salicio, Elena, Guzman, Gabriela, Galeote, Gabriel, Valbuena, Silvia, Peteiro, Jesús, Dolores Martínez-Ruíz, María, Pérez-Fernández, Ruth, Blanco-Calvo, Moisés, Cuenca-Castillo, José J, Alonso-Álvarez, Encarnación, Flores-Ríos, Xacobe, García-González, Paula, Prada-Delgado, Óscar, Barge-Caballero, Gonzalo, Ramon Gonzalez Juanatey, Jose, Seijas Amigo, Jose, Souto Bayarri, Miguel, Pubull Nuñez, Virginia, Ocaranza Sanchez, Raymundo, Cid Alvarez, Belen, Peña Gil, Carlos, Martinez Monzonis, Amparo, Sionis, Alessandro, Fernández Martínez, Ana, Vila Perales, Montserrat, Maria Padró, Josep, Serra Peñaranda, Antonio, García Picart, Joan, Ginel Iglesias, Antonino, Garcia-Moll Marimon, Xavier, Pons Lladó, Guillem, Carreras Costa, Francesc, Miro, Vicente, Igual, Begoña, Diez, Jose L, Calvillo, Pilar, Ortuño, F. Marin, Valdés Chávarri, M., Quintana Giner, M., Tello Montolliu, A., Romero Aniorte, A.I., Pinar Bermudez, E., Rivera Caravaca, JM., De La Morena, G., Gracida Blancas, Montserrat, Cañavate, Olga, Guerrero, Sonia, Riera, Silvia, Enrique Castillo Luena, Jose, Enrique Castillo Luena, Jose, Lasala, Maria, Fernandez-Aviles, Francisco, Lorenzo, Maria, Sobrino, Olga, Vazquez, Alexandra, Jiang, Lixin, Chen, Jiyan, Dong, Haojian, He, Peiyu, Xia, Chunli, Yang, Junqing, Zhong, Qi, Wu, Yongjian, Tian, Yanmeng, Li, Dongze, Ma, Yitong, Li, Xiaomei, Yang, Yining, Ma, Xiang, Yu, Zixiang, Zhao, Qian, Ji, Zheng, Li, Chunguang, Zhang, Lei, Zhao, Yu, Zhu, Bolin, Yang, Xinchun, Chen, Mulei, Chi, Hongjie, Wang, Yang, Zhang, Jing, Lin, Wenhua, Jing, Rui, Liu, Jingjing, Zeng, Hesong, Zhou, Qiang, Xu, Chang, Li, Zhuxi, Li, Junhua, Xiong, Luyang, Fu, Xin, Gao, Dan, Jiang, Dengke, Leng, Ran, Wang, Xutong, Yuan, Qianqian, Zhang, Lili, Yang, Bin, Bai, Ziliang, Li, Jianhua, Qi, Jie, Wang, Fei, Wang, Haitao, Yang, Bin, Yue, Zhou, Zhang, Zhulin, Wang, Songtao, Dong, Yumei, Mao, Jiajia, Zhang, Bin, Cheng, Gong, Li, Xiuhong, Yao, Xiaowei, Zhong, Nier, Zhou, Ning, Zhao, Yulan, Huang, Yaping, Zhou, Panpan, Fang, Xuehua, Su, Wei, Zeng, Qiutang, Kunwu, Yu, Peng, Yudong, Su, Xin, Su, Xi, Wang, Chen, Zhao, Yunhai, Li, Qingxian, Geng, Yaming, Wang, Yanfu, Nie, Shao-ping, Fan, Jing-yao, Feng, Si-ting, Wang, Xiao, Yan, Yan, Zhang, Hui-min, Yu, Qin, Chi, Lingping, Liu, Fang, Wang, Jian’an, Chen, Han, Jiang, Jun, Li, Huajun, Wang, Jian’an, Han, Yechen, Xu, Lihong, Zhang, Shuyang, Liu, Zhenyu, Liu, Zhenyu, Chen, Gang, Hu, Rongrong, Maggioni, Aldo P., Piero Perna, Gian, Pietrucci, Francesca, Marini, Marco, Gabrielli, Gabriele, Provasoli, Stefano, Di Donato, Anna, Verna, Edoardo, Monti, Lorenzo, Nardi, Barbara, Di Chiara, Antonio, Pezzetta, Francesca, Mortara, Andrea, Casali, Valentina, Galvani, Marcello, Attanasio, Chiara, Ottani, Filippo, Sicuro, Marco, Leone, Gianpiero, Pisano, Francesco, Bare, Cristina, Calabro, Paolo, Fimiani, Fabio, Formisano, Tiziana, Tarantini, Giuseppe, Barioli, Alberto, Cucchini, Umberto, Ramani, Federica, Luigi Andres, Anto, Racca, Emanuela, Rolfo, Fabrizio, Goletto, Cecilia, Briguori, Carlo, De Micco, Francesca, Amati, Roberto, Di Marco, Stefano, Vergoni, William, Tricoli, Martina, Russo, Aldo, Villella, Massimo, Fanelli, Raffaele, Douglas White, Harvey, Alsweiler, Caroline, Poh, Kian-Keong, Chai, Ping, Lau, Titus, Loh, Joshua P., Tay, Edgar L., Teoh, Kristine, Tan, Sik-Yin V, Teo, Lynette L., Sia, Winnie C, Ong, Ching-Ching, Leong, Audrey W, Wong, Raymond C., Loh, Poay-Huan, Kofidis, Theodoros, Xian Chan, Wan, Hui Chan, Koo, Foo, David, Hai Yan, Li, Loh Kwok Kong, Jason, Min Er, Ching, Haider Jafary, Fahim, Chua, Terrance, Ismail, Nasrul, Tun Kyaw, Min, Yip, Deborah, Doerr, Rolf, Doerr, Rolf, Stumpf, Juergen, Grahl, Dorit, Matschke, Klaus, Guenther, Franziska, Simonis, Gregor, Bonin, Kerstin, Kadalie, Clemens T., Sechtem, Udo, Wenzelburger, Ina, Ong, Peter, Gruensfelder, Susanne, Christian Schulze, P., Goebel, Bjoern, Lenk, Karsten, Nickenig, Georg, Sinning, Jan-Malte, Weber, Marcel, Werner, Nikos, Marthe Lang, Irene, Huber, Kurt, Schuchlenz, Herwig, Steinmaurer, Gudrun, Weikl, Stefan, Marthe Lang, Irene, Winter, Max-Paul, Andric, Tijana, Huber, Kurt, Tscharre, Maximilian, Jakl-Kotauschek, Gabriele, Wegmayr, Claudia, Jäger, Bernhard, Egger, Florian, Keltai, Matyas, Vertes, Andras, Sebo, Judit, Davidovits, Zoltan, Matics, Laszlone, Varga, Albert, Ágoston, Gergely, Fontos, Geza, Dekany, Gabor, Merkely, Bela, Bartykowszki, Andrea, Maurovich-Horvat, Pal, Kerecsen, Gabor, Jakal, Agnes, Hinic, Sasa, Djokic, Jelena, Zdravkovic, Marija, Mudrenovic, Vladan, Crnokrak, Bogdan, Beleslin, Branko D., Boskovic, Nikola N., Djordjevic-Dikic, Ana D., Petrovic, Marija T., Giga, Vojislav L., Dobric, Milan R., Stepanovic, Jelena J., Markovic, Zeljko Z., Mladenovic, Ana S., Cemerlic-Adjic, Nada, Velicki, Lazar, Kamenica, Sremska, Pupic, Ljiljana, Davidović, Goran, Simović, Stefan M., Vučić, Rada, Dekleva, Milica Nikola, Martinovic, Miroslav Stevo, Stevanovic, Gordana, Stankovic, Goran, Dobric, Milan, Apostolovic, Svetlana, Martinovic, Sonja Salinger, Stanojevic, Dragana, Escobedo, Jorge, Jesús-Pérez, Ramon de, Juarez, Benito, Baleón-Espinosa, Rubén, Campos-Santaolalla, Arturo S, Durán-Cortés, Elihú, Flores-Palacios, José M, García-Rincón, Andrés, Jiménez-Santos, Moisés, Peñafiel, Joaquín V, Ortega-Ramírez, José A, Valdespino-Estrada, Aquiles, Rosas, Erick Alexánderson, Canales Brassetti, María Fernanda, Vences Anaya, Diego Adrián, García, María Pérez, Carvajal Juarez, Isabel Estela, Rovalo, Magdalena Madero, Morales Rodríguez, Erick Donato, Selvanayagam, Joseph B., Rankin, Jamie, Murphy, Deirdre, Selvanayagam, Joseph B., Lee, Sau, Joseph, Majo X., Thomas, Prince, Thambar, Suku T., Chaplin, Melissa D, Boer, Stephanie C, Beltrame, John F., Stansborough, Jeanette K., Black, Marilyn, Hillis, Graham S., Bonner, Michelle M., Ireland, Kim F., Venn-Edmonds, Clare, Steg, Philippe-Gabriel, Abergel, Helene, Juliard, Jean-Michel, Thobois, Corine, Pasteur, C.H. Louis, Thuaire, Christophe, Tachot, Emilie, Dutoiu, Téodora, Laure, Christophe, Vassaliere, Christel, Steg, Philippe Gabriel, Abergel, Helene, Juliard, Jean-Michel, Fuentes, Axelle, Slama, Michel S., Eliahou, Ludivine, Cedex, Clamart, El Mahmoud, Rami, Dubourg, Olivier, Michaud, Pierre, Nicollet, Eric, Hadjih, Sarah, Cedex, Corbeil-Essonnes, Goube, Pascal, Brito, Patricia, Barone-Rochette, Gilles, Barone-Rochette, Gilles, Furber, Alain, Cornet, Charles, Bière, Loïc, Rautureau, Jeremy, Juceviciene, Agne, Kalibataite-Rutkauskiene, Irma, Keinaite, Laura, Laucevicius, Aleksandras, Laukyte, Monika, Celutkiene, Jelena, Mikolaitiene, Gelmina, Smigelskaite, Akvile, Tamasauskiene, Ilona, Urboniene, Agne, Kedhi, Elvin, Klinieken, Isala, Timmer, Jorik, Bouwhuis, Ilse, Hermanides, Rik, Nijmeijer, Lia, Kaplan, Eliza, Riezebos, Robert K., Samadi, Pouneh, Schoep Jeannette, J. M., Dongen, Elise van, Janzen, Elisabeth M., Niehe, Sander R., Suryapranata, Harry, Ahoud, Sandra, Vugt, Stijn van, Ramos, Ruben, Santa Marta, Hospital de, Cacela, Duarte, Santana, Ana, Fiarresga, Antonio, Sousa, Lidia, Marques, Hugo, Patricio, Lino, Selas, Mafalda, Bernanrdes, Luis, Silva, Filipa, Rio, Pedro, Freixo, Cláudia, Carvalho, Ramiro, Ferreira, Rui, Silva, Tiago, Rodrigues, Ines, Modas, Pedro, Portugal, Guilherme, Fragata, Jose, Pinto, Fausto J., Cabrita, Inês Zimbarra, Menezes, Miguel Nobre, Rocha, Andreia, Lopes, Guilhermina Cantinho, Figueiras, Francisca Patuleia, Almeida, Ana Gomes, Coelho, Andreia, CanVas Silva, Pedro, Capinha, Marta, Nobre, Angelo, Caetano, Maria Inês, Francisco, Ana Rita, Silva, Susana, Ferreira, Nuno, de Gaia, Vila Nova, Lopes, Ricardo L., Diaz, Rafael, Guzman, Luis, Tinnirello, Veronica, Figal, Julio César, Nicolás Mungo, Matías, Buenos Aires, Ciudad Autonoma de, Méndiz, Oscar, Cortés, Claudia, Favaloro, Roberto René, Alvarez, Carlos, Garcia, Marina, Blanca, Bahia, Courtis, Javier, Godoy, Valeria, Zeballos, Gabriela, Schiavi, Lilia, Actis, Maria Victoria, Rubio, Mariano, Scaro, Graciela, White, Harvey Douglas, Alsweiler, Caroline, Devlin, Gerard Patrick, Low, Liz, Fisher, Raewyn, Scales, Jayne, Abercrombie, Kirsty, Stewart, Ralph Alan Huston, Howell, Leah, White, Harvey Douglas, Patten, Cathrine, Benatar, Jocelyne, Kedev, Sasko, Mitevska, Irena Peovska, Kostovska, Elizabeta Srbinovska, Pejkov, Hristo, Held, Claes, Held, Claes, Eggers, Kai, Frostfelt, Gunnar, Björklund, Christina, Johnston, Nina, Andreasson, Maria, Olsowka, Maciej, Essermark, Marie, Åkerblom, Axel, Soveri, Inga, Aspberg, Johannes, Persson, Liselotte, Beyar, Rafael, Sharir, Tali, Nikolsky, Eugenia, Sharir, Tali, Harel, Or, Elian, Dan, Kerner, Arthur, Bentzvi, Margalit, Massalha, Samia, Helmer, Ludmila, Kohsaka, Shun, Fukuda, Keiichi, Ueda, Ikuko, Kohsaka, Shun, Fujita, Jun, Yasuda, Satoshi, Furukawa, Akemi, Hirase, Kanae, Nagai, Toshiyuki, Otsuka, Fumiyuki, Nishimura, Shigeyuki, Nakano, Shintaro, de Werf, Frans Van, Goetschalckx, Kaatje, Goetschalckx, Kaatje, Robesyn, Valerie, de Werf, Frans Van, Claes, Kathleen, White, Harvey Douglas, Alsweiler, Caroline, Hung, Chung-Lieh, Yang, Yi-Hsuan, Yun, Chun-Ho, Hou, Charles Jia-Yin, Kuo, Jen-Yuan, Yeh, Hung-I, Hung, Ta-Chuan, Li, Jiun-Yi, Chien, Chen-Yen, Tsai, Cheng-Ting, Liu, Chun-Chieh, Yu, Fa-Chang, Lin, Yueh-Hung, Lan, Wei-Ren, Yen, Chih-Hsuan, Tsai, Jui-Peng, Sung, Kuo-Tzu, Ntsekhe, Mpiko, Pandie, Shaheen, Philander (Nee Talliard), Constance, Viljoen, Charle A, Mtana, Noloyiso, De Andrade, Marianne, Maggioni, Aldo P., Moccetti, Tiziano, Anesini, Adriana, Rossi, M.Grazia, Maspoli, Simona, Mombelli, Manuela, Abdelhamid, Magdy, Talaat, Ahmed, Adel, Ahmed, Kamal, Ahmed, Mahrous, Hossam, Kaffas, Sameh El, Fishawy, Hussien El, Pop, Calin, Claudia, Matei, Popescu, Bogdan A., Ginghina, Carmen, Rosca, Monica, Deleanu, Dan, Beladan, Carmen C., Iliescu, Vlad A., Al-Mallah, Mouaz H., Zahrani, Sarah, Aljzeeri, Ahmed, Najm, Hani, Alghamdi, Ali, Mogrovejo Ramos, Walter Enrique, Monsalve Davila, Marco Antonio, White, Harvey Douglas, Alsweiler, Caroline, Kuanprasert, Srun, Mai, Chiang, Prommintikul, Arintaya, Nawarawong, Weerachai, Khwakhong, Supatchara, Woragidpoonpol, Surin, Chaiyasri, Anong, Tepsuwan, Thitipong, Mekara, Warangkana, Taksaudom, Noppon, Kulthawong, Supap, Rimsukcharoenchai, Chataroon, Amaritakomol, Anong, Euathrongchit, Juntima, Wannasopha, Yutthaphan, Yamwong, Sukit, Panpunuan, Pachara, Sritara, Piyamitr, Aramcharoen, Suthara, Meemuk, Krissada, White, Harvey Douglas, Alsweiler, Caroline, Khairuddin, Ahmad, Mokhtar, Noor Syamira, Hadi, Hafidz Abd, Basri, Nor Asiah, Yahaya, Shaiful Azmi, Yusnida, Irni, Hashim, Humayrah, Harrington, Robert, Williams, David, Alexander, Karen P., Berger, Jeffrey, Harrington, Robert, Mark, Daniel, O’Brien, Sean M., Rosenberg, Yves, Shaw, Leslee J., Ballantyne, Christie, Berman, Daniel, Beyar, Rafael, Bhargava, Balram, Buller, Chris, (Tony) Carvalho*, Antonio, Chaitman, Bernard R., Diaz, Rafael, Doerr, Rolf, Dzavik, Vladimir, Goodman, Shaun, Gosselin, Gilbert, Hachamovitch, Rory, Hamm, Christian, Held, Claes, Helm, Malte, Huber, Kurt, Jiang, Lixin, Keltai, Matyas, Kohsaka, Shun, Lang, Irene, Lopes, Renato, Lopez-Sendon, Jose, Maggioni, Aldo, Bairey Merz, C. Noel, Min, James, Peterson, Eric, Picard, Michael H., Selvanayagam, Joseph, Senior, Roxy, Sharir, Tali, Steg, Gabriel, Szwed, Hanna, de Werf, Frans Van, Weintraub, William, White, Harvey, Williams, David, Ballantyne, Christie, Calfas*, Karen, Chaitman, Bernard R., Champagne, Mary Ann, Davidson, Michael, Fleg, Jerome, McCullough, Peter A., Stone, Peter, Menasche, Philippe, Davidson*, Michael, Fremes, Stephen, Guyton, Robert, Mack, Michael, Mohr, Fred, Rao, Anupama, Sabik, Joe, Shapira, Oz, Taggart, David, Tatoulis, James, Williams, David, Blankenship, Jim, Brener, Sorin, Buller, Chris, Colombo, Antonio, Bruyne, Bernard de, Généreux, Philippe, Harrington, Robert, Kereiakes, Dean, Lefevre, Thierry, Moses, Jeffrey, Chaitman, Bernard R., Alexander, Karen P., Mahaffey, Ken, White, Harvey, Chaitman, Bernard R., Cruz-Flores, Salvador, Danchin, Nicholas, Feen, Eli, Garcia, Mario J., Hauptman, Paul, Laddu, Abhay A., Passamani, Eugene, Pina, Ileana L., Simoons, Maarten, Skali, Hicham, Thygesen, Kristian, Waters, David, Alexander, Karen P., Endsley, Patricia, Esposito, Gerard, Kanters, Jeffrey, Pownall, John, Stournaras, Dimitrios, Shaw, Leslee J., Berman, Daniel, Friedrich, Matthias, Hachamovitch, Rory, Kwong, Raymond, Min, James, Oliver, Dana, Picard, Michael H., Harrell, Frank, Blume, Jeffrey, Lee, Kerry, O’Brien, Sean M., Berger, Jeffrey, Held, Claes, Kullo, Iftikhar, McManus, Bruce, Newby, Kristin, Mark, Daniel, Cohen, David, Weintraub, William, Merz, C. Noel Bairey, Bugiardini, Raffaele, Celutkiene, Jelena, Escobedo, Jorge, Hoye, Angela, Lyubarova, Radmila, Mattina, Deirdre, Peteiro, Jesus, Alexander, Karen P., Berger, Jeffrey, Harrington, Robert, O’Brien, Sean M., Rosenberg, Yves, Mark, Daniel, Mark, Daniel, Shaw, Leslee J., Berman, Dan, Chaitman, Bernard R., Fleg, Jerome, Kwong, Raymond, Picard, Michael H., Senior, Roxy, Min, James, Leipsic, Jonathan, Ali, Ziad, Williams, David, Fleg, Jerome, Berger, Jeffrey, Chaitman, Bernard R., Alexander, Karen P., Alexander, Karen P., Fleg, Jerome, Mathew, Roy, O’Brien, Sean M., Sidhu, Mandeep, Friedman, Lawrence, Anderson, Jeffrey, Berg, Jessica, DeMets, David, Gibson, C. Michael, Lamas, Gervasio, Deming, Nicole, Himmelfarb, Jonathan, Ouyang, Pamela, Woodard, Pamela, Harrell, Frank, Nwosu, Samuel, Rosenberg, Yves, Fleg, Jerome, Kirby, Ruth, Jeffries, Neal, Berger, Jeffrey, Sidhu, Mandeep, Denaro*, Jean E., Mavromichalis, Stephanie, Chan, Kevin, Cobb, Gia, Contreras, Aira, Cukali, Diana, Ferket, Stephanie, Gabriel, Andre, Hansen, Antonietta, Roberts, Arline, Chang, Michelle, Islam, Sharder, Wayser, Graceanne, Yakubov, Solomon, Yee, Michelle, Callison, Caroline, Hogan, Isabelle, Qelaj, Albertina, Pirro, Charlotte, Loo, Kerrie Van, Wisniewski, Brianna, Gilsenan, Margaret, Lang, Bevin, Mohamed, Samaa, Esquenazi-Karonika, Shari, Mathews, Patenne, Naumova, Anna, Lyo, Jihyun, Setang, Vincent, Xavier, Mark, O’Brien, Sean M., Alexander, Karen P., Mark, Daniel B., Anstrom, Kevin, Baloch, Khaula, Blount, Janet, Cowper, Patricia, Davidson-Ray, Linda, Drew, Laura, Harding, Tina, Knight, J David, Liu, Diane Minshall, O’Neal, Betsy, Redick, Thomas, Jones, Philip, Nugent, Karen, Wang, Grace Jingyan, Shaw, Leslee J., Phillips, Lawrence, Goyal, Abhinav, Hetrick, Holly, Oliver, Dana, Berman, Daniel, Hayes, Sean W., Friedman, John D., Gerlach, R. James, Hyun, Mark, Miranda-Peats, Romalisa, Slomka, Piotr, Thomson, Louise, Kwong, Raymond Y., Friedrich, Matthias, Mongeon, Francois Pierre, Michael, Steven, Picard, Michael H., Hung, Judy, Scherrer-Crosbie, Marielle, Zeng, Xin, Chaitman, Bernard R., Eckstein, Jane, Guruge, Bandula, Streif, Mary, Ali, Ziad, Genereux, Philippe, Alfonso, Maria A., Corral, Maria P., Garcia, Javier J., Horst, Jennifer, Jankovic, Ivana, Konigstein, Maayan, Lustre, Mitchel B., Peralta, Yolayfi, Sanchez, Raquel, Min, James, Arsanjani, Reza, Budoff, Matthew, Elmore, Kimberly, Gomez, Millie, Hague, Cameron, Hindoyan, Niree, Leipsic, Jonathan, Nakanishi, Rine, Srichai-Parsia, M. Barbara, Yeoh, Eunice, Youn, Tricia, Maggioni, Aldo P., Bianchini, Francesca, Ceseri, Martina, Lorimer, Andrea, Magnoni, Marco, Orso, Francesco, Sarti, Laura, Tricoli, Martinia, Carvalho, Antonio, Lopes, Renato, Barbosa, Lilian Mazza, Duarte, Tauane Bello, Soares, Tamara Colaiácovo, Aveiro Morata, Julia de, Carvalho, Pedro, Carvalho Maffei, Natalia de, Egydio, Flávia, Kawakami, Anelise, Oliveira, Janaina, Piloto, Elissa Restelli, Pozzibon, Jaqueline, Goodman, Shaun, Camara, Diane, Mowafy, Neamat, Spindler, Caroline, Jiang, Lixin, Dai, Hao, Feng, Fang, Li, Jia, Li, Li, Liu, Jiamin, Xie, Qiulan, Zhang, Haibo, Zhang, Jianxin, Zhang, Lihua, Zhang, Liping, Zhang, Ning, Zhong, Hui, Diaz, Rafael, Escobar, Claudia, Martin, Maria Eugenia, Pascual, Andrea, Lopez-Sendon, José, Moraga, Paloma, Hernandez, Victoria, Castro, Almudena, Posada, Maria, Fernandez, Sara, Villanueva, José Luis Narro, Selgas, Rafael, Steg, Gabriel, Abergel, Helene, Juliard, Jean Michel, White, Harvey, Alsweiler, Caroline, de Werf, Frans Van, Claes, Kathleen, Goetschalckx, Kaatje, Luyten, Ann, Robesyn, Valerie, Selvanayagam, Joseph B., Murphy, Deirdre, Ahmed, Asker, Bhatt, Richa, Chadha, Nitika, Kumar, Vijay, Lubna, Sadath, Naik, Pushpa, Pandey, Shruti, Ramasamy, Karthik, Saleem, Mohammed, Sharma, Pratiksha, and Siddaram, Hemalata

Published
2024
Full Text
View/download PDF

22. RINDNet: Edge Detection for Discontinuity in Reflectance, Illumination, Normal and Depth

Author

Pu, Mengyang, Huang, Yaping, Guan, Qingji, and Ling, Haibin

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

As a fundamental building block in computer vision, edges can be categorised into four types according to the discontinuity in surface-Reflectance, Illumination, surface-Normal or Depth. While great progress has been made in detecting generic or individual types of edges, it remains under-explored to comprehensively study all four edge types together. In this paper, we propose a novel neural network solution, RINDNet, to jointly detect all four types of edges. Taking into consideration the distinct attributes of each type of edges and the relationship between them, RINDNet learns effective representations for each of them and works in three stages. In stage I, RINDNet uses a common backbone to extract features shared by all edges. Then in stage II it branches to prepare discriminative features for each edge type by the corresponding decoder. In stage III, an independent decision head for each type aggregates the features from previous stages to predict the initial results. Additionally, an attention module learns attention maps for all types to capture the underlying relations between them, and these maps are combined with initial results to generate the final edge detection results. For training and evaluation, we construct the first public benchmark, BSDS-RIND, with all four types of edges carefully annotated. In our experiments, RINDNet yields promising results in comparison with state-of-the-art methods. Additional analysis is presented in supplementary material., Comment: Accepted by ICCV2021

Published
2021

27. Uncertainty Inspired Autism Spectrum Disorder Screening

Author

Zhang, Ying, Huang, Yaping, Qi, Jiansong, Zhang, Sihui, Tian, Mei, Tian, Yi, 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, Greenspan, Hayit, editor, Madabhushi, Anant, editor, Mousavi, Parvin, editor, Salcudean, Septimiu, editor, Duncan, James, editor, Syeda-Mahmood, Tanveer, editor, and Taylor, Russell, editor

Published
2023
Full Text
View/download PDF

35. Learning from Pixel-Level Label Noise: A New Perspective for Semi-Supervised Semantic Segmentation

Author

Yi, Rumeng, Huang, Yaping, Guan, Qingji, Pu, Mengyang, and Zhang, Runsheng

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

This paper addresses semi-supervised semantic segmentation by exploiting a small set of images with pixel-level annotations (strong supervisions) and a large set of images with only image-level annotations (weak supervisions). Most existing approaches aim to generate accurate pixel-level labels from weak supervisions. However, we observe that those generated labels still inevitably contain noisy labels. Motivated by this observation, we present a novel perspective and formulate this task as a problem of learning with pixel-level label noise. Existing noisy label methods, nevertheless, mainly aim at image-level tasks, which can not capture the relationship between neighboring labels in one image. Therefore, we propose a graph based label noise detection and correction framework to deal with pixel-level noisy labels. In particular, for the generated pixel-level noisy labels from weak supervisions by Class Activation Map (CAM), we train a clean segmentation model with strong supervisions to detect the clean labels from these noisy labels according to the cross-entropy loss. Then, we adopt a superpixel-based graph to represent the relations of spatial adjacency and semantic similarity between pixels in one image. Finally we correct the noisy labels using a Graph Attention Network (GAT) supervised by detected clean labels. We comprehensively conduct experiments on PASCAL VOC 2012, PASCAL-Context and MS-COCO datasets. The experimental results show that our proposed semi supervised method achieves the state-of-the-art performances and even outperforms the fully-supervised models on PASCAL VOC 2012 and MS-COCO datasets in some cases.

Published
2021
Full Text
View/download PDF

36. Transform consistency for learning with noisy labels

Author

Yi, Rumeng and Huang, Yaping

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

It is crucial to distinguish mislabeled samples for dealing with noisy labels. Previous methods such as Coteaching and JoCoR introduce two different networks to select clean samples out of the noisy ones and only use these clean ones to train the deep models. Different from these methods which require to train two networks simultaneously, we propose a simple and effective method to identify clean samples only using one single network. We discover that the clean samples prefer to reach consistent predictions for the original images and the transformed images while noisy samples usually suffer from inconsistent predictions. Motivated by this observation, we introduce to constrain the transform consistency between the original images and the transformed images for network training, and then select small-loss samples to update the parameters of the network. Furthermore, in order to mitigate the negative influence of noisy labels, we design a classification loss by using the off-line hard labels and on-line soft labels to provide more reliable supervisions for training a robust model. We conduct comprehensive experiments on CIFAR-10, CIFAR-100 and Clothing1M datasets. Compared with the baselines, we achieve the state-of-the-art performance. Especially, in most cases, our proposed method outperforms the baselines by a large margin.

Published
2021

37. Few-Shot Domain Adaptation for Grammatical Error Correction via Meta-Learning

Author

Zhang, Shengsheng, Huang, Yaping, Chen, Yun, Yang, Liner, Wang, Chencheng, and Yang, Erhong

Subjects
Computer Science - Computation and Language
Abstract

Most existing Grammatical Error Correction (GEC) methods based on sequence-to-sequence mainly focus on how to generate more pseudo data to obtain better performance. Few work addresses few-shot GEC domain adaptation. In this paper, we treat different GEC domains as different GEC tasks and propose to extend meta-learning to few-shot GEC domain adaptation without using any pseudo data. We exploit a set of data-rich source domains to learn the initialization of model parameters that facilitates fast adaptation on new resource-poor target domains. We adapt GEC model to the first language (L1) of the second language learner. To evaluate the proposed method, we use nine L1s as source domains and five L1s as target domains. Experiment results on the L1 GEC domain adaptation dataset demonstrate that the proposed approach outperforms the multi-task transfer learning baseline by 0.50 $F_{0.5}$ score on average and enables us to effectively adapt to a new L1 domain with only 200 parallel sentences.

Published
2021

38. Classification-driven Single Image Dehazing

Author

Pei, Yanting, Huang, Yaping, and Zhang, Xingyuan

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

Most existing dehazing algorithms often use hand-crafted features or Convolutional Neural Networks (CNN)-based methods to generate clear images using pixel-level Mean Square Error (MSE) loss. The generated images generally have better visual appeal, but not always have better performance for high-level vision tasks, e.g. image classification. In this paper, we investigate a new point of view in addressing this problem. Instead of focusing only on achieving good quantitative performance on pixel-based metrics such as Peak Signal to Noise Ratio (PSNR), we also ensure that the dehazed image itself does not degrade the performance of the high-level vision tasks such as image classification. To this end, we present an unified CNN architecture that includes three parts: a dehazing sub-network (DNet), a classification-driven Conditional Generative Adversarial Networks sub-network (CCGAN) and a classification sub-network (CNet) related to image classification, which has better performance both on visual appeal and image classification. We conduct comprehensive experiments on two challenging benchmark datasets for fine-grained and object classification: CUB-200-2011 and Caltech-256. Experimental results demonstrate that the proposed method outperforms many recent state-of-the-art single image dehazing methods in terms of image dehazing metrics and classification accuracy.

Published
2019

48. Unsupervised Part Mining for Fine-grained Image Classification

Author

Zhang, Runsheng, zhang, jian, Huang, Yaping, and Zou, Qi

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

Fine-grained image classification remains challenging due to the large intra-class variance and small inter-class variance. Since the subtle visual differences are only in local regions of discriminative parts among subcategories, part localization is a key issue for fine-grained image classification. Most existing approaches localize object or parts in an image with object or part annotations, which are expensive and labor-consuming. To tackle this issue, we propose a fully unsupervised part mining (UPM) approach to localize the discriminative parts without even image-level annotations, which largely improves the fine-grained classification performance. We first utilize pattern mining techniques to discover frequent patterns, i.e., co-occurrence highlighted regions, in the feature maps extracted from a pre-trained convolutional neural network (CNN) model. Inspired by the fact that these relevant meaningful patterns typically hold appearance and spatial consistency, we then cluster the mined regions to obtain the cluster centers and the discriminative parts surrounding the cluster centers are generated. Importantly, any annotations and sophisticated training procedures are not used in our proposed part localization approach. Finally, a multi-stream classification network is built for aggregating the original, object-level and part-level features simultaneously. Compared with other state-of-the-art approaches, our UPM approach achieves the competitive performance., Comment: 10 pages,4 figures

Published
2019

49. Object Discovery From a Single Unlabeled Image by Mining Frequent Itemset With Multi-scale Features

Author

Zhang, Runsheng, Huang, Yaping, Pu, Mengyang, Zhang, Jian, Guan, Qingji, Zou, Qi, and Ling, Haibin

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

TThe goal of our work is to discover dominant objects in a very general setting where only a single unlabeled image is given. This is far more challenge than typical co-localization or weakly-supervised localization tasks. To tackle this problem, we propose a simple but effective pattern mining-based method, called Object Location Mining (OLM), which exploits the advantages of data mining and feature representation of pre-trained convolutional neural networks (CNNs). Specifically, we first convert the feature maps from a pre-trained CNN model into a set of transactions, and then discovers frequent patterns from transaction database through pattern mining techniques. We observe that those discovered patterns, i.e., co-occurrence highlighted regions, typically hold appearance and spatial consistency. Motivated by this observation, we can easily discover and localize possible objects by merging relevant meaningful patterns. Extensive experiments on a variety of benchmarks demonstrate that OLM achieves competitive localization performance compared with the state-of-the-art methods. We also evaluate our approach compared with unsupervised saliency detection methods and achieves competitive results on seven benchmark datasets. Moreover, we conduct experiments on fine-grained classification to show that our proposed method can locate the entire object and parts accurately, which can benefit to improving the classification results significantly.

Published
2019
Full Text
View/download PDF

50. Does Haze Removal Help CNN-based Image Classification?

Author

Pei, Yanting, Huang, Yaping, Zou, Qi, Lu, Yuhang, and Wang, Song

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

Hazy images are common in real scenarios and many dehazing methods have been developed to automatically remove the haze from images. Typically, the goal of image dehazing is to produce clearer images from which human vision can better identify the object and structural details present in the images. When the ground-truth haze-free image is available for a hazy image, quantitative evaluation of image dehazing is usually based on objective metrics, such as Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity (SSIM). However, in many applications, large-scale images are collected not for visual examination by human. Instead, they are used for many high-level vision tasks, such as automatic classification, recognition and categorization. One fundamental problem here is whether various dehazing methods can produce clearer images that can help improve the performance of the high-level tasks. In this paper, we empirically study this problem in the important task of image classification by using both synthetic and real hazy image datasets. From the experimental results, we find that the existing image-dehazing methods cannot improve much the image-classification performance and sometimes even reduce the image-classification performance.

Published
2018

Catalog

Books, media, physical & digital resources
See catalog results