Are you over 18 and want to see adult content?
More Annotations
A complete backup of https://schmallenberger-sauerland.de
Are you over 18 and want to see adult content?
A complete backup of https://leggilanotizia.it
Are you over 18 and want to see adult content?
A complete backup of https://secarts.org
Are you over 18 and want to see adult content?
A complete backup of https://forexearlywarning.com
Are you over 18 and want to see adult content?
A complete backup of https://toonly.com
Are you over 18 and want to see adult content?
A complete backup of https://london.gov.uk
Are you over 18 and want to see adult content?
A complete backup of https://creativetime.org
Are you over 18 and want to see adult content?
A complete backup of https://wisconsinbudgetproject.org
Are you over 18 and want to see adult content?
A complete backup of https://partnerre.info
Are you over 18 and want to see adult content?
A complete backup of https://economatica.com
Are you over 18 and want to see adult content?
A complete backup of https://belisce.hr
Are you over 18 and want to see adult content?
A complete backup of https://scar.org
Are you over 18 and want to see adult content?
Favourite Annotations
A complete backup of https://amvnews.ru
Are you over 18 and want to see adult content?
A complete backup of https://nanjingmarketinggroup.com
Are you over 18 and want to see adult content?
A complete backup of https://sportmedia.tv
Are you over 18 and want to see adult content?
A complete backup of https://tutorjobsonline.com
Are you over 18 and want to see adult content?
A complete backup of https://biblhertz.it
Are you over 18 and want to see adult content?
A complete backup of https://racialprofilingessay.com
Are you over 18 and want to see adult content?
A complete backup of https://stoptorture.org.il
Are you over 18 and want to see adult content?
A complete backup of https://burdenbearersministries.org
Are you over 18 and want to see adult content?
A complete backup of https://bbvaopen4u.com
Are you over 18 and want to see adult content?
A complete backup of https://market-inspector.co.uk
Are you over 18 and want to see adult content?
A complete backup of https://radioszene.de
Are you over 18 and want to see adult content?
A complete backup of https://spreekbuis.nl
Are you over 18 and want to see adult content?
Text
Peter Stone
DISENTANGLED FEATURE LEARNING NETWORK FOR VEHICLE RE Vehicle Re-Identification (ReID) has attracted lots of research efforts due to its great significance to the public security. In vehicle ReID, we aim to learn features that are powerful in discriminating subtle differences between vehicles which are visually similar, and also robust against different orientations of the samevehicle.
ON DEEP UNSUPERVISED ACTIVE LEARNING On Deep Unsupervised Active Learning Changsheng Li1, Handong Ma2, Zhao Kang2, Ye Yuan1, Xiao-Yu Zhang3 and Guoren Wang1 1School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China 2SCSE, University of Electronic Science and Technology of China, Chengdu, China 3Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China EXPLOITING MUTUAL INFORMATION FOR SUBSTRUCTURE-AWARE GRAPH Exploiting Mutual Information for Substructure-aware Graph Representation Learning Pengyang Wang 1, Yanjie Fu , Yuanchun Zhou2, Kunpeng Liu1, Xiaolin Li3 and Kien Hua1 1University of Central Florida 2Computer Network Information Center, Chinese Academy of Sciences 3Nanjing University pengyang.wang@knights.ucf.edu, yanjie.fu@ucf.edu, zyc@cnic.cn, kunpengliu@knights.ucf.edu, PERSISTENT HOMOLOGY: AN INTRODUCTION AND A NEW TEXT Definition 9. Let S⊂G. The subgroup generated by S, S , is the subgroup of all elements of Gthat can expressed as the finite operation of elements in Sand their inverses. UNITRANS : UNIFYING MODEL TRANSFER AND DATA TRANSFER FOR UniTrans : Unifying Model Transfer and Data Transfer for Cross-Lingual Named Entity Recognition with Unlabeled Data Qianhui Wu, Zijia Lin, Börje F. Karlsson, Biqing Huang, Jian-Guang Lou MODELING BOTH CONTEXT- AND SPEAKER-SENSITIVE DEPENDENCE Recently, emotion detection in conversations becomes a hot research topic in the Natural Language Processing community. In this paper, we focus on emotion detection in multi-speaker conversations instead of traditional two-speaker conversations in existing studies. PROCEEDINGS OF THE TWENTY-NINTH INTERNATIONAL JOINT Pay Attention to Devils: A Photometric Stereo Network for Better Details Yakun Ju1, Kin-Man Lam2, Yang Chen1, Lin Qi1 and Junyu Dong1 1Department of Computer Science and Technology, Ocean University of China 2Department of Electronic and Information Engineering, The Hong Kong Polytechnic University fjuyakun, chenyang8484g@stu.ouc.edu.cn, kin.man.lam@polyu.edu.hk, fqilin, dongjunyug@ouc.edu.cn EXPLOITING PERSONA INFORMATION FOR DIVERSE GENERATION OF Exploiting Persona Information for Diverse Generation of Conversational Responses Haoyu Song1, Wei-Nan Zhang1;2, Yiming Cui1;3, Dong Wang3 and Ting Liu1;2 1Research Center for Social Computing and Information Retrieval, Harbin Institute of Technology, China 2Peng Cheng Laboratory, Shenzhen, China 3Joint Laboratory of HIT and iFLYTEK (HFL), iFLYTEK Research, Beijing, China METAMORPHIC TESTING AND CERTIFIED MITIGATION OF FAIRNESS5 Metamorphic Testing and Certified Mitigation of Fairness Violations in NLP Models Pingchuan Ma, Shuai Wang, Jin Liu A PENNY FOR YOUR THOUGHTS: THE VALUE OF COMMUNICATION IN2 A Penny for Your Thoughts: The Value of Communication in Ad Hoc Teamwork Reuth Mirsky, William Macke, Andy Wang, Harel Yedidsion,Peter Stone
DISENTANGLED FEATURE LEARNING NETWORK FOR VEHICLE RE Vehicle Re-Identification (ReID) has attracted lots of research efforts due to its great significance to the public security. In vehicle ReID, we aim to learn features that are powerful in discriminating subtle differences between vehicles which are visually similar, and also robust against different orientations of the samevehicle.
ON DEEP UNSUPERVISED ACTIVE LEARNING On Deep Unsupervised Active Learning Changsheng Li1, Handong Ma2, Zhao Kang2, Ye Yuan1, Xiao-Yu Zhang3 and Guoren Wang1 1School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China 2SCSE, University of Electronic Science and Technology of China, Chengdu, China 3Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China EXPLOITING MUTUAL INFORMATION FOR SUBSTRUCTURE-AWARE GRAPH Exploiting Mutual Information for Substructure-aware Graph Representation Learning Pengyang Wang 1, Yanjie Fu , Yuanchun Zhou2, Kunpeng Liu1, Xiaolin Li3 and Kien Hua1 1University of Central Florida 2Computer Network Information Center, Chinese Academy of Sciences 3Nanjing University pengyang.wang@knights.ucf.edu, yanjie.fu@ucf.edu, zyc@cnic.cn, kunpengliu@knights.ucf.edu, PERSISTENT HOMOLOGY: AN INTRODUCTION AND A NEW TEXT Definition 9. Let S⊂G. The subgroup generated by S, S , is the subgroup of all elements of Gthat can expressed as the finite operation of elements in Sand their inverses. UNITRANS : UNIFYING MODEL TRANSFER AND DATA TRANSFER FOR UniTrans : Unifying Model Transfer and Data Transfer for Cross-Lingual Named Entity Recognition with Unlabeled Data Qianhui Wu, Zijia Lin, Börje F. Karlsson, Biqing Huang, Jian-Guang Lou MODELING BOTH CONTEXT- AND SPEAKER-SENSITIVE DEPENDENCE Recently, emotion detection in conversations becomes a hot research topic in the Natural Language Processing community. In this paper, we focus on emotion detection in multi-speaker conversations instead of traditional two-speaker conversations in existing studies. PROCEEDINGS OF THE TWENTY-NINTH INTERNATIONAL JOINT Pay Attention to Devils: A Photometric Stereo Network for Better Details Yakun Ju1, Kin-Man Lam2, Yang Chen1, Lin Qi1 and Junyu Dong1 1Department of Computer Science and Technology, Ocean University of China 2Department of Electronic and Information Engineering, The Hong Kong Polytechnic University fjuyakun, chenyang8484g@stu.ouc.edu.cn, kin.man.lam@polyu.edu.hk, fqilin, dongjunyug@ouc.edu.cn EXPLOITING PERSONA INFORMATION FOR DIVERSE GENERATION OF Exploiting Persona Information for Diverse Generation of Conversational Responses Haoyu Song1, Wei-Nan Zhang1;2, Yiming Cui1;3, Dong Wang3 and Ting Liu1;2 1Research Center for Social Computing and Information Retrieval, Harbin Institute of Technology, China 2Peng Cheng Laboratory, Shenzhen, China 3Joint Laboratory of HIT and iFLYTEK (HFL), iFLYTEK Research, Beijing, China ON DEEP UNSUPERVISED ACTIVE LEARNING Electronic proceedings of IJCAI 2020. On Deep Unsupervised Active Learning Changsheng Li, Handong Ma, Zhao Kang, Ye Yuan, Xiao-Yu Zhang,Guoren Wang
IJCAI | INTERNATIONAL JOINT CONFERENCES ON ARTIFICIAL International Joint Conferences on Artificial Intelligence Organization. Navigation. Home; Conferences. Future Conferences; PastConferences
DISENTANGLED FEATURE LEARNING NETWORK FOR VEHICLE RE Vehicle Re-Identification (ReID) has attracted lots of research efforts due to its great significance to the public security. In vehicle ReID, we aim to learn features that are powerful in discriminating subtle differences between vehicles which are visually similar, and also robust against different orientations of the samevehicle.
AFFECTIVE IMAGE CONTENT ANALYSIS: A COMPREHENSIVE SURVEY Images can convey rich semantics and induce strong emotions in viewers. Recently, with the explosive growth of visual data, extensive research efforts have been A CONVOLUTIONAL APPROACH FOR MISINFORMATION IDENTIFICATION The fast expanding of social media fuels the spreading of misinformation which disrupts people's normal lives. It is urgent to achieve goals of misinformation identification and early detection insocial media.
A SURVEY ON REPRESENTATION LEARNING FOR USER MODELING A Survey on Representation Learning for User Modeling Sheng Li1 and Handong Zhao2 1Department of Computer Science, University of Georgia, GA 2Adobe Research, San Jose, CA sheng.li@uga.edu, hazhao@adobe.com Abstract Artificial intelligent systems are changing every as- DEEP TEXT CLASSIFICATION CAN BE FOOLED The Uganda Securities Exchange (USE) is thehistoricprincipal stock exchange of Uganda. It was founded in June 1997. The USE is operated under the jurisdiction of Uganda’s Capital Markets Authority whichin
AN ITERATIVE MULTI-SOURCE MUTUAL KNOWLEDGE TRANSFER An Iterative Multi-Source Mutual Knowledge Transfer Framework for Machine Reading Comprehension Xin Liu1, Kai Liu2, Xiang Li3, Jinsong Su1y, Yubin Ge4, Bin Wang3 and Jiebo Luo5 1Xiamen University, Xiamen, China 2Baidu Inc., Beijing, China 3Xiaomi AI Lab, Xiaomi Inc., Beijing, China 4University of Illinois at Urbana-Champaign, Urbana, IL 61801, USA 5Department of Computer Science, University of FEDERATED META-LEARNING FOR FRAUDULENT CREDIT CARD DETECTION Federated Meta-Learning for Fraudulent Credit Card Detection Wenbo Zheng 1 ;2, Lan Yan 4, Chao Gou 3 and Fei-Yue Wang 2;4 1 School of Software Engineering, Xi’an Jiaotong University 2 The State Key Laboratory for Management and Control of Complex Systems, Institute of Automation, Chinese Academy of Sciences 3 School of Intelligent Systems Engineering, Sun Yat-sen University ANRL: ATTRIBUTEDNETWORK REPRESENTATIONLEARNING VIA DEEP ANRL: AttributedNetwork RepresentationLearning via Deep Neural Networks Zhen Zhang1;2, Hongxia Yang3, Jiajun Bu1, Sheng Zhou1;2, Pinggang Yu1;2, Jianwei Zhang3, Martin Ester4, Can Wang1 1 College of Computer Science, Zhejiang University, China 2Alibaba-Zhejiang University Joint Institute of Frontier Technologies, China 3 Alibaba Group, China 4 Simon Fraser University, Canada METAMORPHIC TESTING AND CERTIFIED MITIGATION OF FAIRNESS5 Hence, it is critical to know that the decisions made by NLP models are free of unfair bias toward certain subpopulation groups. In this paper, we propose a novel framework employing metamorphic testing, a well-established software testing scheme, to test NLP models and find discriminatory inputs that provoke fairness violations. Furthermore A PENNY FOR YOUR THOUGHTS: THE VALUE OF COMMUNICATION IN2 This paper considers how such a shared protocol can be leveraged, introducing a means to reason about Communication in Ad Hoc Teamwork (CAT). The goal of this work is enabling improved ad hoc teamwork by judiciously leveraging the ability of the team to communicate. We situate our study within a novel CAT scenario, involving tasks withmultiple
DISENTANGLED FEATURE LEARNING NETWORK FOR VEHICLE RE Here we propose a Disentangled Feature Learning Network (DFLNet) to learn orientation specific and common features concurrently, which are discriminative at details and invariant to orientations, respectively. Moreover, to effectively use these two types of features for ReID, we further design a feature metric alignment scheme to ensure the EXPLOITING MUTUAL INFORMATION FOR SUBSTRUCTURE-AWARE GRAPH Exploiting Mutual Information for Substructure-aware Graph Representation Learning Pengyang Wang 1, Yanjie Fu , Yuanchun Zhou2, Kunpeng Liu1, Xiaolin Li3 and Kien Hua1 1University of Central Florida 2Computer Network Information Center, Chinese Academy of Sciences 3Nanjing University pengyang.wang@knights.ucf.edu, yanjie.fu@ucf.edu, zyc@cnic.cn, kunpengliu@knights.ucf.edu, UNITRANS : UNIFYING MODEL TRANSFER AND DATA TRANSFER FOR UniTrans : Unifying Model Transfer and Data Transfer for Cross-Lingual Named Entity Recognition with Unlabeled Data Qianhui Wu, Zijia Lin, Börje F. Karlsson, Biqing Huang, Jian-Guang Lou ON DEEP UNSUPERVISED ACTIVE LEARNING On Deep Unsupervised Active Learning Changsheng Li1, Handong Ma2, Zhao Kang2, Ye Yuan1, Xiao-Yu Zhang3 and Guoren Wang1 1School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China 2SCSE, University of Electronic Science and Technology of China, Chengdu, China 3Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China MODELING BOTH CONTEXT- AND SPEAKER-SENSITIVE DEPENDENCE Modeling both Context- and Speaker-Sensitive Dependence for Emotion Detection in Multi-speaker Conversations Dong Zhang, Liangqing Wu, Changlong Sun, Shoushan Li, Qiaoming Zhu, Guodong Zhou PERSISTENT HOMOLOGY: AN INTRODUCTION AND A NEW TEXT Definition 9. Let S⊂G. The subgroup generated by S, S , is the subgroup of all elements of Gthat can expressed as the finite operation of elements in Sand their inverses. DEEP TEXT CLASSIFICATION CAN BE FOOLED The Uganda Securities Exchange (USE) is thehistoricprincipal stock exchange of Uganda. It was founded in June 1997. The USE is operated under the jurisdiction of Uganda’s Capital Markets Authority whichin
EXPLOITING PERSONA INFORMATION FOR DIVERSE GENERATION OF Exploiting Persona Information for Diverse Generation of Conversational Responses Haoyu Song1, Wei-Nan Zhang1;2, Yiming Cui1;3, Dong Wang3 and Ting Liu1;2 1Research Center for Social Computing and Information Retrieval, Harbin Institute of Technology, China 2Peng Cheng Laboratory, Shenzhen, China 3Joint Laboratory of HIT and iFLYTEK (HFL), iFLYTEK Research, Beijing, China METAMORPHIC TESTING AND CERTIFIED MITIGATION OF FAIRNESS5 Hence, it is critical to know that the decisions made by NLP models are free of unfair bias toward certain subpopulation groups. In this paper, we propose a novel framework employing metamorphic testing, a well-established software testing scheme, to test NLP models and find discriminatory inputs that provoke fairness violations. Furthermore A PENNY FOR YOUR THOUGHTS: THE VALUE OF COMMUNICATION IN2 This paper considers how such a shared protocol can be leveraged, introducing a means to reason about Communication in Ad Hoc Teamwork (CAT). The goal of this work is enabling improved ad hoc teamwork by judiciously leveraging the ability of the team to communicate. We situate our study within a novel CAT scenario, involving tasks withmultiple
DISENTANGLED FEATURE LEARNING NETWORK FOR VEHICLE RE Here we propose a Disentangled Feature Learning Network (DFLNet) to learn orientation specific and common features concurrently, which are discriminative at details and invariant to orientations, respectively. Moreover, to effectively use these two types of features for ReID, we further design a feature metric alignment scheme to ensure the EXPLOITING MUTUAL INFORMATION FOR SUBSTRUCTURE-AWARE GRAPH Exploiting Mutual Information for Substructure-aware Graph Representation Learning Pengyang Wang 1, Yanjie Fu , Yuanchun Zhou2, Kunpeng Liu1, Xiaolin Li3 and Kien Hua1 1University of Central Florida 2Computer Network Information Center, Chinese Academy of Sciences 3Nanjing University pengyang.wang@knights.ucf.edu, yanjie.fu@ucf.edu, zyc@cnic.cn, kunpengliu@knights.ucf.edu, UNITRANS : UNIFYING MODEL TRANSFER AND DATA TRANSFER FOR UniTrans : Unifying Model Transfer and Data Transfer for Cross-Lingual Named Entity Recognition with Unlabeled Data Qianhui Wu, Zijia Lin, Börje F. Karlsson, Biqing Huang, Jian-Guang Lou ON DEEP UNSUPERVISED ACTIVE LEARNING On Deep Unsupervised Active Learning Changsheng Li1, Handong Ma2, Zhao Kang2, Ye Yuan1, Xiao-Yu Zhang3 and Guoren Wang1 1School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China 2SCSE, University of Electronic Science and Technology of China, Chengdu, China 3Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China MODELING BOTH CONTEXT- AND SPEAKER-SENSITIVE DEPENDENCE Modeling both Context- and Speaker-Sensitive Dependence for Emotion Detection in Multi-speaker Conversations Dong Zhang, Liangqing Wu, Changlong Sun, Shoushan Li, Qiaoming Zhu, Guodong Zhou PERSISTENT HOMOLOGY: AN INTRODUCTION AND A NEW TEXT Definition 9. Let S⊂G. The subgroup generated by S, S , is the subgroup of all elements of Gthat can expressed as the finite operation of elements in Sand their inverses. DEEP TEXT CLASSIFICATION CAN BE FOOLED The Uganda Securities Exchange (USE) is thehistoricprincipal stock exchange of Uganda. It was founded in June 1997. The USE is operated under the jurisdiction of Uganda’s Capital Markets Authority whichin
EXPLOITING PERSONA INFORMATION FOR DIVERSE GENERATION OF Exploiting Persona Information for Diverse Generation of Conversational Responses Haoyu Song1, Wei-Nan Zhang1;2, Yiming Cui1;3, Dong Wang3 and Ting Liu1;2 1Research Center for Social Computing and Information Retrieval, Harbin Institute of Technology, China 2Peng Cheng Laboratory, Shenzhen, China 3Joint Laboratory of HIT and iFLYTEK (HFL), iFLYTEK Research, Beijing, China ON DEEP UNSUPERVISED ACTIVE LEARNING Electronic proceedings of IJCAI 2020. On Deep Unsupervised Active Learning Changsheng Li, Handong Ma, Zhao Kang, Ye Yuan, Xiao-Yu Zhang,Guoren Wang
IJCAI | INTERNATIONAL JOINT CONFERENCES ON ARTIFICIAL International Joint Conferences on Artificial Intelligence Organization. Navigation. Home; Conferences. Future Conferences; PastConferences
DISENTANGLED FEATURE LEARNING NETWORK FOR VEHICLE RE Here we propose a Disentangled Feature Learning Network (DFLNet) to learn orientation specific and common features concurrently, which are discriminative at details and invariant to orientations, respectively. Moreover, to effectively use these two types of features for ReID, we further design a feature metric alignment scheme to ensure the FEDERATED META-LEARNING FOR FRAUDULENT CREDIT CARD DETECTION Federated Meta-Learning for Fraudulent Credit Card Detection Wenbo Zheng 1 ;2, Lan Yan 4, Chao Gou 3 and Fei-Yue Wang 2;4 1 School of Software Engineering, Xi’an Jiaotong University 2 The State Key Laboratory for Management and Control of Complex Systems, Institute of Automation, Chinese Academy of Sciences 3 School of Intelligent Systems Engineering, Sun Yat-sen University COLLABORATIVE SELF-ATTENTION NETWORK FOR SESSION-BASED Collaborative Self-Attention Network for Session-based Recommendation Anjing Luo 1, Pengpeng Zhao , Yanchi Liu2, Fuzhen Zhuang3;4, Deqing Wang5, Jiajie Xu 1, Junhua Fang and Victor S. Sheng6 1Institute of AI, School of Computer Science and Technology, Soochow University, China 2Rutgers University, New Jersey, USA 3Key Lab of IIP of CAS, Institute of Computing Technology, Beijing, China AN ITERATIVE MULTI-SOURCE MUTUAL KNOWLEDGE TRANSFER An Iterative Multi-Source Mutual Knowledge Transfer Framework for Machine Reading Comprehension Xin Liu1, Kai Liu2, Xiang Li3, Jinsong Su1y, Yubin Ge4, Bin Wang3 and Jiebo Luo5 1Xiamen University, Xiamen, China 2Baidu Inc., Beijing, China 3Xiaomi AI Lab, Xiaomi Inc., Beijing, China 4University of Illinois at Urbana-Champaign, Urbana, IL 61801, USA 5Department of Computer Science, University of A SURVEY ON REPRESENTATION LEARNING FOR USER MODELING A Survey on Representation Learning for User Modeling Sheng Li1 and Handong Zhao2 1Department of Computer Science, University of Georgia, GA 2Adobe Research, San Jose, CA sheng.li@uga.edu, hazhao@adobe.com Abstract Artificial intelligent systems are changing every as- AFFECTIVE IMAGE CONTENT ANALYSIS: A COMPREHENSIVE SURVEY Images can convey rich semantics and induce strong emotions in viewers. Recently, with the explosive growth of visual data, extensive research efforts have been dedicated to affective image content analysis (AICA). In this paper, we review the state-of-the-art methods comprehensively with respect to two main challenges -- affective gapand
A CONVOLUTIONAL APPROACH FOR MISINFORMATION IDENTIFICATION In this paper, we propose a novel method, Convolutional Approach for Misinformation Identification (CAMI) based on Convolutional Neural Network (CNN). CAMI can flexibly extract key features scattered among an input sequence and shape high-level interactions among significant features, which help effectively identify misinformation and achieve ANRL: ATTRIBUTEDNETWORK REPRESENTATIONLEARNING VIA DEEP ANRL: AttributedNetwork RepresentationLearning via Deep Neural Networks Zhen Zhang1;2, Hongxia Yang3, Jiajun Bu1, Sheng Zhou1;2, Pinggang Yu1;2, Jianwei Zhang3, Martin Ester4, Can Wang1 1 College of Computer Science, Zhejiang University, China 2Alibaba-Zhejiang University Joint Institute of Frontier Technologies, China 3 Alibaba Group, China 4 Simon Fraser University, CanadaWELCOME TO IJCAI
International Joint Conferences on Artificial Intelligence is a non-profit corporation founded in California, in 1969 for scientific and educational purposes, including dissemination of information on Artificial Intelligence at conferences in which cutting-edge scientific results are presented and through dissemination of materials presented at these meetings in form of Proceedings, books METAMORPHIC TESTING AND CERTIFIED MITIGATION OF FAIRNESS4 Hence, it is critical to know that the decisions made by NLP models are free of unfair bias toward certain subpopulation groups. In this paper, we propose a novel framework employing metamorphic testing, a well-established software testing scheme, to test NLP models and find discriminatory inputs that provoke fairness violations. Furthermore ON DEEP UNSUPERVISED ACTIVE LEARNING On Deep Unsupervised Active Learning Changsheng Li1, Handong Ma2, Zhao Kang2, Ye Yuan1, Xiao-Yu Zhang3 and Guoren Wang1 1School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China 2SCSE, University of Electronic Science and Technology of China, Chengdu, China 3Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China A DEEP REINFORCEMENT LEARNING APPROACH TO CONCURRENT A Deep Reinforcement Learning Approach to Concurrent Bilateral Negotiation Pallavi Bagga 1, Nicola Paoletti , Bedour Alrayes2 and Kostas Stathis1 1Royal Holloway, University of London, UK 2King Saud University, Saudi Arabia fpallavi.bagga, nicola.paolettig@rhul.ac.uk, balrayes@ksu.edu.sa, kostas.stathis@rhul.ac.uk EXPLOITING MUTUAL INFORMATION FOR SUBSTRUCTURE-AWARE GRAPH Exploiting Mutual Information for Substructure-aware Graph Representation Learning Pengyang Wang 1, Yanjie Fu , Yuanchun Zhou2, Kunpeng Liu1, Xiaolin Li3 and Kien Hua1 1University of Central Florida 2Computer Network Information Center, Chinese Academy of Sciences 3Nanjing University pengyang.wang@knights.ucf.edu, yanjie.fu@ucf.edu, zyc@cnic.cn, kunpengliu@knights.ucf.edu, COLLABORATIVE SELF-ATTENTION NETWORK FOR SESSION-BASED Collaborative Self-Attention Network for Session-based Recommendation Anjing Luo 1, Pengpeng Zhao , Yanchi Liu2, Fuzhen Zhuang3;4, Deqing Wang5, Jiajie Xu 1, Junhua Fang and Victor S. Sheng6 1Institute of AI, School of Computer Science and Technology, Soochow University, China 2Rutgers University, New Jersey, USA 3Key Lab of IIP of CAS, Institute of Computing Technology, Beijing, China PERSISTENT HOMOLOGY: AN INTRODUCTION AND A NEW TEXT Definition 9. Let S⊂G. The subgroup generated by S, S , is the subgroup of all elements of Gthat can expressed as the finite operation of elements in Sand their inverses. ANRL: ATTRIBUTEDNETWORK REPRESENTATIONLEARNING VIA DEEP ANRL: AttributedNetwork RepresentationLearning via Deep Neural Networks Zhen Zhang1;2, Hongxia Yang3, Jiajun Bu1, Sheng Zhou1;2, Pinggang Yu1;2, Jianwei Zhang3, Martin Ester4, Can Wang1 1 College of Computer Science, Zhejiang University, China 2Alibaba-Zhejiang University Joint Institute of Frontier Technologies, China 3 Alibaba Group, China 4 Simon Fraser University, Canada A NEW SIMPLEX SPARSE LEARNING MODEL TO MEASURE DATA A New Simplex Sparse Learning Model to Measure Data Similarity for Clustering Jin Huang, Feiping Nie, Heng Huang University of Texas atArlington
FRAMING IMAGE DESCRIPTION AS A RANKING TASK DATA, MODELS Image Retrieval: Rank of the original item R@1 R@5 R@10 Median r NN 2.5 4.7 7.2 272.0 BOW1 4.5 14.3 20.8 67.0 BOW5 5.8 16.7 23.6 60.0 TAGRANK 5.4 17.4 24.3 52.5 TRI5 6.0 17.8 26.2 55.0 TRI5SEM 7.6 20.7 30.1 38.0 Table 1: Model performance as measured by the rank of theWELCOME TO IJCAI
International Joint Conferences on Artificial Intelligence is a non-profit corporation founded in California, in 1969 for scientific and educational purposes, including dissemination of information on Artificial Intelligence at conferences in which cutting-edge scientific results are presented and through dissemination of materials presented at these meetings in form of Proceedings, books METAMORPHIC TESTING AND CERTIFIED MITIGATION OF FAIRNESS4 Hence, it is critical to know that the decisions made by NLP models are free of unfair bias toward certain subpopulation groups. In this paper, we propose a novel framework employing metamorphic testing, a well-established software testing scheme, to test NLP models and find discriminatory inputs that provoke fairness violations. Furthermore ON DEEP UNSUPERVISED ACTIVE LEARNING On Deep Unsupervised Active Learning Changsheng Li1, Handong Ma2, Zhao Kang2, Ye Yuan1, Xiao-Yu Zhang3 and Guoren Wang1 1School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China 2SCSE, University of Electronic Science and Technology of China, Chengdu, China 3Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China A DEEP REINFORCEMENT LEARNING APPROACH TO CONCURRENT A Deep Reinforcement Learning Approach to Concurrent Bilateral Negotiation Pallavi Bagga 1, Nicola Paoletti , Bedour Alrayes2 and Kostas Stathis1 1Royal Holloway, University of London, UK 2King Saud University, Saudi Arabia fpallavi.bagga, nicola.paolettig@rhul.ac.uk, balrayes@ksu.edu.sa, kostas.stathis@rhul.ac.uk EXPLOITING MUTUAL INFORMATION FOR SUBSTRUCTURE-AWARE GRAPH Exploiting Mutual Information for Substructure-aware Graph Representation Learning Pengyang Wang 1, Yanjie Fu , Yuanchun Zhou2, Kunpeng Liu1, Xiaolin Li3 and Kien Hua1 1University of Central Florida 2Computer Network Information Center, Chinese Academy of Sciences 3Nanjing University pengyang.wang@knights.ucf.edu, yanjie.fu@ucf.edu, zyc@cnic.cn, kunpengliu@knights.ucf.edu, COLLABORATIVE SELF-ATTENTION NETWORK FOR SESSION-BASED Collaborative Self-Attention Network for Session-based Recommendation Anjing Luo 1, Pengpeng Zhao , Yanchi Liu2, Fuzhen Zhuang3;4, Deqing Wang5, Jiajie Xu 1, Junhua Fang and Victor S. Sheng6 1Institute of AI, School of Computer Science and Technology, Soochow University, China 2Rutgers University, New Jersey, USA 3Key Lab of IIP of CAS, Institute of Computing Technology, Beijing, China PERSISTENT HOMOLOGY: AN INTRODUCTION AND A NEW TEXT Definition 9. Let S⊂G. The subgroup generated by S, S , is the subgroup of all elements of Gthat can expressed as the finite operation of elements in Sand their inverses. ANRL: ATTRIBUTEDNETWORK REPRESENTATIONLEARNING VIA DEEP ANRL: AttributedNetwork RepresentationLearning via Deep Neural Networks Zhen Zhang1;2, Hongxia Yang3, Jiajun Bu1, Sheng Zhou1;2, Pinggang Yu1;2, Jianwei Zhang3, Martin Ester4, Can Wang1 1 College of Computer Science, Zhejiang University, China 2Alibaba-Zhejiang University Joint Institute of Frontier Technologies, China 3 Alibaba Group, China 4 Simon Fraser University, Canada A NEW SIMPLEX SPARSE LEARNING MODEL TO MEASURE DATA A New Simplex Sparse Learning Model to Measure Data Similarity for Clustering Jin Huang, Feiping Nie, Heng Huang University of Texas atArlington
FRAMING IMAGE DESCRIPTION AS A RANKING TASK DATA, MODELS Image Retrieval: Rank of the original item R@1 R@5 R@10 Median r NN 2.5 4.7 7.2 272.0 BOW1 4.5 14.3 20.8 67.0 BOW5 5.8 16.7 23.6 60.0 TAGRANK 5.4 17.4 24.3 52.5 TRI5 6.0 17.8 26.2 55.0 TRI5SEM 7.6 20.7 30.1 38.0 Table 1: Model performance as measured by the rank of the IJCAI | INTERNATIONAL JOINT CONFERENCES ON ARTIFICIAL International Joint Conferences on Artificial Intelligence Organization. Navigation. Home; Conferences. Future Conferences; PastConferences
METAMORPHIC TESTING AND CERTIFIED MITIGATION OF FAIRNESS Hence, it is critical to know that the decisions made by NLP models are free of unfair bias toward certain subpopulation groups. In this paper, we propose a novel framework employing metamorphic testing, a well-established software testing scheme, to test NLP models and find discriminatory inputs that provoke fairness violations. Furthermore DISENTANGLED FEATURE LEARNING NETWORK FOR VEHICLE RE Here we propose a Disentangled Feature Learning Network (DFLNet) to learn orientation specific and common features concurrently, which are discriminative at details and invariant to orientations, respectively. Moreover, to effectively use these two types of features for ReID, we further design a feature metric alignment scheme to ensure the ON DEEP UNSUPERVISED ACTIVE LEARNING On Deep Unsupervised Active Learning Changsheng Li1, Handong Ma2, Zhao Kang2, Ye Yuan1, Xiao-Yu Zhang3 and Guoren Wang1 1School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China 2SCSE, University of Electronic Science and Technology of China, Chengdu, China 3Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China COLLABORATIVE SELF-ATTENTION NETWORK FOR SESSION-BASED Collaborative Self-Attention Network for Session-based Recommendation Anjing Luo 1, Pengpeng Zhao , Yanchi Liu2, Fuzhen Zhuang3;4, Deqing Wang5, Jiajie Xu 1, Junhua Fang and Victor S. Sheng6 1Institute of AI, School of Computer Science and Technology, Soochow University, China 2Rutgers University, New Jersey, USA 3Key Lab of IIP of CAS, Institute of Computing Technology, Beijing, China AN ITERATIVE MULTI-SOURCE MUTUAL KNOWLEDGE TRANSFER An Iterative Multi-Source Mutual Knowledge Transfer Framework for Machine Reading Comprehension Xin Liu1, Kai Liu2, Xiang Li3, Jinsong Su1y, Yubin Ge4, Bin Wang3 and Jiebo Luo5 1Xiamen University, Xiamen, China 2Baidu Inc., Beijing, China 3Xiaomi AI Lab, Xiaomi Inc., Beijing, China 4University of Illinois at Urbana-Champaign, Urbana, IL 61801, USA 5Department of Computer Science, University of AN INTERACTIVE MULTI-TASK LEARNING FRAMEWORK FOR NEXT POI An Interactive Multi-Task Learning Framework for Next POI Recommendation with Uncertain Check-ins Lu Zhang1, Zhu Sun2, Jie Zhang1, Yu Lei3, Chen Li3, Ziqing Wu1, Horst Kloeden4 and Felix Klanner4 1Nanyang Technological University, Singapore 2Macquarie University, Australia 3Yanshan University, China 4BMW Group, Germany z.sun@mq.edu.au Abstract Studies on next point-of-interest (POI) DEEP TEXT CLASSIFICATION CAN BE FOOLED The Uganda Securities Exchange (USE) is thehistoricprincipal stock exchange of Uganda. It was founded in June 1997. The USE is operated under the jurisdiction of Uganda’s Capital Markets Authority whichin
EXPLOITING PERSONA INFORMATION FOR DIVERSE GENERATION OF Exploiting Persona Information for Diverse Generation of Conversational Responses Haoyu Song1, Wei-Nan Zhang1;2, Yiming Cui1;3, Dong Wang3 and Ting Liu1;2 1Research Center for Social Computing and Information Retrieval, Harbin Institute of Technology, China 2Peng Cheng Laboratory, Shenzhen, China 3Joint Laboratory of HIT and iFLYTEK (HFL), iFLYTEK Research, Beijing, China ATTNSENSE: MULTI-LEVEL ATTENTION MECHANISM FOR MULTIMODAL AttnSense: Multi-level Attention Mechanism For Multimodal Human Activity Recognition Haojie Ma, Wenzhong Li, Xiao Zhang, SongchengGaoand Sanglu Lu
IJCAI
International Joint Conferences on Artificial IntelligenceOrganization
Navigation
* Home
* Conferences
* Future Conferences* Past Conferences
* Proceedings
* IJCAI 2020 Proceedings* Past Proceedings
* Awards
* Trustees/officers
* Current trustees
* Trustees Elect
* IJCAI Secretariat
* IJCAI Sponsorship and Publicity Officers* IJCAI Team
* Local Arrangements Chairs * Former Trustees serving on the Executive Committee * Other Former Officers* AI Journal
* About
* About IJCAI
* Contact InformationWELCOME TO IJCAI
International Joint Conferences on Artificial Intelligence is a non-profit corporation founded in California, in 1969 for scientific and educational purposes, including dissemination of information on Artificial Intelligence at conferences in which cutting-edge scientific results are presented and through dissemination of materials presented at these meetings in form of Proceedings, books, video recordings, and other educational materials. IJCAI consists of two divisions: the Conference Division and the AI Journal Division . IJCAI conferences present premier international gatherings of AI researchers and practitioners and they were held biennially in odd-numbered years since 1969. Starting with 2016, IJCAI conferences are held annually. IJCAI-PRICAI-20 will be held in Yokohama, Japan, IJCAI-21 in Montreal, Canada, IJCAI-ECAI-22 in Bologna, Italy and IJCAI-23 in Cape Town, South Africa. IJCAI is governed by the Board of Trustees, with IJCAI
Secretariat in
charge of its operations. IJCAI-19 was be held in Macao, P.R. China from August 10-16, 2019. The IJCAI Organization and Local Arrangements Committee thank you for participating. IJCAI-20 Awards announcedAI Hub launched
IJCAI Marvin Minsky Medal for Outstanding Achievements in AI Awardedto Libratus Team
Funding Opportunities for Promoting AI Research Free Access to the AI journal IJCAI Anti-Discrimination Policy (pdf)
IJCAI Privacy Policy (pdf)
IJCAI Organization would like to acknowledge and thank the following platinum level sponsors of its past three conferences in a row: Copyright © 2020, IJCAIDetails
Copyright © 2024 ArchiveBay.com. All rights reserved. Terms of Use | Privacy Policy | DMCA | 2021 | Feedback | Advertising | RSS 2.0