News

2022年度东南大学青年五四奖章入围个人及集体新鲜出炉。经个人申报、学院推荐,校团委组织专家评审,PALM实验室入围2022年度“东南大学青年五四奖章”集体。入围集体名单如下。

“东南大学青年五四奖章”是共青团东南大学委员会授予东大青年的最高荣誉,PALM实验室集体成员坚决拥护中国共产党的领导,理想信念坚定,全体师生追求卓越,活跃在学术科研一线。PALM未来也将继续充分发挥集体力量,团结引领广大团员青年踔厉奋发、砥砺前行!

题目: 鲁棒稳健半监督学习:模型与应用

报告人: 史颖欢

报告时间和地点: 2023年3月22日, 15:30,计算机学院413

摘要: 近年来,以一致性正则化为代表的深度半监督学习已经在模型、方法与应用层面取得了较大进展。本报告将介绍课题组在鲁棒稳健条件下的深度半监督学习模型与应用方面的初步探索。

个人简介:史颖欢,南京大学计算机系副教授/博导、兼任南大健康医疗大数据国家研究院医疗人工智能平台主要负责人,南京市鼓楼医院双聘教授。国家自然科学基金优秀青年科学基金、吴文俊人工智能优秀青年奖获得者。于2007和2013年在南大计算机系获学士和博士学位。研究兴趣为机器学习、模式识别、机器视觉、以及在医疗图像处理、医疗数据分析方面的交叉研究。近年来主持国家重点研发计划(课题)、国家自然科学基金重大仪器子课题/面上/青年、CCF-腾讯犀牛鸟科研基金。在CCF-A类会议、IEEE/ACM汇刊发表论文50余篇,包括TPAMI、TIP、TMI、TNNLS、CVPR、ICCV、ECCV、NeurIPS、AAAI、IJCAI等。曾入选中国科协青年人才托举工程,获得ACM南京新星奖、江苏省计算机学会青年科技奖、江苏省自然科学二等奖(第二完成人)、中国人民解放军军队医疗成果奖(第三完成人)等荣誉。

题目: 可泛化的行人再辨识:挑战、方法和数据

报告人: 廖胜才

报告时间和形式: 北京时间4月30日下午2点,线上

摘要: 行人再辨识是近年来的热门研究领域,随着深度学习的发展取得了很大的进步。但是已有模型在不同场景下的泛化能力依然较差。虽然迁移学习被大量地研究用于增强模型在新场景下的适应性,但其代价是为了应用到处需要深度学习训练。为此,面向实际应用迫切需要研究开箱即用的行人再辨识——即可泛化的行人再辨识。本报告将从该问题所面临的挑战、我们提出的一些方法、及大规模虚拟数据对模型泛化性的提升等方面,全面阐述可泛化的行人再辨识这一前沿研究课题。

个人简介:廖胜才,博士,阿联酋起源人工智能研究院(IIAI)Lead Scientist,IEEE高级会员。2005年获中山大学数学与应用数学学士学位,2010年获中科院自动化所模式识别与智能系统博士学位,2010年至2012年任美国密歇根州立大学计算机系博士后研究员,2012-2018年间在中科院自动化所历任助理研究员、副研究员。廖博士主要从事模式识别和计算机视觉方面的研究工作,特别是人脸和行人检测与识别,和智能视频分析。在国际主流期刊和会议上发表论文100余篇,论文被引用超过13000次,H-Index 41。其中,发表在CVPR2015上的LOMO+XQDA是行人再辨识的代表性算法,被国内外学者引用1726次,为CVPR2015中602篇论文的Top10。曾担任ICPR、ICB等国际会议领域主席,IJCAI高级程序委员,Springer《生物特征识别百科全书》领域编辑。曾获得ICB 2006优秀学生论文奖,ICB 2007最佳论文奖,被2008北京奥运会安保部授予突出贡献荣誉(人脸识别电子票证系统),并荣获国家科技进步二等奖一项。此外,还获得IJCB 2014最佳审稿人奖和CVPR 2019杰出审稿人奖;指导学生获得ICB 2015和CCBR 2016最佳学生论文奖;荣获CVPR2017行人检测竞赛冠军和ICCV2019黑夜行人检测竞赛冠军。个人主页:https://liaosc.wordpress.com/

会议链接:https://cse.seu.edu.cn/2021/0414/c22635a368233/pagem.htm

2020年11月14日,PALM实验室成立十周年之际,近50位PALM毕业同学与老师齐聚一堂。每一位PALMer都在各自的岗位上发光发热,也祝愿实验室越来越好!

祝贺PALM毕业生侯鹏获得江苏省优秀硕士学位论文!此外,PALM毕业生邢超、徐海洋也获得了东南大学优秀硕士论文奖,同样对他们表示祝贺!

2018年4月28日,中国人工智能学会(CAAI)发起并联合中国科学院大学共同主办,中国科学院大学人工智能技术学院承办的首届“全国高校人工智能学院院长/系主任论坛”在中国科学院大学雁栖湖校区隆重举行。来自中国科学院大学、北京大学、清华大学、浙江大学、南京大学、东南大学、北京理工大学、北京航空航天大学、国防科技大学、湖南大学、北京交通大学、西安电子科技大学、百度、360、平安集团、美团等单位的百余位专家和代表济济一堂,共同就人工智能的学科建设与发展、人才培养体系建设与产业人才需求匹配等方面进行了深入探讨和前瞻式分析展望。耿新老师应邀作为嘉宾参加了本次会议的Panel讨论环节。


耿新老师参与论坛(右二)

耿新老师在讲话(中)

4月20日至22日,第八届视觉与学习青年学者研讨会(Vision And Learning SEminar, VALSE)在大连举行。PALM实验室的老师与同学参加了此次会议。耿新老师担任了会议的部分主持人。


11月3日至5日,第十五届中国机器学习及其应用研讨会在北京交通大学举行。PALM实验室的老师与同学参加了此次会议。耿新与张敏灵老师分别担任了会议的部分主持人。


耿新老师担任部分环节主持人

张敏灵老师担任特TCR节主持人

9月14日至16日,第六届全国社会媒体处理大会(SMP 2017)在北京举行。PALM实验室团队“palm”在用户画像评测中取得总成绩第二名以及任务二冠军,参加了颁奖仪式并作了技术报告。周德宇老师担任指导老师,团队成员包括张致恺、缪磊和徐海洋。评测结果见下表。


左起:PALM实验室成员:周德宇老师,徐海洋,张致恺,缪磊, 以及颁奖老师:沈华伟老师(中科院计算所)。

IJCAI is the International Joint Conference on Artificial Intelligence, the main international gathering of researchers in AI. The 26th International Joint Conference on Artificial Intelligence is held in Melbourne, Australia in August 19-26. PALM students Yi Ren, Zengwei Huo, Yu Song attend the conference and report their newly research.


Yi Ren is giving report(left) and sharing the post(right).

Zengwei Huo is giving report(left) and sharing the post(right).

Yu Song is giving report(left) and sharing the post(right).

8月1日至3日,2017年中国计算机协会人工智能会议在云南省昆明市举行,会议安排6个大会特邀报告、3个专题研讨会,并与ACM数据挖掘中国分会联合举办“CCFAI工业高峰论坛暨ACM数据挖掘中国分会年会”。PALM实验室的老师与同学参加了此次会议。耿新老师做特邀报告《标记分布学习范式》,张敏灵老师和薛晖老师分别担任了部分报告的主持人工作。王靖、徐宁、吴璇和孙彦苹代表实验室参与了讲习班。


耿新老师在做特邀报告

张敏灵老师担任分会主持人

与会老师与同学合影

7月26日到28日,第十六届中国机器学习会议(CCML)在天津举办,PALM实验室的老师和同学参与了该会议。张敏灵老师参加了青年学者特别论坛、专委会工作会议,并担任分会报告主持人。同时,薛晖老师也受邀担任分会报告主持人。PALM学生丁思宇替周斌斌做了《基于三元纠错输出编码的偏标记学习算法》。


张敏灵老师参与青年学者特别论文、专委会工作会议并担任分会主持人

薛晖老师担任分会主持人

丁思宇在做报告

与会同学合影

7月16日,“山西省大数据分析与挖掘研究生暑期学校”开班,20余位国内外大数据和人工智能领域的知名学者、杰出专家汇聚山西大学,展开为期一周的专题讲学。PALM实验室的老师和同学参与了该暑期学校。耿新老师和张敏灵老师分别做了《标记分布学习范式》与《多标记机器学习》的专题讲座。


耿新老师在做《标记分布学习范式》的专题讲座

张敏灵老师在做《多标记机器学习》的专题讲座

The Thirty-First AAAI Conference on Artificial Intelligence (AAAI-17) is held February 4–9 at the Hilton San Francisco, San Francisco, California, USA. PALM faulties Xin Geng and Min-ling Zhang and students Miao-gen Ling, Cai-zhi Tang and Hai-ming Xu attended this conference. Miao-gen Ling and Cai-zhi Tang gave a report on their newly research, meanwhile, Hai-ming Xu took part in the post communication.


2016年11月4日至6日,MAL'16会议在南京(南京大学)举行。PALM实验室的老师和同学参加了此次会议。耿新老师担任了会议第四部分的主持。在会议回顾部分,张敏灵老师介绍了KDD'16会议,耿新老师介绍了CVPR'16会议。实验室同学侯鹏、邢超和周斌斌参加了墙展交流,并做了相关报告。


耿新老师在介绍CVPR'16会议

张敏灵老师在介绍KDD'16会议

侯鹏在介绍自己的研究成果

邢超在介绍自己的研究成果

周斌斌在介绍自己的研究成果

侯鹏(左上)、邢超(坐下)和周斌斌(右)与参会人员进行墙展交流

PALM实验室成员与周志华老师合影留念

The IEEE Conference on Computer Vision and Pattern Recognition (CVPR2016) was held from June 26th to July 1st at Las Vegas, NV, USA. Proffessor Xin Geng and student Chao Xing attended the conference. Chao Xing showed the poster about the "Logistic Boosting Regression for Label Distribution Learning", moreover, he gave an oral talk about the CVPR2016 ChaLearn LAP and FoW - Age Estimation Competition named "Deep Age Distribution Learning for Apparent Age Estimation".

Title: Neuroscience-informed sound, music, and wearable computing for rehabilitation and learning

Abstract

The use of music as an aid in improving body and mind has received enormous attention over the last 20 years from a wide range of disciplines, including neuroscience, physical therapy, exercise science, and psychological medicine. We have attempted to transform insights gained from the scientific study of music, learning, and medicine into real-life applications that can be delivered widely, effectively, and accurately. We have been using music to enhance learning as well as to augment evidence-based medicine. In this talk, I will describe tools to facilitate the delivery of established music-enhanced therapies, harnessing the synergy of sound and music computing (SMC), mobile computing, and cloud computing technologies to promote learning and to facilitate disease prevention, diagnosis, and treatment in both developed countries and resource-poor developing countries. These tools are being developed as part of ongoing research projects that combine wearable sensors, smartphone apps, and cloud-based therapy delivery systems to facilitate music-enhanced learning and music-enhanced physical therapy. I will also discuss the joys and pains working in such a multidisciplinary environment.

Biography

Ye Wang is an Associate Professor in the Computer Science Department at the National University of Singapore (NUS) and NUS Graduate School for Integrative Sciences and Engineering (NGS). He established and directed the sound and music computing (SMC) Lab (www.smcnus.org). Before joining NUS he was a member of the technical staff at Nokia Research Center in Tampere, Finland for 9 years. His research interests include sound analysis and music information retrieval (MIR), mobile computing, and cloud computing, and their applications in music edutainment , e-Learning, and e-Health, as well as determining their effectiveness via subjective and objective evaluations. His most recent projects involve the design and evaluation of systems to support 1) therapeutic gait training using Rhythmic Auditory Stimulation (RAS), 2) second language learning, and 3) motivating exercise via music-based systems.

2016年4月22日至24日,VALSE'16会议在武汉(巴山夜雨大酒店)举行。PALM实验室的老师和同学参加了此次会议。张敏灵老师做了题为《多示例学习简介及其在计算机视觉中的应用》的报告。侯鹏(下图左)和邢超(下图右)参加了墙展交流。


Congratulations to the PALM team 'palm_seu' which won the runner-up in the Chalearn LAP Apparent Age Estimation challenge!

The challenge is part of Face Analysis Workshop and Challenge, CVPR'16 and the details can be found in http://gesture.chalearn.org/ . The team is supervised by professor Xin Geng and its members include: Chao Xing, Zeng-wei Huo, Ying Zhou, Xu Yang, Peng Hou and Jia-qi Lv. The result of the challenge is showed in the table.

The Thirtieth AAAI Conference on Artificial Intelligence (AAAI'16) was held February 12-17 at the Phoenix Convertion Center, Phoenix, Arizona, USA. Peng Hou attended the conference and gave an oral talk about the paper "Multi-Label Manifold Learning".

Title: Scene Text Detection/Recognition: Recent Advances and Our Solutions

Abstract

Text information appearing in a scene carries vital information for interpreting the contents, and identifying objects and surrounding environment in images. Although conventional document analysis techniques have bee quite successful, identifying general text in images remains a very challenging research problem. The recent prestigious conferences on computer vision, pattern recognition, and machine learning have seen an increased interest on this topic from the computer vision research community. In this talk, I will show you the challenges and the recent advances in research on scene text recognition and our solutions and attempts.

Biography

Dr. Wenjing Jia is currently a Lecturer at the School of Computing and Communications at University of Technology Sydney (UTS) teaching various under- and postgraduate internetworking subjects. She is also a core research member of UTS Global Big Data Technologies Centre. Her research interests include image processing/analysis and object detection and recognition. In particular, she has been working in the field of text information extraction for several years. This has included working on applications such as vehicle identification via recognizing their license plates, textual information retrieval from images on web pages and emails, and text sign recognition from natural scene images. She has had over 70 publications in journals such as TIP and conferences such as ICIP and ICPR. A focus of more recent work has been to explore deep features and deep learning architectures for detecting and recognising scene text or text signage from unconstrained, outdoor street level imagery. Prior to UTS, Wenjing worked at Fuzhou University from 1999 to 2003 as an Associate Lecturer teaching various subjects in communications and information systems and conducting research on medical image analysis.

Congratulations to the PALM graduates Lei Wu who won the Jiangsu Province outstanding master's degree thesis!

祝贺PALM毕业生吴磊获得江苏省优秀硕士学位论文!

题目: 自然人机交互与情感计算

讲者: 陶建华,研究员,中科院自动化所

摘要: 情感信息是人机交互的重要组成部分,本报告将重点分析多模态人机交互过程中,情感分析与处理的建模方法,以及不同模态信息对情感分析的影响。报告还将对人机交互面临的一系列挑战进行分析。

个人简介:中科院自动化所模式识别国家重点实验室研究员、副主任,中科院脑科学与智能技术卓越创新研究中心核心骨干,中国科学院大学首席教授,国家杰出青年基金获得者。担任中国计算机学会常务理事,中国人工智能学会理事,中国中文信息学会理事,中国声学学会理事,Steering Committee Member of IEEE Trans. On Affective Computing,以及Journal on Multimodal User Interfaces, Speech Communication等期刊编委。主要研究方向为语音识别与合成、人机交互、模式识别等,在主要国际期刊或会议上发表论文100余篇。