Visual relations, such as “person ride bike” and “bike next to car”, offer a comprehensive scene understanding of an image, and have already shown their great utility in connecting computer vision and natural language. ACM is meeting this challenge, continuing to work to improve the automated merges by tweaking the weighting of the evidence in light of experience. Yulei Niu Postdoc ... Ph.D. @ Columbia University bc2754[at]columbia.edu. As MF is continuous, we used cosine ranking and table lookup is not applied. Neural Collaborative Filtering ∗ Xiangnan He National University of Singapore, Singapore xiangnanhe@gmail.com Lizi Liao National University of Singapore, Singapore Hanwang Zhang Columbia University hanwangzhang@gmail.com Xiangnan He ∗ National University of Singapore xiangnanhe@gmail.com Liqiang Nie ShanDong University nieliqiang@gmail.com Wei Liu Tencent AI Lab wliu@ee.columbia.edu Tat-Seng Chua National University of Singapore dcscts@nus.edu.sg ABSTRACT Multimedia content is dominating today’s Web information. It is hard to predict what shape such an area for user-generated content may take, but it carries interesting potential for input from the community. Geochemistry 1; Lamont-Doherty Earth Observatory 1; Subject. About; Explore; Log In; Upload Your Research; Academic Commons. Ideas occur to us when they please, not when it pleases us. Shih-Fu Chang Professor of Electrical Engineering and Computer Science, Columbia University Verified email at columbia.edu. Search Search. How to quickly get a good reply: Give credit where it’s due by listing out the positive … Hanwang Zhang's 15 research works with 205 citations and 599 reads, including: Stochastic Dynamics for Video Infilling With very common family names, typical in Asia, more liberal algorithms result in mistaken merges. search for Search. Email:shenhengtao@hotmail.com video captioning is more difficult for the diverse sets of objects, scenes, actions, attributes and salient contents. View distribution Comments 0. Qiangeng Xu; 1Hanwang Zhang 2 Weiyue Wang Peter N. Belhumeur3 Ulrich Neumann1 1University of Southern California 2Nanyang Technological University 3Columbia University fqiangenx,weiyuewa,uneumanng@usc.edu hanwangzhang@ntu.edu.sg belhumeur@cs.columbia.edu Abstract In this paper, we introduce a stochastic dynamics video infilling (SDVI) framework to … View Hanwang Zhang’s profile on LinkedIn, the world’s largest professional community. Undergraduate works. Hanwang Zhang is an Assistant Professor at Nanyang Technological University, Singapore. Jingyuan Chen, Hanwang Zhang, Xiangnan He, Liqiang Nie, Wei Liu, and Tat-Seng Chua, "Attentive Collaborative Filtering: Multimedia Recommendation with Item- and Component-Level Attention", in Proc. Long Chen 1 Wenbo Ma 1 1 Jun Xiao 1 Hanwang Zhang 2 Wei Liu 3 Shih-Fu Chang 4 1 DCD Lab, College of Computer Science, Zhejiang University 2 Nanyang Technological University 3 Tencent AI Lab 4 Columbia University Long Chen and Wenbo Ma are co-first authors with equal contributions. Academic Commons. Long Chen (陈隆) Zhejiang University Verified email at zju.edu.cn. (Hons.) Download . The more conservative the merging algorithms, the more bits of evidence are required before a merge is made, resulting in greater precision but lower recall of works for a given Author Profile. I'm Bo Wu (Chinese Name: 吴波), a Research Scientist at Columbia University in New York, working with Prof. Shih-Fu Chang. Toggle facets Refine your search Author. Hanwang Zhang1∗ Yulei Niu2† Shih-Fu Chang3 1Nanyang Technological University, 2Renmin University of China, 3Columbia University, hanwangzhang@ntu.edu.sg; niu@ruc.edu.cn; shih.fu.chang@columbia.edu Abstract We focus on grounding (i.e., localizing or linking) refer-ring expressions in images, e.g., “largest elephant stand- ing behind baby elephant”. Hanwang Zhang Nanyang Assistant Professor hanwangzhang[at]ntu.edu.sg. It is ACM's intention to make the derivation of any publication statistics it generates clear to the user. search for Search. Context-Aware Visual Policy Network for Sequence-Level Image Captioning. ACM will expand this edit facility to accommodate more types of data and facilitate ease of community participation with appropriate safeguards. However, the exploration of deep neural networks on recommender systems has received relatively less scrutiny. Hang Gao Contact: er@clbuensdeg.eegeh.aky unscramble About. Figure 6: Item recommendation performance (NDCG@K) of all the CF hashing methods of various code lengths. of Electronic Science and Technology of China, 611731. Hanwang Zhang Columbia University hanwangzhang@gmail.com Richang Hong Hefei University of Technology hongrc.hfut@gmail.com Qi Tian University of Texas at San Antonio qi.tian@utsa.edu ABSTRACT Di‡erent from traditional long videos, micro-videos are much shorter and usually recorded at a speci•c place with mobile devices. Geochemistry 1; Lamont-Doherty Earth Observatory 1; Subject. I am a second-year CS Ph.D. student at UC Berkeley and a member of Berkeley AI Research, advised by Angjoo Kanazawa. Han, Shuangbao [remove] 1; Wang, Cheng [remove] 1; Wen, Dongguang 1; Zhang, Eryong [remove] 1; Zhang, Fucun 1; more Author » Academic Unit. Generated by LaTeXML . Venue Prediction for Social Images by Exploiting Rich Temporal Patterns in LBSNs Jingyuan Chen1(B), Xiangnan He1, Xuemeng Song2, Hanwang Zhang3, Liqiang Nie2, and Tat-Seng Chua1 1 School of Computing, National University of Singapore, Singapore, Singapore jingyuanchen91@gmail.com, xiangnanhe@gmail.com, dcscts@nus.edu.sg About; Explore; Log In; Upload Your Research; Academic Commons. SCA-CNN: Spatial and Channel-wise Attention in Convolutional Networks for Image Captioning Long Chen1 Hanwang Zhang2 Jun Xiao1∗ Liqiang Nie3 Jian Shao1 Wei Liu4 Tat-Seng Chua5 1Zhejiang University 2Columbia University 3Shandong University 4Tencent AI Lab 5National University of Singapore Abstract Visual attention has been successfully applied in struc- Ruiwei Zhao Postdoc rwzhao[at]ntu.edu.sg. https://scholar.google.com.sg/citations?user=-gtmMpIAAAAJ&hl=en There are currently no products in your area. The system can't perform the operation now. We would like to show you a description here but the site won’t allow us. Columbia University. „e nature … I'm Bo Wu (Chinese Name: 吴波), a Research Scientist at Columbia University in New York, working with Prof. Shih-Fu Chang. - "Discrete Collaborative Filtering" ConvNet Architecture Search for Spatiotemporal Feature Learning. Tongtao Zhang1, Spencer Whitehead1, Hanwang Zhang2, Hongzhi Li3, Joseph Ellis2, Lifu Huang1, Wei Liu 4 , Heng Ji 1 , Shih-Fu Chang 2 1 Rensselaer Polytechnic Institute, USA 2 Columbia University, USA 3 Microso› Research, USA 4 Tencent AI Lab, China Thirty-second Conference on Neural Information Processing Systems , 2018. Heng Tao Shen is the correspondence author. Kaihua Tang Nanyang Technological University Verified email at e.ntu.edu.sg. research-article. A discriminative tracklets representation for crowd analysis. Thirty-second Conference on Neural Information Processing Systems , 2018. degree in computer science from Zhejiang University, Hangzhou, China, in 2009, and the Ph.D. degree in computer science from the National University of Singapore, Singapore, in 2014. Hanwang Zhang (张含望) Assistant Professor, SCSE, Nanyang Technological University Verified email at ntu.edu.sg Laura Sevilla-Lara Lecturer at University of Edinburgh Verified email at tuebingen.mpg.de Previously, I obtained my master degree from Columbia where I worked with Shih-Fu Chang.During my undergrad years in Jiao Tong University, I collaborated closely with Anind Dey. He was a research scientist at the Department of Computer Science, Columbia University, USA and a senior research fellow at the School of Computing, National University of Singapore, Singapore. Research Staffs. Hanwang Zhang 张含望) Assistant Professor, SCSE, Nanyang Technological University Verified email at ntu.edu.sg. Hanwang Zhang. It is possible, too, that the Author Profile page may evolve to allow interested authors to upload unpublished professional materials to an area available for search and free educational use, but distinct from the ACM Digital Library proper. Hanwang Zhang3, Liqiang Nie2, Tat-Seng Chua1 1School of Computing, National University of Singapore 2School of Computer Science and Technology, ShanDong University 3Department of Computer Science, Columbia University fjingyuanchen91, xiangnanhe, sxmustc, hanwangzhang, nieliqiangg@gmail.com dcscts@nus.edu.sg Abstract. Nanyang Technological University, Singapore, Singapore, University of Science and Technology of China, Hefei, China, Hefei University of Technology, Hefei, China, National University of Singapore, Singapore, Singapore, The University of Sydney, Sydney, Australia. Han, Shuangbao 1; Wang, Cheng [remove] 1; Wen, Dongguang 1; Zhang, Eryong 1; Zhang, Fucun [remove] 1; more Author » Academic Unit. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018. … • Prof. Shih-Fu Chang at Columbia University • Prof. Hanwang Zhang at Nanyang Technological University • Prof. Tat-Seng Chua at National University of Singapore My primary research interests are Computer Vision and Multimodal Analysis. Hanwang Zhang, Fumin Shen, Wei Liu, Xiangnan He, Huanbo Luan, and Tat-Seng Chua, "Discrete Collaborative Filtering", in Proc. Despite Long Chen, Hanwang Zhang, Jun Xiao, Wei Liu, Shih-Fu Chang. Previously, I obtained my master degree from Columbia where I worked with Shih-Fu Chang.During my undergrad years in Jiao Tong University, I collaborated closely with Anind Dey. degree in computer science from Zhejiang University, Hangzhou, China, in 2009, and the Ph.D. degree in computer science from the National University of Singapore, Singapore, in 2014. Hence it is clear that manual intervention based on human knowledge is required to perfect algorithmic results. Hang Gao UC Berkeley Verified email at berkeley.edu. Request Comment. Long Chen1 Hanwang Zhang2 Jun Xiao1∗ Liqiang Nie3 Jian Shao1 Wei Liu4 Tat-Seng Chua5 1Zhejiang University 2Columbia University 3Shandong University 4Tencent AI Lab 5National University of Singapore Abstract Visual attention has been successfully applied in struc-tural prediction tasks such as visual captioning and ques- tion answering. Email:shenhengtao@hotmail.com video captioning is more difficult for the diverse sets of objects, scenes, actions, attributes and salient contents. ‪Columbia University‬ - ‪Cited by 1,567‬ - ‪Computer Vision‬ - ‪Machine Learning‬ - ‪Multimedia‬ ... Hanwang Zhang 张含望) ... Z Shou, H Gao, L Zhang, K Miyazawa, SF Chang. Hanwang Zhang y, Zawlin Kyawz, Shih-Fu Chang , Tat-Seng Chuaz yColumbia University, zNational University of Singapore fhanwangzhang, kzl.zawling@gmail.com; sfchang@ee.columbia.edu; dcscts@nus.edu.sg Abstract Visual relations, such as “person ride bike” and “bike next to car”, offer a comprehensive scene understanding of an image, and have already shown their great utility in … Tue Dec 04 07:45 AM -- 09:45 AM (PST) @ Room 210 #35 ... Zheng Shou (Columbia University) Alireza Zareian (Columbia University) hanwang Zhang (NTU) Shih-Fu Chang (Columbia University) More from the Same Authors. Hang Gao 1, Zheng Shou , Alireza Zareian , Hanwang Zhang2, Shih-Fu Chang1 1Columbia University, 2Nanyang Technological University {hg2469, zs2262, az2407, sc250}@columbia.edu hanwangzhang@ntu.edu.sg Abstract Deep neural networks suffer from over-fitting and catastrophic forgetting when trained with small data. During my Ph.D. study, I was fortunate to have opportunities to work closely with Prof. Hanwang Zhang from Nanyang Technological University (2016-2019), and Prof. Shih-Fu Chang from Columbia University (2017-2020). Read Hanwang Zhang's latest research, browse their coauthor's research, and play around with their algorithms Nanyang Assistant Professor. Shih-Fu Chang. 12/05/2017 ∙ by Hanwang Zhang, ... Nanyang Technological University ∙ Columbia University ∙ 0 ∙ share We focus on grounding (i.e., localizing or linking) referring expressions in images, e.g., "largest elephant standing behind baby elephant". Hanwang Zhang is with Department of Computer Science, Columbia University, USA. Hanwang Zhang. Try again later. Current results range from 2013 to 2015. Columbia University Libraries. Hang Gao, Zheng Shou, Alireza Zareian, Hanwang Zhang, and Shih-Fu Chang. Many names lack affiliations. Undergraduate works. Hanwang Zhang (张含望) Assistant Professor, SCSE, Nanyang Technological University Verified email at ntu.edu.sg Tat-Seng Chua National University of Singapore Verified email at comp.nus.edu.sg Wei Liu Tencent Verified email at ee.columbia.edu December 2018 NIPS'18: Proceedings of the 32nd International Conference on Neural Information Processing Systems. Video Question Answering via Gradually Refined Attention over Appearance and Motion∗ Dejing Xu‡, Zhou Zhao‡, Jun Xiao‡, Fei Wu‡, Hanwang Zhang§, Xiangnan He¶, Yueting Zhuang‡ ‡Zhejiang University, §Columbia University, ¶National University of Singapore {xudejing, zhaozhou, yzhuang}@zju.edu.cn, {junx,wufei}@cs.zju.edu.cn In recent years, deep neural networks have yielded immense success on speech recognition, computer vision and natural language processing. Neural Collaborative Filtering ∗ Xiangnan He National University of Singapore, Singapore xiangnanhe@gmail.com Lizi Liao National University of Singapore, Singapore SCA-CNN: Spatial and Channel-wise Attention in Convolutional Networks for Image Captioning Long Chen 1Hanwang Zhang2 Jun Xiao Liqiang Nie3 Jian Shao1 Wei Liu4 Tat-Seng Chua5 1Zhejiang University 2Columbia University 3Shandong University 4Tencent AI Lab 5National University of Singapore Abstract Visual attention has been successfully applied in struc- Hang Gao, Zheng Shou, Alireza Zareian, Hanwang Zhang, and Shih-Fu Chang. Hang Gao 1, Zheng Shou 1, Alireza Zareian 1, Hanwang Zhang 2, Shih-Fu Chang 1 1 Columbia University, 2 Nanyang Technological University {hg2469, zs2262, az2407, sc250}@columbia.edu hanwangzhang@ntu.edu.sg He is currently an Assistant Professor with Nanyang Technological University, Singapore. See the complete profile on LinkedIn and discover Hanwang’s connections and jobs at similar companies. Du Tran, Jamie Ray, Zheng Shou, Shih-Fu Chang, Manohar Paluri. Check back later. Du Tran, Jamie Ray, Zheng Shou, Shih-Fu Chang, Manohar Paluri. Shih-Fu Chang's 20 research works with 736 citations and 1,954 reads, including: Deep Learning Guided Building Reconstruction from Satellite Imagery-derived Point Clouds Brian Chen,1 Bo Wu,1 Alireza Zareian,1 Hanwang Zhang,2 Shih-Fu Chang1 1Columbia University, 2Nanyang Technological University fbc2754,bo.wu,az2407,sc250g@columbia.edu; hanwangzhang@ntu.edu.sg Abstract We formulate a practical yet challenging problem: General Partial Label Learning (GPLL). Many bibliographic records have only author initials. Before this, I was a undergraduate student of Dalian University of Technology (2011-2015). Hanwang Zhang†, Zawlin Kyaw‡, Shih-Fu Chang†, Tat-Seng Chua‡ †Columbia University, ‡National University of Singapore {hanwangzhang, kzl.zawlin}@gmail.com; sfchang@ee.columbia.edu; dcscts@nus.edu.sg Abstract Visual relations, such as “person ride bike and “bike next to car, offer a comprehensive scene understanding Hanwang Zhang 2020 Poster: Causal Intervention for Weakly-Supervised Semantic Segmentation » … (Hons.) School of Computer Science and Engineering (SCSE) Nanyang Technological University Block N4 #02c-87, Nanyang Avenue, Singapore 639798 . Jianglong Zhang Communication University of China zhangjianglong135@126.com Xiangnan He National University of Singapore xiangnanhe@gmail.com Hanwang Zhang Columbia University hanwangzhang@gmail.com Richang Hong Hefei University of Technology hongrc.hfut@gmail.com Qi Tian University of Texas at San Antonio Hanwang Zhang (Nanyang Technological University, Singapore) Svebor Karaman (DataMiner) Xu Zhang (Amazon) Former Visitors: Wei-Kai Chan (MediaTek) Prof. Wei-Hai Li (University of Science and Technology of China) Prof. Min-Jen Tsai (National Jiaotong University) Elie El-Khoury (IRIT) Prof. Nenghai Yu (University of Science and Technology of China) Nevenka Dimitrova (Philips) Jason … Hanwang Zhang is with Department of Computer Science, Columbia University, USA. The ones marked, X He, L Liao, H Zhang, L Nie, X Hu, TS Chua, Proceedings of the 26th International Conference on World Wide Web, 173-182, L Chen, H Zhang, J Xiao, L Nie, J Shao, L Wei, TS Chua, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Proceedings of the 39th International ACM SIGIR conference on Research and …, J Chen, H Zhang, X He, L Nie, W Liu, TS Chua, Proceedings of the 40th International ACM SIGIR conference on Research and …, IEEE Transactions on Multimedia 19 (9), 2045-2055, J Xiao, H Ye, X He, H Zhang, F Wu, TS Chua, IEEE Transactions on Knowledge and Data Engineering, H Zhang, F Shen, W Liu, X He, H Luan, TS Chua, H Zhang, ZJ Zha, Y Yang, S Yan, Y Gao, TS Chua, ACM Transactions on Multimedia Computing, Communications, and Applications …, Proceedings of the IEEE Conference on Computer Vision and Pattern …, J Song, H Zhang, X Li, L Gao, M Wang, R Hong, IEEE Transactions on Image Processing 27 (7), 3210-3221, Proceedings of the IEEE International Conference on Computer Vision, 4274-4282, J Chen, X Song, L Nie, X Wang, H Zhang, TS Chua, Proceedings of the 24th ACM international conference on Multimedia, 898-907, H Zhang, X Shang, H Luan, M Wang, TS Chua, ACM transactions on multimedia computing, communications, and applications …, IEEE Transactions on multimedia 17 (2), 216-228, Proceedings of the IEEE International Conference on Computer Vision, D Xu, Z Zhao, J Xiao, F Wu, H Zhang, X He, Y Zhuang, Proceedings of the 25th ACM international conference on Multimedia, 1645-1653, New articles related to this author's research, University of Science and Technology of China, School of Data Science, University of Electronic Science and Technology of China (电子科技大学), Professor of Electrical Engineering and Computer Science, Columbia University, Professor of Data Science & AI, Monash University, Ph.D candidate, University of Science and Technology of China, Research Fellow, Nanyang Technological University, PhD Student, National University of Singapore, University of Science and Technology of China, Assistant Professor, Singapore Management University, SCA-CNN: Spatial and Channel-wise Attention in Convolutional Networks for Image Captioning, Fast matrix factorization for online recommendation with implicit feedback, Attentive collaborative filtering: Multimedia recommendation with item-and component-level attention, Video Captioning With Attention-Based LSTM and Semantic Consistency, Visual Translation Embedding Network for Visual Relation Detection, Attentional factorization machines: Learning the weight of feature interactions via attention networks, Attribute-Augmented Semantic Hierarchy: Towards a Unified Framework for Content-Based Image Retrieval, Auto-encoding scene graphs for image captioning, Zero-shot visual recognition using semantics-preserving adversarial embedding networks, Self-supervised video hashing with hierarchical binary auto-encoder, Learning Image and User Features for Recommendation in Social Networks, Micro tells macro: predicting the popularity of micro-videos via a transductive model, Learning from collective intelligence: Feature learning using social images and tags, Multimedia summarization for social events in microblog stream, PPR-FCN: Weakly Supervised Visual Relation Detection via Parallel Pairwise R-FCN, Video question answering via gradually refined attention over appearance and motion, Grounding Referring Expressions in Images by Variational Context. Long Chen 1Hanwang Zhang2 Jun Xiao Wei Liu3 Shih-Fu Chang4 1Zhejiang University 2Nanyang Technological University 3Tencent AI Lab 4Columbia University flongc, junxg@zju.edu.cn; hanwangzhang@ntu.edu.sg; fwliu, sfchangg@ee.columbia.edu DO $(1 7UDLQ 7HVW 7HVW 681 &8% 7UDLQ 7HVW 7HVW D E Figure 1: (a) Attribute variance heat maps of the 312 attributes in CUB birds … Date Published range begin – Date Published range end. We propose to compose dynamic tree structures that place the objects in an image into a visual context, helping visual reasoning tasks such as scene graph generation and visual … Columbia University Libraries. Hanwang Zhang. Proceedings of the European Conference on Computer Vision (ECCV), 154-171, 2018. We use cookies to ensure that we give you the best experience on our website. The following articles are merged in Scholar. Skip slideshow. The ACM DL is a comprehensive repository of publications from the entire field of computing. Despite Academic Commons. Copyright © 2021 ACM, Inc. MM '20: Proceedings of the 28th ACM International Conference on Multimedia, MM '19: Proceedings of the 27th ACM International Conference on Multimedia, NIPS'18: Proceedings of the 32nd International Conference on Neural Information Processing Systems, MM '18: Proceedings of the 26th ACM international conference on Multimedia, Hierarchical Scene Graph Encoder-Decoder for Image Paragraph Captioning, Question-Aware Tube-Switch Network for Video Question Answering, Single-shot Semantic Image Inpainting with Densely Connected Generative Networks, Learning Using Privileged Information for Food Recognition, Low-shot learning via covariance-preserving adversarial augmentation networks, Context-Aware Visual Policy Network for Sequence-Level Image Captioning, All Holdings within the ACM Digital Library. Toggle facets Refine your search Author. Nanyang Technological University, Shih-Fu Chang. Hang Gao 1, Zheng Shou 1, Alireza Zareian 1, Hanwang Zhang 2, Shih-Fu Chang 1 1 Columbia University, 2 Nanyang Technological University {hg2469, zs2262, az2407, sc250}@columbia.edu hanwangzhang@ntu.edu.sg. Yang HAN of Columbia University, NY (CU) | Read 25 publications | Contact Yang HAN For each dataset, the top row is the performance by Hamming ranking and the bottom row is by table lookup (RQ 1). You are adding the first comment! A direct search interface for Author Profiles will be built. Mike Zheng SHOU Columbia University Verified email at columbia.edu. Long Chen (陈隆) Zhejiang University Verified email at zju.edu.cn. Hanwang Zhang hanwangzhang@ntu.edu.sg Nanyang Technological University Weiyue Wang weiyuewa@usc.edu University of Southern California Peter N. Belhumeur belhumeur@cs.columbia.edu.com Columbia University Ulrich Neumann uneumann@usc.edu University of Southern California Abstract In this paper, we introduce a stochastic generation framework Compared to the traditional Partial Label Learning (PLL) problem, GPLL relaxes … In recent years, deep neural networks have yielded immense success on speech recognition, computer vision and natural language processing. Search for Hanwang Zhang's work. Heng Tao Shen is the correspondence author. I am a second-year CS Ph.D. student at UC Berkeley and a member of Berkeley AI Research, advised by Angjoo Kanazawa. Shih-Fu Chang Professor of Electrical Engineering and Computer Science, Columbia University Verified email at columbia.edu. Hanwang has 3 jobs listed on their profile. An institutional view of works emerging from their faculty and researchers will be provided along with a relevant set of metrics. In particular, authors or members of the community will be able to indicate works in their profile that do not belong there and merge others that do belong but are currently missing. Zero-Shot Visual Recognition using Semantics-Preserving Adversarial Embedding Network. Hang Gao Contact: er@clbuensdeg.eegeh.aky unscramble About. Columbia University, Hanwang Zhang. Hanwang Zhang Columbia University hanwangzhang@gmail.com Richang Hong Hefei University of Technology hongrc.hfut@gmail.com Qi Tian University of Texas at San Antonio qi.tian@utsa.edu ABSTRACT Di‡erent from traditional long videos, micro-videos are much ({longc, ) The ACM Digital Library is published by the Association for Computing Machinery. International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR), 2016 (Full Oral, Best Paper Award Honorable Mention). Home Hanwang Zhang. Shuicheng Yan, 颜水成, FSAEng, FIEE... YITU, NUS Verified email at nus.edu.sg. International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR), 2017 … Hanwang Zhang received the B.Eng. This is a general yet … ConvNet Architecture Search for Spatiotemporal Feature Learning.