[Biography](google scholar, wordpress)

I'm currently a member of Cognitive and Interactive Vision & Digital Dntelligence E-commerce team, in Machine Intelligence Technology Lab, Alibaba Damo Academy. My adviser is Prof. Rong Jin. I finished my PhD at Harbin Institute of Technology, with Professor Qingming Huang. My research interests include multimedia multimedia retrieval, social media analysis, and computer vision. I used to dive into several industral projects i.e. "Pailitao", "TaobaoLive", etc. Currently, I start to work on video content structuring, multi-model learning.

[News]

• 2022.3.28: One paper accepted as ORAL in CVPR 2022

• 2021.7.28: Two paper accepted in ACM MM 2021

• 2021.2.11: One paper accepted in ICASSP 2021

• 2020.10.16: One paper accepted in AAAI 2021

• 2019.8.16: Two paper accepted in CIKM 2019

• 2018.5.31: One paper accepted in KDD 2018, Visual Search At Alibaba [pdf]

[Research Experience]

• Machine Intelligence Technology Lab, Alibaba Damo Academy

Algorithm Expert: April, 2019 – Present

Short video recommendation, deep embedding learning, user behavior mining

• Visual Intelligent Lab, Harbin Institute of Technology, Part of Joint Development Laboratory (JDL), China

Ph.D Student: Sep, 2012 – April 2017 Supervisor: Prof.Qingming Huang

Crowd Behavior Analysis and Mining, Crowd Behavior Semantic Representation, Crowd based Applications

• Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China

Research Assistant, Nov, 2011 – Jun, 2012 Supervisor: Prof.Qingming Huang

Abnormal detection,Crowd behavior recognition.

• Cognitive, Linguistic & Psychological Sciences (CLPS), Brown University, U.S

Visiting Student, Sep, 2013 – Sep,2014 Supervisor: Prof.Thomas Serre

Understanding the brain mechanisms underlying the recognition of crowd and complex visual scenes.

• Microsoft Research Aisa (MSRA), Beijing, China

Intern Student, Sep, 2015 – May,2016 Supervisor: Dr.Kuiyuan Yang

Similar image service based on deep transfer networks for Microsoft XiaoIce.

[Selected Publications]

【Video Commodity Shopping】

• Exploring visual-audio composition alignment network for quality fashion retrieval in video

Yanhao Zhang, Jianmin Wu, Xiong Xiong, Dangwei Li, Chenwei Xie, Yun Zheng, Pan Pan, Yinghui Xu,ICASSP 2021 [PDF]

• Fashion Focus: Multi-modal Retrieval System for Video Commodity localization in E-commerce

Yanhao Zhang, Qiang Wang, Pan Pan, Yun Zheng, Cheng Da, Siyang Sun and Yinghui Xu, AAAI 2021 [PDF]

【Large Scale Visual Search】

• Virtual ID Discovery from E-commerce Media At Alibaba

Yanhao Zhang, Pan Pan, Yun Zheng, Kang Zhao, Jianmin Wu, Rong Jin

ACM International Conference on Information and Knowledge Management (CIKM), 2019 [PDF]

• Large-Scale Visual Search with Binary Distributed Graph at Alibaba

Kang Zhao, Pan Pan, Yun Zheng, Yanhao Zhang, Changxu Wang, Rong Jin

ACM International Conference on Information and Knowledge Management (CIKM), 2019 [PDF]

• Visual Search at Alibaba

Yanhao Zhang, Pan Pan, Yun Zheng, Kang Zhao, Yingya Zhang, Xiaofeng Ren, Rong Jin

International Conference on Knowledge Discovery & Data Mining (SIGKDD), 2018 [PDF]

【Crowd , action, tracking】

Conference Paper

• Yanhao Zhang, Lei Qin, Qingming Huang, Kuiyuan Yang, Hongxun Yao, Jun Zhang. From Seed Discovery To Deep Reconstruction, Predicting Saliency In Crowd Via Deep Networks, ACM MM 2016, Netherland.

• Yanhao Zhang, Lei Qin, Rongrong Ji, Sicheng Zhao, Hongxun Yao, Qingming Huang. Crowd video retrieval via Deep Attribute-embedding Ranking, IEEE ICME 2016, Seattle, U.S.

• Yanhao Zhang, Lei Qin, Shengping Zhang, Hongxun Yao, Qingming Huang. Formation period matters: Towards socially consistent group detection via dense subgraph seeking, ICMR 2015, Shanghai, China.

• Yanhao Zhang, Shengping Zhang, Qingming Huang, Thomas Serre. Learning sparse prototypes for crowd perception via Ensemble Coding Mechanisms, HBU@ECCV 2014, Zurich, Switzerland.

• Yanhao Zhang, Lei Qin , Hongxun Yao, Pengfei Xu, Qingming Huang. Beyond Particle Flow: Bag Of Trajectory Graphs For Dense Crowd Event Recognition, IEEE ICIP 2013, Sydney, Australia.

• Yanhao Zhang, Xiaoshuai Sun, Hongxun Yao, Lei Qin, Qingming Huang. Aesthetic Composition Representation for portrait photographing recommendation, IEEE ICIP 2012, Orlando, U.S.

• Yanhao Zhang, Lei Qin, Hongxun Yao, Qingming Huang. Abnormal crowd behavior detection based on Social attribute-aware force model, IEEE ICIP 2012, Orlando, U.S. (Oral)

• Yanhao Zhang, Hongxun Yao, Pengfei Xu, RongrongJi, Xiaoshuai Sun, Xianming Liu.Video Stabilization based on Saliency driven SIFT Matching and discriminative Ransac. ACM ICIMCS 2011, Chengdu, China. (Oral)

• Pengfei Xu, Xian-Ming Liu, Hongxun Yao, Yanhao Zhang, Shaopeng Tang. Structured Textons for Texture Representation, IEEE ICIP 2013, Sydney, Australia.

• Tingting Han, Hongxun Yao, Yanhao Zhang, Pengfei Xu. A spatial-temporal constraint-based action recognition method, IEEE ICIP 2013, Sydney, Australia.

• Xue Li, Hongxun Yao, Xiaoshuai Sun, Yanhao Zhang. On dense sampling size, IEEE ICIP 2013, Sydney, Australia.

• Yi Liu, Lei Qin, Zhongwei Cheng, Yanhao Zhang, Weigang Zhang, Qingming Huang . Weakly Supervised Cross-view Action Recognition via Sequential Motion Accumulation . IEEE ICIP 2014,Paris, France.

• Yi Liu, Lei Qin, Zhongwei Cheng, Yanhao Zhang, Weigang Zhang, Qingming Huang . DA-CCD: A Novel Action Representation by Deep Architecture of Local Depth Feature. IEEE ICIP 2014,Paris, France.

• Yuankai Qi, Hongxun Yao, Xiaoshuai Sun, Xin Sun, Yanhao Zhang, Qingming Huang. Structure-Aware Multi-Object Discovery For Weakly Supervised Tracking. IEEE ICIP 2014, Paris, France.

• Tingting Han, Hongxun Yao, Xiaoshuai Sun, Yanhao Zhang. Clustering By Saliency”—Unsupervised Discovery Of Crowd Activities, IEEE ICIP 2014, Paris, France.

• Sicheng Zhao, Hongxun Yao, You Yang, Yanhao Zhang. Affective Image Retrieval via Multi-Graph Learning. ACM MM 2014, Orlando, U.S.

• Tingting Han, Hongxun Yao, Xiaoshuai Sun, Yanhao Zhang, Sicheng Zhao, Xiusheng Lu, Yinghao Huang, Wenlong Xie. "Clustering of Dancelets": Towards Video Recommendation Based on Dance Styles. ACM MM 2015: 915-918

• Xiusheng Lu,Shengping Zhang, Hongxun Yao, Xin Sun, Yanhao Zhang, Histograms Of Locally Aggregated Oriented Gradients. IEEE ICIP 2015.

Journal Paper

• Yanhao Zhang, Lei Qin, Rongrong Ji, Sicheng Zhao, Qingming Huang, Jiebo Luo. Exploring Coherent Motion Patterns via Structured Trajectory Learning for Crowd Mood Modeling, IEEE Transactions on Circuits and Systems for Video Technology (TCSVT). 2016.

• Yanhao Zhang, Lei Qin, Rongrong Ji, Hongxun Yao, Qingming Huang. Social Attribute-aware Force Model: Exploiting Richness of Interaction for Abnormal Crowd Detection, IEEE Transactions on Circuits and Systems for Video Technology (TCSVT). 2015.

• Yanhao Zhang, Qingming Huang, Lei Qin, Sicheng Zhao, Pengfei Xu, Hongxun Yao. Representing dense crowd event recognition using bag of trajectory graphs, Signal, Image and Video Processing (SIVP) .2014

• Yanhao Zhang, Qingming Huang, Lei Qin, Sicheng Zhao, Xiusheng Lu, Xiaoshuan Sun, Hongxun Yao. Strategy for Aesthetic Photographing Recommendation via Collaborative Composition Model, IET Computer Vision (IET CV). 2015

• Shengping Zhang, Hongxun Yao, Xin Sun, Kuanquan Wang, Jun Zhang, Xiusheng Lu, Yanhao Zhang. Action recognition based on over complete independent components analysis, Information Science. 2014.

• Sicheng Zhao, Lujun Chen, Hongxun Yao, Yanhao Zhang, Xiaoshuai Sun. Strategy for Dynamic 3D Depth Data Matching Towards Robust Action Retrieval. Neurocomputing, 2014

• Shengping Zhang, Huiyu Zhou, Hongxun Yao, Yanhao Zhang, Kuanquan Wang, Jun Zhang, Adaptive NormalHedge for Robust Visual Tracking, Signal Processing, 2014

• Sicheng Zhao; Hongxun Yao; Fanglin Wang; Yanhao Zhang; Yasi Wang; Shaohui Liu, View-based 3D Object Retrieval via Multi modal Graph Learning, Signal Processing, 2014

• Tingting Han, Hongxun Yao, Xiaoshuai Sun, Sicheng Zhao, Yanhao Zhang. Unsupervised Discovery of Crowd Activities by Saliency-based Clustering. Neurocomputing, 2015

• Yinghao Huang, Hongxun Yao, Sicheng Zhao, Yanhao Zhang. Towards more efficient and flexible face image deblurring using robust salient face landmark detection. Multimedia Tools and Applications, 2015

[Reviewer]

IEEE Transactions on Circuits and Systems for Video Technology (TCSVT)

IEEE Transactions on Multimedia (TMM)

IEEE Transactions on Image Processing (TIP)

IEEE Transactions on Cybernetics (TCYB)

IEEE Transactions on Knowledge and Data Engineering (TKDE)

ACM Transactions on Intelligent Systems and Technology (TIST)

IET Computer Vision

PLOS ONE

Neurocomputing

[Awards]

National Development Bank Innovation Team 2016

National Scholarship 2015

Huawei Scholarship 2015