S
icheng ZHAO (赵思成)

Ph.D., Postdoc research fellow
EECS, UC Berkeley
Email: schzhao at gmail dot com

Biography

I am a postdoc research fellow athe Department of Electrical Engineering and Computer Sciences, University of California Berkeley. My supervisor is Prof. Kurt Keutzer. I worked as a postdoc at School of SoftwareTsinghua University, China, from 2016 to 2017, working with Prof. Guiguang Ding.  I obtained the Ph.D. degree at School of Computer Science and TechnologyHarbin Institute of Technology, China, in 2016, under the supervision of Prof. Hongxun Yao. I was a research assistant at School of ComputingNational University of Singapore from 2013 to 2014, advised by Prof. Tat-Seng Chua and Prof. Yue Gao. My research interests include multimedia affective computing, social media analysis, and computer vision, especially focusing on image emotion analysis and related applications. Currently, I start to work on domain adaptation. My research works have been published in top-tier conferences such as ACM MM, IJCAI, AAAI, NeurIPS, ICCV, CVPR, ICRA, and top-tier journals such as IEEE TAFFC, TCYB, TMM, TCSVT, TITS, ACM TOMM.

News
  • [Call for paper] IEEE International Conference on Multimedia and Expo (ICME) 2020 Special Session on "Domain Adaptation for Multimedia Semantic Understanding" [Deadline: 13 December 2019[CFP] [URL]
  • [Call for paper] International Conference on Multimedia Modeling (MMM) 2020 Special Session on "MMAC: Multi-Modal Affective Computing of Large-Scale Multimedia Data" [Deadline: 31 July 2019[CFP] [closed]
  • [Call for paper] ACM International Conference on Multimedia Retrieval (ICMR) 2019 Special Session on "MMAC: Multi-Modal Affective Computing of Large-Scale Multimedia Data" [Deadline: 20 April 2019[CFP] [closed]
  • [Call for paper] IEEE International Conference on Image Processing (ICIP) 2019 Special Session on "Machine Learning for Affective Computing of Large-scale Visual Content" [Deadline extended to: 12 February 2019[CFP] [closed]
  • [Call for paper] IEEE International Conference on Multimedia and Expo (ICME) 2019 Special Session on "Pedestrian detection, tracking and re-identification in videos" [Deadline extended to: 17 December 2018[CFP] [URL] [closed]
  • [Call for paper] Signal, Image and Video Processing (SIVP) Special Issue on "Learning Methods for Social Media Computing of Heterogeneous Multimedia Data" [Deadline: 31 January 2019[CFP] [closed]
  • [Call for paper] ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM) Special Issue on "Affective Computing for Large-Scale Heterogeneous Multimedia Data" [Deadline extended to: 31 January 2019[CFP] [closed]
  • [Call for paper] Neural Processing Letters (NPL) Special Issue on "Affective Computing of Large-Scale Visual Content: Directions, Methodologies, and Applications" [Deadline: 30 September 2018[CFP] [closed]
  • [Call for paper] ACM MM 2018 Workshop on "MMAC: Multi-Modal Affective Computing of Large-Scale Multimedia Data[Deadline: 21 July 2018[URL[closed]
  • [Call for paper] IEEE VCIP 2018 Special Session on "3D Big Data: Representation, Understanding and Applications" [Deadline: 25 May 2018[URL[closed]
  • [Call for paper] ACM ICMR 2018 Special Session on "Large-Scale 3D Multimedia Analysis and Applications[Deadline extended to: 25 February 2018 23:59 PST[URL] [closed]
  • [Call for paper] Multimedia Tools and Applications Special Session on "Large-Scale 3D Multimedia Analysis and Applications[Deadline extended to: 31 August 2017[CFP] [closed]

Research Experiences

Berkeley DeepDriveBerkeley Artificial Intelligence Research Lab
UC Berkeley: 2017.09 - 

Postdoc research fellow,  Supervisor: Prof. Kurt Keutzer

Domain adaptation, multimedia affective computing

Multimedia Intelligence GroupTsinghua University: 2016.08 - 2017.09

Postdoc research fellow,  Supervisor: Prof. Guiguang Ding

Multimedia affective computing, image captioning

Lab for Media SearchNational University of Singapore: 2013.07 - 2014.06

Visiting student, Supervisor: Prof. Tat-Seng Chua and Prof. Yue Gao

Social media analysis, brand tracking and social event detection

Visual Intelligence Lab, Harbin Institute of Technology: 2009.09 - 2016.07

Research assistant,  Supervisor: Prof. Hongxun Yao

Multimedia affective computing, Image emotion ayalysis and applications


Selected Publications [full list]

Conference Papers:

27. Sicheng Zhao, Guangzhi Wang, Shanghang Zhang, Yang Gu, Yaxian Li, Zhichao Song, Pengfei Xu, Runbo Hu, Hua Chai, Kurt Keutzer. Multi-source Distilling Domain AdaptationAAAI Conference on Artificial Intelligence (AAAI), Feb. 2020, New York, USA. [full paperoral]

26. Sicheng Zhao, Yunsheng Ma, Yang Gu, Jufeng Yang, Tengfei Xing, Pengfei Xu, Runbo Hu, Hua Chai, Kurt Keutzer. An End-to-End Visual-Audio Attention Network for Emotion Recognition in User-Generated VideosAAAI Conference on Artificial Intelligence (AAAI), Feb. 2020, New York, USA. [full paperoral]

25. Chuang Lin#Sicheng Zhao#, Lei Meng, Tat-Seng Chua. Multi-source Domain Adaptation for Visual Sentiment ClassificationAAAI Conference on Artificial Intelligence (AAAI), Feb. 2020, New York, USA. [#Co-first authors, full paper]

24. Yuwei He, Xiaoming Jin, Guiguang Ding, Yuchen Guo, Jungong Han, Jiyong Zhang, Sicheng ZhaoHeterogeneous Transfer Learning With Weighted Instance-Correspondence DataAAAI Conference on Artificial Intelligence (AAAI), Feb. 2020, New York, USA. [full paper]

23. Sicheng Zhao, Bo Li, Xiangyu Yue, Yang Gu, Pengfei Xu, Runbo Hu, Hua Chai, Kurt Keutzer. Multi-Source Domain Adaptation for Semantic SegmentationAdvances in Neural Information Processing Systems (NeurIPS), Dec. 2019, Vancouver, Canada. [full paper] [code]

22. Sicheng Zhao, Zizhou Jia, Hui Chen, Leida Li, Guiguang Ding, Kurt Keutzer. PDANet: Polarity-consistent Deep Attention Network for Fine-grained Visual Emotion RegressionACM International Conference on Multimedia (ACM MM), Oct. 2019, Nice, France. [full paper][code]

21. Hui Chen, Guiguang Ding, Zijia Lin, Sicheng Zhao, Jungong Han. Cross-Modal Image-Text Retrieval with Semantic ConsistencyACM International Conference on Multimedia (ACM MM), Oct. 2019, Nice, France. [full paper]

20. Xingxu Yao, Dongyu She, Sicheng Zhao, Jie Liang, Yu-Kun Lai, Jufeng Yang. Attention-Aware Polarity Sensitive Embedding for Affective Image RetrievalIEEE International Conference on Computer Vision (ICCV), Oct. 2019, Seoul, Korea. [full paper]

19. Chi Zhan, Dongyu She, Sicheng ZhaoMing-Ming Cheng, Jufeng Yang. Zero-Shot Emotion Recognition via Affective Structural EmbeddingIEEE International Conference on Computer Vision (ICCV), Oct. 2019, Seoul, Korea. [full paper]

18. Xiangyu Yue, Yang Zhang, Sicheng ZhaoAlberto Sangiovanni-Vincentelli, Kurt Keutzer, Boqing Gong. Domain Randomization and Pyramid Consistency: Simulation-to-Real Generalization without Accessing Target Domain DataIEEE International Conference on Computer Vision (ICCV), Oct. 2019, Seoul, Korea. [full paper]

17. Sicheng Zhao, Chuang Lin, Pengfei Xu, Sendong Zhao, Yuchen Guo, Ravi Krishna, Guiguang Ding, Kurt Keutzer. CycleEmotionGAN: Emotional Semantic Consistency Preserved CycleGAN for Adapting Image EmotionsAAAI Conference on Artificial Intelligence (AAAI), Jan. 2019, Honolulu, USA. [full paperoral]

16. Sendong Zhao, Ting LiuSicheng Zhao, Fei WangA Neural Multi-Task Learning Framework to Jointly Model Medical Named Entity Recognition and NormalizationAAAI Conference on Artificial Intelligence (AAAI), Jan. 2019, Honolulu, USA. [full paperoral]

15. Yuchen Guo, Guiguang Ding, Jungong Han, Xiaohan Ding, Sicheng Zhao, Zheng Wang, Chenggang Yan, Qionghai Dai. Dual-view Ranking with Hardness Assessment for Zero-shot LearningAAAI Conference on Artificial Intelligence (AAAI), Jan. 2019, Honolulu, USA. [full paper]

14. Bichen Wu#, Xuanyu Zhou#Sicheng Zhao#, Xiangyu Yue, Kurt Keutzer. SqueezeSegV2: Improved Model Structure and Unsupervised Domain Adaptation for Road-Object Segmentation from a LiDAR Point CloudIEEE International Conference on Robotics and Automation (ICRA), May 2019, Montreal, Canada. [#Co-first authors]

13. Sicheng Zhao, Xin Zhao, Guiguang Ding, Kurt Keutzer. EmotionGAN: Unsupervised Domain Adaptation for Learning Discrete Probability Distributions of Image EmotionsACM International Conference on Multimedia (ACM MM), Oct. 2018, Seoul, Korea. [full paperoral]

12. Sicheng Zhao, Guiguang Ding, Jungong Han, Yue Gao. Personality-Aware Personalized Emotion Recognition from Physiological SignalsInternational Joint Conference on Artificial Intelligence (IJCAI), Jul. 2018, Stockholm, Sweden. [full paperoral]

11. Sicheng Zhao, Guiguang Ding, Qingming Huang, Tat-Seng Chua, Bjorn W. Schuller, Kurt Keutzer. Affective Image Content Analysis: A Comprehensive SurveyInternational Joint Conference on Artificial Intelligence (IJCAI), Jul. 2018, Stockholm, Sweden. [full paperoral]

10. Hui Chen, Guiguang Ding, Zijia Lin,  Sicheng Zhao, Jungong Han. Show, Observe and Tell: Attribute-driven Attention Model for Image CaptioningInternational Joint Conference on Artificial Intelligence (IJCAI), Jul. 2018, Stockholm, Sweden. [full paperoral]

9. Yuchen Guo, Guiguang Ding, Jungong Han, Sicheng Zhao, Bin Wang. Implicit Non-linear Similarity Scoring for Recognizing Unseen ClassesInternational Joint Conference on Artificial Intelligence (IJCAI), Jul. 2018, Stockholm, Sweden. [full paperoral]

8. Bichen WuAlvin WanXiangyu YuePeter H. JinSicheng ZhaoNoah GolmantAmir GholaminejadJoseph GonzalezKurt Keutzer. Shift: A Zero FLOP, Zero Parameter Alternative to Spatial ConvolutionsIEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9127-9135, Jun. 2018, Salt Lake City, USA. [full paperspotlight]

7. Hui Chen, Guiguang Ding, Sicheng Zhao, Jungong Han. Temporal-difference Learning with Sampling Baseline for Image CaptioningAAAI Conference on Artificial Intelligence (AAAI), Feb. 2018, New Orleans, USA. [full paper]

6. Sicheng Zhao, Guiguang Ding, Yue Gao, Jungong Han. Learning Visual Emotion Distributions via Multi-Modal Features FusionACM International Conference on Multimedia (ACM MM), pp. 369-377, Oct. 2017, Mountain View, USA. [full paper]

5. Sicheng Zhao, Guiguang Ding, Yue Gao, Jungong Han. Approximating Discrete Probability Distribution of Image Emotions by Multi-Modal Features FusionInternational Joint Conference on Artificial Intelligence (IJCAI), pp. 4669-4675, Aug. 2017, Melbourne, Australia. [full paperoral]

4. Minghai Chen, Guiguang Ding, Sicheng Zhao, Hui Chen, Jungong Han, Qiang Liu. Reference Based LSTM for Image CaptioningAAAI Conference on Artificial Intelligence (AAAI), pp. 3981-3987, Feb. 2017, San Francisco, USA. [full paperoral]

3. Sicheng Zhao, Hongxun Yao, Yue Gao, Rongrong Ji, Wenlong Xie, Xiaolei Jiang, Tat-Seng Chua. Predicting Personalized Emotion Perceptions of Social ImagesACM International Conference on Multimedia (ACM MM), pp. 1385-1394, Oct. 2016, Amsterdam, the Netherlands. [full paperoral[data]

2. Yue Gao, Sicheng Zhao, Yang Yang and Tat-Seng Chua. Multimedia Social Event Detection in MicroblogInternational Conference on Multimedia Modeling (MMM), pp. 269-281, Jan. 2015, Sydney, Australia. [oralbest paper runner-up award]

1. Sicheng Zhao, Yue Gao, Xiaolei Jiang, Hongxun Yao, Tat-Seng Chua, Xiaoshuai Sun. Exploring Principles-of-Art Features for Image Emotion RecognitionACM International Conference on Multimedia (ACM MM), pp. 47-56, Nov. 2014, Orlando, USA. [full paperoral]

Journal Papers:

11. Sicheng ZhaoShangfei Wang, Mohammad Soleymani, Dhiraj Joshi, Qiang Ji. Affective Computing for Large-Scale Heterogeneous Multimedia Data: A Survey. ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM), 2019. [accepted]

10. Hui Chen, Guiguang Ding, Zijia Lin,  Sicheng ZhaoJungong Han. ACMNet: Adaptive Confidence Matching Network for Cross-Modal Image-Text Retrieval. ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM), 2019. [accepted]

9. Sicheng ZhaoGuiguang Ding, Yue Gao, Xin Zhao, Youbao Tang, Jungong Han, Hongxun Yao, Qingming Huang. Discrete Probability Distribution Prediction of Image Emotions With Shared Sparse Learning. IEEE Transactions on Affective Computing (TAFFC), 2019. [accepted]

8. Sicheng ZhaoAmir Gholaminejad, Guiguang Ding, Yue Gao, Jungong Han, Kurt KeutzerPersonalized Emotion Recognition by Personality-aware High-order Learning of Physiological Signals. ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM) 15(1s): 14:1-14:18, 2019.

7. Dong Wang, Hongxun Yao, Federico Tombari, Sicheng Zhao, Bin Wang, Hong Liu. Learning Descriptors with Cube Loss for View-based 3D Object Retrieval. IEEE Transactions on Multimedia (TMM) 21(8): 2071-2082, 2019.

6. Wenlong Xie, Hongxun Yao, Xiaoshuai Sun, Tingting Han, Sicheng Zhao, Tat-Seng Chua. Discovering Latent Discriminative Patterns for Multi-Mode Event RepresentationIEEE Transactions on Multimedia (TMM) 21(6): 1425-1436, 2019.

5. Sicheng Zhao, Hongxun Yao, Yue Gao, Guiguang Ding, Tat-Seng Chua. Predicting Personalized Image Emotion Perceptions in Social Networks. IEEE Transactions on Affective Computing (TAFFC) 9(4): 526-540, 2018.[data]

4. Sicheng Zhao, Yue Gao, Guiguang Ding, Tat-Seng Chua. Real-Time Multimedia Social Event Detection in MicroblogIEEE Transactions on Cybernetics (TCYB) 48(11): 3218-3231, 2018.

3. Guiguang Ding, Wenshuo Chen, Sicheng Zhao, Jungong Han, Qiaoyan Liu. Real-Time Scalable Visual Tracking via Quadrangle Kernelized Correlation FiltersIEEE Transactions on Intelligent Transportation Systems (TITS) 19(1): 140-150, 2018.

2. Yanhao Zhang, Lei Qin, Rongrong Ji, Sicheng Zhao, Qingming Huang, Jiebo Luo. Exploring Coherent Motion Patterns via Structured Trajectory Learning for Crowd Mood ModelingIEEE Transactions on Circuits and Systems for Video Technology (TCSVT) 27(3): 635-648, 2017.

1. Sicheng Zhao, Hongxun Yao, Yue Gao, Rongrong Ji, Guiguang Ding. Continuous Probability Distribution Prediction of Image Emotions via Multi-Task Shared Sparse RegressionIEEE Transactions on Multimedia (TMM) 19 (3): 632-645, 2017. [data]