Selected industrial projects

Yahoo Taiwan Supermarket App	IBM IMARS	Smart Supermarket Surveillance System at Tokyo
Lead contributor of "image2product" function	Lead contributor of making IMARS 100x times faster	Contributor to "action detection" function

Selected peer-reviewed publications

Viusual Memory Question Answering
Lu Jiang, Liangliang Cao, Yannis Kalantidis, Sachin, Farfade, Alex Hauptmann
AAAI demo, 2017

Delving Deep into Personal Photo and Video Search
Lu Jiang, Yannis Kalantidis, Liangliang Cao, Sachin, Farfade, Jiliang Tang, Alex Hauptmann
ACM International Conference on Web Search and Data Mining (WSDM), 2017.

Detecting Sarcasm in Multimodal Social Platforms
Rossano Schifanella, Paloma de Juan, Joel Tetreault, Liangliang Cao
ACM Multimedia, 2016
[Press report]

Robust Visual-Textual Sentiment Analysis: When Attention meets Tree-structured Recursive Neural Network
Quanzeng You, Liangliang Cao, Hailin Jin, Jiebo Luo
ACM Multimedia, 2016.

TGIF: A New Dataset and Benchmark on Animated GIF Description
Yuncheng Li, Yale Song, Liangliang Cao, Joel Tetreault, Larry Goldberg, Alejandro Jaimes, Jiebo Luo
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016
[dataset and code, A side by side comparison ]

Video2GIF: Automatic Generation of Animated GIFs from Video
Michael Gygli, Yale Song, Liangliang Cao
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016
[dataset, Online demo , Press report 1, Press report 2]

Faster and Cheaper: Parallelizing Large-Scale Matrix Factorization on GPUs
Wei Tan, Liangliang Cao, Liana Fong
High-Performance Parallel and Distributed Computing, 2016.
[code, Press report]

Building Joint Spaces for Relation Extraction
Chang Wang, Liangliang Cao, James Fan
International Joint Conference on Artificial Intelligence (IJCAI), 2016
[Slides]

Poker-CNN: A Pattern Learning Strategy for Making Draws and Bets in Poker Games
Nikolai Yakovenko, Liangliang Cao, Colin Raffel, James Fan
AAAI Conference on Artificial Intelligence (AAAI), 2016.
[code]

GPU-FV: Realtime Fisher Vector and Its Applications in Video Monitoring
Wenying Ma, Liangliang Cao, Lei Yu, Guoping Long, Yucheng Li
ACM International Conference in Multimedia Retrieval, 2016
[code]

Massive-scale learning of image and video semantic concepts
John R. Smith, Liangliang Cao, Noel C. F. Codella, Matthew L. Hill, Michele Merler, Quoc-Bao Nguyen, E. Pring, R. A. Uceda-Sosa
IBM Journal of Research and Development 59(2/3), 2015

A multifaceted approach to social multimedia- based prediction of elections
Quanzeng You, Liangliang Cao, Yang Cong, Xianchao Zhang, and Jiebo Luo
IEEE Transaction on Multimedia, Vol 17, No. 12, 2015.

A Multifaceted Approach to Social Multimedia-Based Prediction of Elections
Quanzeng You, Liangliang Cao, Yang Cong, Xianchao Zhang, Jiebo Luo
IEEE Transation on Multimedia 17(12): 2271-2280, 2015

Medical Synonym Extraction with Concept Space Models
Chang Wang, Liangliang Cao, Bowen Zhou
International Joint Conference on Artificial Intelligence (IJCAI), 2015

You are what you tweet...pic! gender prediction based on semantic analysis of social media images
Michele Merler, Liangliang Cao, John R. Smith
IEEE International Conference on Multimedia and Expo (ICME), 2015

The placing task: A large-scale geo-estimation challenge for social-media videos and images
Jaeyoung Choi, Bart Thomee, Gerald Friedland, Liangliang Cao, Karl Ni, Damian Borth, Benjamin Elizalde, Luke Gottlieb, Carmen Carrano, Roger Pearce, Doug Poland
Proceedings of the 3rd ACM Multimedia Workshop on Geotagging and Its Applications in Multimedia, 2014

A spatial-color layout feature for representing galaxy images
Yin Cui, Yongzhou Xiang, Kun Rong, Rogerio Schmidt Feris, Liangliang Cao
IEEE Winter Conference on Application of Computer Vision (WACV), 2014

Cuteness Recognition and Localization in the Photos of Animals
Yu Bao, Jing Yang, Liangliang Cao, Haojie Li, Jinhui Tang
ACM Multimedia 2014: 1193-1196

Efficient maximum appearance search for large-scale object detection
Qiang Chen, Zheng Song, Rogerio Feris, Ankur Datta, Liangliang Cao, Zhongyang Huang, Shuicheng Yan
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2013

Designing category-level attributes for discriminative visual recognition
Felix Yu, Liangliang Cao, Rogerio Feris, John Smith, Shih-Fu Chang
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2013

Learning Locally-Adaptive Decision Functions for Person Verification
Zhen Li, Shiyu Chang, Feng Liang, Thomas S. Huang, Liangliang Cao, John R. Smith
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2013
[Experiments using VIPeR dataset] [Experiments using CAVIAR4REID dataset]

Learning by focusing: A new framework for concept recognition and feature selection Liangliang Cao, Leiguang Gong, John R. Kender, Noel C. F. Codella, John R. Smith
International Conference on Multimedia and Expo (ICME), 2013

Delta-Simrank Computing on MapReduce
Liangliang Cao, Brian Cho, Hyun Duk Kim, Zhen Li, Min-Hsuan Tsai, Indranil Gupta, Chengxiang Zhai, Thomas S. Huang
1st 1st International Workshop on BigMine, 2012
[Best paper award]

Submodular video hashing: a unified framework towards video pooling and indexing
Liangliang Cao, Zhenguo Li, Yadong Mu, Shih-Fu Chang
ACM Multimedia 2012: 299-308

Learning latent spatio-temporal compositional model for human action recognition
Xiaodan Liang, Liang Lin, Liangliang Cao
ACM Conf. on Multimedia (ACM-MM), 2012

Scene Aligned Pooling for Complex Video Recognition
Liangliang Cao, Yadong Mu, Apostol Natsev, Shih-Fu Chang, Gang Hua, John R Smith
ECCV 2012

Learning to Search Efficiently in High Dimensions
Zhen Li, Huazhong Ning, Liangliang Cao, Tong Zhang, Yihong Gong, Thomas S. Huang
Neural Information Processing Systems (NIPS), 2011

Large-scale image classification: fast feature extraction and SVM training
Yuanqing Lin, Fengjun Lv, Shenghuo Zhu, Ming Yang, Timothee Cour, Kai Yu,
Liangliang Cao, Thomas S. Huang
IEEE Conf. Computer Vision and Pattern Recognition (CVPR), 2011.
1st place in ImageNet LSVRC 2010

Geographical Topic Discovery and Comparison
Zhijun Yin, Liangliang Cao, Jiawei Han, Chengxiang Zhai, Thomas S. Huang
World Wide Web(WWW), 2011.

Diversified Trajectory Pattern Raning in Geo-tagged Social Media
Zhijun Yin, Liangliang Cao, Jiawei Han, Jiebo Luo, and Thomas Huang
SIAM International Conference on Data Mining (SDM), 2011.

Image Segmentation by MAP-ML Estimations
Shifeng Chen, Liangliang Cao, Yueming Wang, Jianzhuang Liu, and Xiaoou Tang.
IEEE Trans. on Image Processing (IP), Vol 19, No. 9, 2010
[software, an early version at CVPR'07]

The Wisdom of Social Multimedia: Using Flickr For Prediction and Forecast
Xin Jin, Andrew C. Gallagher, Liangliang Cao, Jiebo Luo, Jiawei Han
ACM Conf. on Multimedia (ACM-MM), 2010

RankCompete: Simultaneous Ranking and Clustering of Web Photos
Liangliang Cao, Andrey Del Pozo, Xin Jin, Jiebo Luo, Jiawei Han and Thomas S. Huang.
World Wide Web(WWW), 2010. (poster)

Cross-dataset Action Recognition
Liangliang Cao, Zicheng Liu and Thomas S. Huang
IEEE Proc. Computer Vision and Pattern Recognition (CVPR), 2010

Action Detection in Complex Scenes with Spatial and Temporal Ambiguities
Yuxiao Hu, Liangliang Cao, Fengjun Lv, Shuicheng Yan, Yihong Gong, and Thomas S. Huang
IEEE Proc. Int'l Conf. Computer Vision (ICCV), 2009
[ICCV Oral]

Heterogeneous feature machines for visual recognition
Liangliang Cao, Jiebo Luo, Feng Liang, Thomas S Huang
IEEE International Conference on Computer Vision (ICCV), 2009

Robust 3D Object Reconstruction from Line Drawings by the Reduction of Dimension of Optimization
Jianzhuang Liu, Liangliang Cao, Zhenguo Li and Xiaoou Tang.
IEEE Trans. Pattern Analysis and Machine Intelligence (PAMI), vol. 30 (2), pp 315-327, February 2008.

What the Back of the Object Looks Like: 3D Reconstruction from Line Drawings Without Hidden Line
Liangliang Cao, Jianzhuang Liu and Xiaoou Tang.
IEEE Trans. Pattern Analysis and Machine Intelligence (PAMI), vol. 30 (3), pp 507-517, March 2008.
[An early version in ICCV'05]

Annotating photo collections by label propagation according to multiple similarity cues
Liangliang Cao, Jiebo Luo, Thomas S. Huang
16th ACM international conference on Multimedia (ACM MM), pp. 121-130, 2008

Annotating Collections of Photos Using Hierarchical Event and Scene Models
Liangliang Cao, Jiebo Luo, Henry Kautz and Thomas S. Huang.
IEEE Proc. Computer Vision and Pattern Recognition (CVPR), 2008.

Spatially Coherent Latent Topic Model for Concurrent Segmentation and Classification of Objects and Scenes
Liangliang Cao and Fei-Fei Li
IEEE Proc. Int'l Conf. Computer Vision (ICCV) 2007.
[supplementary materials]

Automatic Segmentation of Lung Fields from Radiographic Images of SARS Patients Using a New Graph Cuts Algorithm
Shifeng Chen, Liangliang Cao, Jianzhuang Liu and Xiaoou Tang
International Conf. on Pattern Recognition (ICPR), 2006.

3D Object Retrieval with Easy 3D Query Generation and Graph Based Relevance Feedback
Liangliang Cao, Jianzhuang Liu and Xiaoou Tang
ACM Conf. Multimedia (ACM-MM), 2006.

Patents

Hierarchical filtered Motion Field for Action Recognition
Zicheng Liu, YingLi Tian, Liangliang Cao, and Zhengyou Zhang
US Patent 8,639,042, 2014

Adaptive Action Detection
Zicheng Liu and Liangliang Cao
US Patent 9,014,420, 2015

Techniques for Ground-Level Photo Geolocation Using Digital Elevation
Liangliang Cao, Noel Codella, Gang Hua, John R. Smith
US Patent 9,165,217, 2015.

Techniques for Spatial Semantic Attribute Matching for Location Identification
Liangliang Cao, Noel Codella, Gang Hua, Leiguang Gong, Apostol Natsev, and John R. Smith
US Patent 9,251,433, 2016

Assigning Labels to Images in a Collection
Jiebo Luo and Liangliang Cao
US Patent App. 12/396,642, 2009

Association of Visual Labels and Event Context in Image Data
Liangliang Cao, Yuan-Chi Chang, and Quoc-Bao Nguyen
US Patent App. 13/975,497, 2013.

Generating a Training Model Based on Feedback
Liangliang Cao, Ning Duan, Qian Lin, Chen Wang, Junchi Yan, Xin Zhang
US Patent App. 14/055,387, 2013.

Memory-aware Matrix Factorization
Wei Tan, Liangliang Cao, Liana Fong
US Patent Application, Assignee: IBM, filed 2015.

Semi-supervised Learning for Word Embedding
Chang Wang, Liangliang Cao, James Fan, Bing Xiang, Bowen Zhou
US Patent Application, Assignee: IBM, filed 2015.

More to come