Publications

My citations and full publications can be found on Google Scholar.

2018

Making Convolutional Networks Recurrent for Visual Sequence Learning [Supp]
Xiaodong Yang, Pavlo Molchanov, Jan Kautz
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018

PWC-Net: CNNs for Optical Flow using Pyramid, Warping and Cost Volume [Supp] [Project]
Deqing Sun, Xiaodong Yang, Ming-Yu Liu, Jan Kautz
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018 (Oral)

MoCoGAN: Decomposing Motion and Content for Video Generation [Project]
Sergey Tulyakov, Ming-Yu Liu, Xiaodong Yang, Jan Kautz
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018

Video You Only Look Once: Overall Temporal Convolutions for Action Recognition
Longlong Jing, Xiaodong Yang, Ying-Li Tian
Journal of Visual Communication and Image Representation (JVCI), 2018

2017

Super Normal Vector for Human Activity Recognition with Depth Cameras [Code]
Xiaodong Yang, Ying-Li Tian
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2017

Dynamic Facial Analysis: From Bayesian Filtering to Recurrent Neural Network [Project]
Jinwei Gu, Xiaodong Yang, Shalini De Mello, Jan Kautz
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017

Evaluation of Low-Level Features for Real-World Surveillance Event Detection [Code]
Yang Xian, Xuejian Rong, Xiaodong Yang, Ying-Li Tian
IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2017

3D Convolutional Neural Network with Multi-Model Framework for Action Recognition
Longlong Jing, Yuancheng Ye, Xiaodong Yang, Ying-Li Tian
IEEE International Conference on Image Processing (ICIP), 2017 (Oral)

Budget-Aware Activity Detection with A Recurrent Policy Network
Behrooz Mahasseni, Xiaodong Yang, Pavlo Molchanov, Jan Kautz
arXiv:1712.00097

2016

Multilayer and Multimodal Fusion of Deep Neural Networks for Video Classification
Xiaodong Yang, Pavlo Molchanov, Jan Kautz
ACM Multimedia, 2016 (Oral)

Online Detection and Classification of Dynamic Hand Gestures with Recurrent 3D Convolutional Neural Networks [Project]
Pavlo Molchanov, Xiaodong Yang, Shalini Gupta, Kihwan Kim, Stephen Tyree, Jan Kautz
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016  

Region Trajectories for Video Semantic Concept Detection
Yuancheng Ye, Xuejian Rong, Xiaodong Yang, Ying-Li Tian
ACM International Conference on Multimedia Retrieval (ICMR), 2016

Towards Selecting Robust Hand Gestures for Automotive Interfaces
Shalini Gupta, Pavlo Molchanov, Xiaodong Yang, Kihwan Kim, Stephen Tyree, Jan Kautz
IEEE Intelligent Vehicles Symposium (IVS), 2016

2015

Feature Representations for Human Activity Recognition in Color and Depth Sequences
Xiaodong Yang
Dissertation for Ph.D. Degree, 2015

Discriminative Hierarchical K-Means Tree for Large-Scale Image Classification
Shizhi Chen, Xiaodong Yang, Ying-Li Tian
IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2015

Exploring Pooling Strategies based on Idiosyncrasies of Spatio-Temporal Interest Points
Yuancheng Ye, Xiaodong Yang, Ying-Li Tian
ACM International Conference on Multimedia Retrieval (ICMR), 2015

Hybrid Example based Single Image Super Resolution
Yang Xian, Xiaodong Yang, Ying-Li Tian
International Symposium on Visual Computing (ISVC), 2015 (Oral)

CCNY at TRECVID 2015: Video Semantic Concept Localization
Yuancheng Ye, Xuejian Rong, Xiaodong Yang, Ying-Li Tian
NIST TREC Video Retrieval Evaluation (TRECVID), 2015

2014

Super Normal Vector for Activity Recognition Using Depth Sequences [Code]
Xiaodong Yang, Ying-Li Tian
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2014

Action Recognition Using Super Sparse Coding Vector with Spatio-Temporal Awareness [Code]
Xiaodong Yang, Ying-Li Tian
European Conference on Computer Vision (ECCV), 2014

Effective 3D Action Recognition Using EigenJoints
Xiaodong Yang, Ying-Li Tian
Journal of Visual Communication and Image Representation (JVCI), 2014 (Best Paper Award)

Scene Text Recognition in Multiple Frames based on Text Tracking
Xuejian Rong, Chucai Yi, Xiaodong Yang, Ying-Li Tian
IEEE International Conference on Multimedia & Expo (ICME), 2014

Assistive Clothing Pattern Recognition for Visually Impaired People
Xiaodong Yang, Shuai Yuan, Ying-Li Tian
IEEE Transactions on Human-Machine Systems (THMS), 2014

CCNY at TRECVID 2014: Surveillance Event Detection
Yang Xian, Xuejian Rong, Xiaodong Yang, Ying-Li Tian
NIST TREC Video Retrieval Evaluation (TRECVID), 2014

Polynormal Fisher Vector for Activity Recognition from Depth Sequences
Xiaodong Yang, Ying-Li Tian  
SIGGRAPH ASIA Workshop on Autonomous Virtual Humans and Social Robots, 2014

2013

Histogram of 3D Facets: A Characteristic Descriptor for Hand Gesture Recognition
Chenyang Zhang, Xiaodong Yang, Ying-Li Tian
IEEE International Conference on Automatic Face and Gesture Recognition (FG), 2013 (Oral)

Texture Representations Using Subspace Embeddings
Xiaodong Yang, Ying-Li Tian
Pattern Recognition Letters (PRL), 2013

Feature Representations for Scene Text Character Recognition: A Comparative Study
Chucai Yi, Xiaodong Yang, Ying-Li Tian
International Conference on Document Analysis and Recognition (ICDAR), 2013

AT&T Research at TRECVID 2013: Surveillance Event Detection
Xiaodong Yang, Zhu Liu, Eric Zavesky, David Gibbon, Behzad Shahraray, Ying-Li Tian
NIST TREC Video Retrieval Evaluation (TRECVID), 2013

Visual Speech Learning Using Dynamic Lip Movement based Video Segmentation and Comparison
Carol Mazuera, Xiaodong Yang, Ying-Li Tian
IEEE International Conference on Bioinformatics and Biomedicine (BIBM), 2013 (Oral)

Toward A Computer Vision based Wayfinding Aid for Blind Persons to Access Unfamiliar Indoor Environments
Ying-Li Tian, Xiaodong Yang, Chucai Yi, Aries Arditi
Machine Vision and Applications (MVA), 2013

2012

Recognizing Actions Using Depth Motion Maps based Histograms of Oriented Gradients [Code]
Xiaodong Yang, Chenyang Zhang, Ying-Li Tian
ACM Multimedia, 2012

EigenJoints based Action Recognition Using Naive-Bayes-Nearest-Neighbor
Xiaodong Yang, Ying-Li Tian
IEEE CVPR Workshop on Human Activity Understanding from 3D Data, 2012

MediaCCNY at TRECVID 2012: Surveillance Event Detection [Code] [Data]
Xiaodong Yang, Chucai Yi, Liangliang Cao, Ying-Li Tian
NIST TREC Video Retrieval Evaluation (TRECVID), 2012

Robust and Effective Component based Banknote Recognition for the Blind
Faiz Zaman, Xiaodong Yang, Ying-Li Tian
IEEE Transactions on System, Man, and Cybernetics (TSMC) Part C, 2012

2011

Recognizing Clothes Patterns for Blind People by Confidence Margin based Feature Combination [Data]
Xiaodong Yang, Shuai Yuan, Ying-Li Tian
ACM Multimedia, 2011

Robust and Effective Component based Banknote Recognition by SURF Features
Faiz Zaman, Xiaodong Yang, Ying-Li Tian
IEEE Wireless and Optical Communication Conference (WOCC), 2011  

2010

Context based Indoor Object Detection as an Aid to Blind Persons Accessing Unfamiliar Environments [Data]
Xiaodong Yang, Ying-Li Tian, Chucai Yi, and Aries Arditi
ACM Multimedia, 2010

Robust Door Detection in Unfamiliar Environments by Combining Edge and Corner Features
Xiaodong Yang, Ying-Li Tian
IEEE CVPR Workshop on Computer Vision Applications for Visually Impaired, 2010

Patents

Hand Gesture based Region of Interest Localization
US9778750 Issued on Oct. 3, 2017

Dynamic Hand Gesture based Region of Interest Localization
US9354711 Issued on May 31, 2016

Fusing Multilayer and Multimodal Deep Neural Networks for Video Classification
US Patent App. 15/660719, 2018

Online Detection and Classification of Dynamic Gestures with Recurrent Convolutional Neural Networks
US Patent App. 15/402128, 2017