Publications

2019

Joint Discriminative and Generative Learning for Person Re-Identification [Code] [Video] [Supp]
Z. Zheng, X. Yang, Z. Yu, L. Zheng, Y. Yang, J. Kautz
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019 (Oral)

STEP: Spatio-Temporal Progressive Learning for Video Action Detection [Supp]
X. Yang, X. Yang, M.-Y. Liu, F. Xiao, L. Davis, J. Kautz
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019 (Oral)

CityFlow: A City-Scale Benchmark for Multi-Target Multi-Camera Vehicle Tracking and Re-Identification [Supp] [Data]
Z. Tang, M. Naphade, M.-Y. Liu, X. Yang, S. Birchfield, S. Wang, R. Kumar, D. Anastasiu, J.-N. Hwang
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019 (Oral)

A Delay Metric for Video Object Detection: What Average Precision Fails to Tell [Code]
H. Mao, X. Yang, W. Dally
IEEE International Conference in Computer Vision (ICCV), 2019

PAMTRI: Pose-Aware Multi-Task Learning for Vehicle Re-Identification Using Randomized Synthetic Data
Z. Tang, M. Naphade, S. Birchfield, J. Tremblay, W. Hodge, R. Kumar, S. Wang, X Yang
IEEE International Conference in Computer Vision (ICCV), 2019

Models Matter, So Does Training: An Empirical Study of CNNs for Optical Flow Estimation [Code]
D. Sun, X. Yang, M.-Y. Liu, J. Kautz
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2019

Discovering Spatio-Temporal Action Tubes
Y. Ye, X. Yang, Y. Tian
Journal of Visual Communication and Image Representation (JVCI), 2019

2018

PWC-Net: CNNs for Optical Flow using Pyramid, Warping and Cost Volume [Code] [Supp] [Project]
D. Sun, X. Yang, M.-Y. Liu, J. Kautz
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018 (Oral)

Making Convolutional Networks Recurrent for Visual Sequence Learning [Supp]
X. Yang, P. Molchanov, J. Kautz
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018

MoCoGAN: Decomposing Motion and Content for Video Generation [Code]
S. Tulyakov, M.-Y. Liu, X. Yang, J. Kautz
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018

Budget-Aware Activity Detection with A Recurrent Policy Network [Supp]
B. Mahasseni, X. Yang, P. Molchanov, J. Kautz
British Machine Vision Conference (BMVC), 2018 (Oral)

Video You Only Look Once: Overall Temporal Convolutions for Action Recognition
L. Jing, X. Yang, Y. Tian
Journal of Visual Communication and Image Representation (JVCI), 2018

2017

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

Dynamic Facial Analysis: From Bayesian Filtering to Recurrent Neural Network [Blog] [Project]
J. Gu, X. Yang, S. De Mello, J. Kautz
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017

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

3D Convolutional Neural Network with Multi-Model Framework for Action Recognition
L. Jing, Y. Ye, X. Yang, Y. Tian
IEEE International Conference on Image Processing (ICIP), 2017 (Oral)

2016

Multilayer and Multimodal Fusion of Deep Neural Networks for Video Classification
X. Yang, P. Molchanov, J. Kautz
ACM Multimedia, 2016 (Oral)

Online Detection and Classification of Dynamic Hand Gestures with Recurrent 3D Convolutional Neural Networks [Data] [Project]
P. Molchanov, X. Yang, S. Gupta, K. Kim, S. Tyree, J. Kautz
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016  

Region Trajectories for Video Semantic Concept Detection
Y. Ye, X. Rong, X. Yang, Y. Tian
ACM International Conference on Multimedia Retrieval (ICMR), 2016

Towards Selecting Robust Hand Gestures for Automotive Interfaces
S. Gupta, P. Molchanov, X. Yang, K. Kim, S. Tyree, J. Kautz
IEEE Intelligent Vehicles Symposium (IVS), 2016

2015

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

Discriminative Hierarchical K-Means Tree for Large-Scale Image Classification
S. Chen, X. Yang, Y. Tian
IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2015

Exploring Pooling Strategies based on Idiosyncrasies of Spatio-Temporal Interest Points
Y. Ye, X. Yang, Y. Tian
ACM International Conference on Multimedia Retrieval (ICMR), 2015

Hybrid Example based Single Image Super Resolution
Y. Xian, X. Yang, Y. Tian
International Symposium on Visual Computing (ISVC), 2015 (Oral)

CCNY at TRECVID 2015: Video Semantic Concept Localization
Y. Ye, X. Rong, X. Yang, Y. Tian
NIST TREC Video Retrieval Evaluation (TRECVID), 2015

2014

Super Normal Vector for Activity Recognition Using Depth Sequences [Code]
X. Yang, Y. Tian
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2014

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

Effective 3D Action Recognition Using EigenJoints
X. Yang, Y. Tian
Journal of Visual Communication and Image Representation (JVCI), 2014 (Best Paper Award)

Scene Text Recognition in Multiple Frames based on Text Tracking
X. Rong, C. Yi, X. Yang, Y. Tian
IEEE International Conference on Multimedia & Expo (ICME), 2014

Assistive Clothing Pattern Recognition for Visually Impaired People
X. Yang, S. Yuan, Y. Tian
IEEE Transactions on Human-Machine Systems (THMS), 2014

CCNY at TRECVID 2014: Surveillance Event Detection
Y. Xian, X. Rong, X. Yang, Y. Tian
NIST TREC Video Retrieval Evaluation (TRECVID), 2014

2013

Histogram of 3D Facets: A Characteristic Descriptor for Hand Gesture Recognition
C. Zhang, X. Yang, Y. Tian
IEEE International Conference on Automatic Face and Gesture Recognition (FG), 2013 (Oral)

Feature Representations for Scene Text Character Recognition: A Comparative Study
C. Yi, X. Yang, Y. Tian
International Conference on Document Analysis and Recognition (ICDAR), 2013

AT&T Research at TRECVID 2013: Surveillance Event Detection
X. Yang, Z. Liu, E. Zavesky, D. Gibbon, B. Shahraray, Y. Tian
NIST TREC Video Retrieval Evaluation (TRECVID), 2013

Texture Representations Using Subspace Embeddings
X. Yang, Y. Tian
Pattern Recognition Letters (PRL), 2013

Visual Speech Learning Using Dynamic Lip Movement based Video Segmentation and Comparison
C. Mazuera, X. Yang, Y. 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
Y. Tian, X. Yang, C. Yi, A. Arditi
Machine Vision and Applications (MVA), 2013

2012

Recognizing Actions Using Depth Motion Maps based Histograms of Oriented Gradients [Code]
X. Yang, C. Zhang, Y. Tian
ACM Multimedia, 2012

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

MediaCCNY at TRECVID 2012: Surveillance Event Detection [Code] [Data]
X. Yang, C. Yi, L. Cao, Y. Tian
NIST TREC Video Retrieval Evaluation (TRECVID), 2012

Robust and Effective Component based Banknote Recognition for the Blind
F. Zaman, X. Yang, Y. 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]
X. Yang, S. Yuan, Y. Tian
ACM Multimedia, 2011

Robust and Effective Component based Banknote Recognition by SURF Features
F. Zaman, X. Yang, Y. 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]
X. Yang, Y. Tian, C. Yi, and A. Arditi
ACM Multimedia, 2010

Robust Door Detection in Unfamiliar Environments by Combining Edge and Corner Features
X. Yang, Y. Tian
IEEE CVPR Workshop on Computer Vision Applications for Visually Impaired, 2010

Patents

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

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

Online Detection and Classification of Dynamic Gestures with Recurrent Convolutional Neural Networks
US10157309 Issued on Dec. 18, 2018

Systems and Methods for Dynamic Facial Analysis Using A Recurrent Neural Network
US10373332 Issued on Aug. 6, 2019

Fusing Multilayer and Multimodal Deep Neural Networks for Video Classification
US Patent App. 15/660719, 2017

Transforming Convolutional Neural Networks for Visual Sequence Learning
US Patent App. 15/880472, 2018

System and Method for Content and Motion Controlled Action Video Generation
US Patent App. 15/939098, 2018

System and Method for Optical Flow Estimation
US Patent App. 15/942213, 2018

Iterative Spatio-Temporal Action Detection in Video
US Patent App. 16/152303, 2018

Budget-Aware Method for Detecting Activity in Video
US Patent App. 16/202703, 2018