Refereed Publications:

  • Minding the Gaps in a Video Action Analysis Pipeline.

Jia Chen, Jiang Liu, Junwei Liang, Ting-Yao Hu, Wei Ke, Wayner Barrios, Dong Huang, Alexander Hauptman
WACV Workshop, 2019.

  • DecideNet: Counting Varying Density Crowds Through Attention Guided Detection and Density Estimation.

Jiang Liu, Chenqiang Gao, Deyu Meng, Alexander G. Hauptmann
CVPR, 2018.

  • Informedia@ Trecvid 2017.

Jia Chen, Junwei Liang, Jiang Liu, Shizhe Chen, Chenqiang Gao, Qin Jin, Alexander G. Hauptmann
Technical report for TRECVID 2017 competition.

  • Rewind to track: Parallelized Apprenticeship Learning with Backward Tracklets.

Jiang Liu, Jia Chen, De Cheng, Chenqiang Gao, Alexander G. Hauptmann
IEEE International Conference on Multimedia and Expo, 2017. (oral) [pdf][slides][interactive tool]

  • A novel learning-based frame pooling method for Event Detection.

Lan Wang, Chenqiang Gao, Jiang Liu, Deyu Meng
Signal Processing, 2017.

  • An Error-activation-guided Blind Metric for Stitched Panoramic Image Quality Assessment.

Luyu Yang, Jiang Liu, Chenqiang Gao
CCF Chinese Conference on Computer Vision, 2017.

  • Two-stream contextualized CNN for fine-grained image classification.

Jiang Liu, Chenqiang Gao, Deyu Meng, Wangmeng Zuo
AAAI 2016 Student Poster Program.[abstract]

  • A learning-based frame pooling model for event detection.

Jiang Liu, Chenqiang Gao, Lan Wang, Deyu Meng
[arxiv]

  • People counting based on head detection combining Adaboost and CNN in crowded surveillance environment.

Chenqiang Gao, Pei Li, Yajun Zhang, Jiang Liu, Lan Wang
Neurocomputing, 2016.

  • InfAR Dataset: Infrared Action Recognition at Different Times.

Chenqiang Gao, Yinhe Du, Jiang Liu, Jing Lv, Luyu Yang, Deyu Meng, Alexander G. Hauptmann
Neurocomputing, 2016. [project page] [dataset]

  • A New Dataset and Evaluation for Infrared Action Recognition.

Chenqiang Gao, Yinhe Du, Jiang Liu, Luyu Yang, and Deyu Meng.
CCF Chinese Conference on Computer Vision (2015) (Best paper honorable mention).


  • From constrained to unconstrained datasets: an evaluation of local action descriptors and fusion strategies for interaction recognition

Chenqiang Gao, Luyu Yang, Yinhe Du, Zeming Feng, and Jiang Liu.
World Wide Web (2015): 1-12.


Projects:

  • DIVA: Deep Intermodal Video Analytics.

    • Develop algorithms for robust automatic activity detection in a multi-camera streaming video environment. Activities will be enriched by person and object detection. DIVA will address activity detection for both forensic applications and for real-time alerting. [setup script] [docker images]

    [full video]

  • MDP Labeler: An interactive multiple object tracking dataset annotation tool based on apprenticeship learning.

    • Developing an interactive multiple object tracking annotation and analysis tool, enables user to fast annotate and analyze object trajectories in unconstrained videos.[code]

  • People counting based on head detection combining Adaboost and CNN in crowded surveillance environment.

    • Developing a person counting system combined Adaboost algorithm with CNN framework. The false alarm rate is greatly reduced with the proposed method.

  • MyFlower: An automatic flower species recognition system.

    • We construct a two-stream contextualized Convolutional Neural Network (CNN) for flower recognition.[poster]