maple_logo

Biography

Publications

Research

Team

Teaching

Services

Sponsors

  

Directions to Harris Corporation  Engineering Center

 Campus Map

 

 

 

Laboratory  for MAchine Perception and LEarning (MAPLE)

Research | Awards | Projects | Students | Publications | Teaching | Services | News  | Sponsors

 

    Guo-Jun Qi, Ph.D.

Qi


 

 

Email:
guojunq at gmail dot com

guojun.qi at huawei.com

Laboratory (formerly): 

Machine Perception and Learning (MAPLE) 

http://maple.cs.ucf.edu [url]

Github homepage:

https://github.com/maple-research-lab [github]


Research Interests

  • Machine Learning and Pattern Recognition 
  • Computer Vision and Multimedia Computing 
  • Data Mining and Data Analytics - Knowledge Discovery and Representation

Awards

  • 2015 Best Paper Finalist, International ACM Conference on Multimedia 
  • 2014 Best Student Paper Award (co-recipent as the mentor of the student author), IEEE International Conference on Data Mining (ICDM).
  • 2013 "Best of ICDE Paper" by IEEE Transactions on Knowledge and Data Engineering
  • 2011,2012 IBM Fellowship, IBM
  • Best Paper Award, The 15th ACM International Conference on Multimedia (ACM SIGMM) 
  • 2007 Best Research Intern, Microsoft Research Asia 
  • 2007 Microsoft Fellowship, Microsoft 
  • 2005 Guo Moruo Scholarship, USTC (Top Scholarship in USTC)

Recent Research Projects

  • [AutoEncoding Transformations (AET)] A long version paper on Generalized Transformation-Equivariant Representations (GTER) Learning via AutoEncoding Transformations (AET)  is available at [pdf].  See more information about this series of works on 1) the unsupervised training of AETv1 [link] and AETv2 [link],  2) the (semi-)supervised training  [link] and the ensemble training [pdf] of AET, as well as its applications to 3) the unsupervised training of Graph Convolutional Neural Networks [pdf].

  • [Regularized GANs] We propose a regularized Loss-Sensitive GAN (LS-GAN), and extend  it to a generalized version (GLS-GAN) with many variants of regularized GANs as a special case. We have proved both distributional consistency and generalizability of the LS-GAN model with polynomial sample complexity. See more details about 1) LS-GAN and GLS-GAN in our paper [pdf], 2) an incomplete map of regularized GANs in our view [url], as well as 3) a recent extension by learning an encoder of samples with manifold margins generated by the GAN [github:  torch, blocks].  The LS-GAN was also adopted in Microsoft CNTK (Cognitive  Toolkit) as its standard regularized GAN model [link]. 

  • [Small Data Challenges] Take a look at our survey of"Small Data Challenges in Big Data Era: A Survey of Recent Progress on Unsupervised and Semi-Supervised Methods" [pdf], and our tutorial presented at IJCAI 2019 [link] with the presentation slides [pdf].

  • [First-Take-All Hashing] A novel paradigm of First-Take-All (FTA) hashing was proposed to efficiently index and recognize the time-series signals of human activities [pdf], cross-modal data [pdf], as well as 2D images [pdf].  It was also applied to classify singals of brain neural activities for an early diagnosis of ADHD [pdf], where the proposed method is one order of magnitude faster than state-of-the-art methods with the best accuracy on the real-world multi-facility dataset of a Kaggle competition.

  • [MAPLE Github] The MAPLE lab is releasing the source code of our research projects at github [url]. We are sincerely inviting everyone who is interested in our works to try them. Feedbacks and pull requests are warmly welcome. 

Back to top

News

Recent News:  

  • [November 2019] A paper "POST: POlicy-based Switch Tracking" was accepted by AAAI 2020.
  •  [November 2019] Dr. Qi was elected into IEEE IVMSP and MMSP technical committees.
  • [September 2019] Our paper "Hierarchical Long Short-Term Concurrent Memory for Human Interaction Recognition" has been accepted by IEEE T-PAMI
  • [August 2019] Dr. Qi gave a tutorial on "Small Data Challenges in Big Data Era" at IJCAI 2019. See the slides [pdf] at the tutorial homepage [link].  A keynote on "Learning Generalized Transforamation-Equivariant Representations" was also presented at IJCAI Tusion 2019.
  • [July 2019] Our paper "AVT: Unsupervised Learning of Transformation Equivariant Representations by Autoencoding Variational Transformations" has been accepted by ICCV 2019 [ pdf].  In this work, we study the AutoEncoding Transformations (AET) from an information-theoretic perspective, where we present a novel view of point to generalize the Transformation-Equivariant Representation.
  • [July 2019] "Few-Shot Image Recognition with Knowledge Transfer" was accepted by ICCV 2019.
  • [July 2019] Dr. Qi will serve as a General Chair for ICME 2021 at Shenzhen. 

Archived News:
  • [July 2019] Dr. Qi is appointed as an Associate Editor for IEEE Transactions on Multimedia.
  • [May 2019] Dr. Qi is appointed as an Associate Editor for IEEE Transactions on Image Processing.
  • [February 2019] Our paper "Large-scale Bisample Learning on ID Versus Spot Face Recognition" was accepted by IJCV, see preprint [pdf].
  • [Febuary 2019] Our paper "AET vs. AED: Unsupervised Representation Learning by Auto-Encoding Transformations rather than Data" was accepted by CVPR 2019, see preprint [pdf].  A novel unsupervised learning approach was presented to train Transformation Equivariant Representation (TER) that achieves the state-of-the-art performance on ImageNet by the unsupervised AlexNet (53.2% of Top-1 accuracy) vs. 59.7% of Top-1 accuracy of fully supervised AlexNet.
  • [Feburary 2019] Our paper "Task-Agnostic Meta-Learning for Few-shot Learning" has been accepted by CVPR 2019. See our preprint at arvix [pdf]. It presents a meta-learning regularization approach by encouraging unbiased meta-training over training tasks so that the meta-model can be better generalized to unseen tasks.  
  • Our paper "CapProNet: Deep Feature Learning via Orthogonal Projections onto Capsule Subspaces" was accepted by NIPS 2018. We present a novel capsule projection architecture, setting up a new state-of-the-art for the capsule nets in literature on CIFAR, SVHN and ImageNet. The source code was released at our github homepage.
  • Our paper "Learning Compact Features for Human Activity Recognition via Probabilistic First-Take-All" has been accepted by IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI). The accepted paper and source code will be released soon.
  • We propose a Loss-Sensitive GAN (LS-GAN), and extend  it to a generalized LS-GAN (GLS-GAN) in which Wasserstein GAN is a special case. We have proved both distributional consistency and generalizability of the LS-GAN model in a polynomial sample complexity in terms of the model size and its Lipschitz constants. See more details in our paper [pdf], and an incomplete map of GANs in our view [url]. 
  • Our paper on "Generalized Loss-Sensitive Adversarial Learning with Manifold Margins [pdf]" was accepted by ECCV 2018, where we present to train the Loss-Sensitive GAN by learning a pull-back mapping from a sample x to its projection z onto the manifold generated by the GAN. We shall its applications into generating interpolated edits between images as well as semi-supervised learning with state-of-the-art performances. Source codes are available at [github:  torch, blocks]. 
  • Our paper on "A Principled Approach to Hard Triplet Generation via Adversarial Nets " was accepted by ECCV 2018, where we develop a principled way to generate harder yet more informative triplets to train query and re-identification models. State-of-the-art performances were demonstrated on the re-id and fine-grained classification problems.
  • Microsoft CNTK is officially supporting LS-GAN. You can make a side-by-side comparison with the other GAN models at https://www.cntk.ai/pythondocs/CNTK_206C_WGAN_LSGAN.html.
  • Dr. Qi is serving as a senior TPC member for AAAI 2019.
  • Our paper on "High sensitivity with tiny candidates for Pulmonary Nodule Detection" was accepted by MICCAI 2018.
  • The paper "Global versus Localized Generative Adversarial Nets" will appear in CVPR 2018. We present a new construction of Laplacian-Beltrami operator to enable semi-supervised learning on manifolds without resorting to Laplacian graphs as an approximate. We also demonstrate the state-of-the-art performance on image classiciation tasks. The source codes are released ad available at [code 1: generation, code 2: semi-supervised learning].
  • Our paper "Interleaved Structured Sparse Convolutional Neural Networks" will appear in CVPR 2018 to present a new compact CNN model.
  • Dr. Qi is invited as an area chair for ICPR 2018.
  • Dr. Qi will serve as a Technical Program Co-chair for ACM Multimedia 2020 at Seattle.
  • We have a paper "Interleaved Group Group Convolutions for Deep Neural Networks" accepted by ICCV 2017, where a super compact and fast deep convolutional model was develop that can be deployed on mobile devices. Two types of group convolutions, a primal group sparse convolution and a dual point-wise permutation convolution, are developed to make the model more efficient. [pdf]
  • We released our sources for our ICML 2017 and KDD 2017 papers on State-Frequency LSTM [githubpdf] and stock price prediction [githubpdf].
  • Congratulations to Hao and Liheng on their ICML2017 and KDD2017 papers being accepted.  
  • Congratulations to Mr. Joey Velez-Ginorio, an undergraduate researcher of our group, on being selected as a Barry Goldwater scholar. This is the most prestigious undergraduate scholarship across the country established by the United States Congress to support highly qualified college students to pursue careers in STEM.
  • Dr. Qi will serve as an Area Chair for ICCV 2017.
  • Dr. Qi is serving as an Area Chair for ICME 2017
  • A paper on learning compact features that encode dynamics of video and sensor data has been accepted by ACM TOMM.  
  • A paper on jointly learning label classification and tag recommendation has been accepted by AAAI 2017.  
  • One paper developing an efficient ranking-based hashing algorithm has been accepted for the publication in IEEE Transactions on Pattern Analysis and Machine Intelligence. [pdf] [code
  • One paper "Tri-Clustered Tensor Completion for Social-Aware Image Tag Refinement" has been accepted for publication in IEEE Transactions on Pattern Analysis and Machine Intelligence
  • One paper has been accepted by IEEE Transactions on Pattern Analysis and Machine Intelligence for classifying images of rarely seen or unseen classes with the help of text labels. [pdf][code]  
  • Two research papers, including an oral presentation "Hierarchically Gated Deep Networks for Segmantic Segmentation", have been accepted for presentation at CVPR 2016, Las Vegas, Nevada. [pdf]
  • One paper has been accepted for plenary presentation at SIGKDD 2016. A fast detection method for brain disorder based on fMRI was presented. It is one order of magnitude faster than state-of-the-art methods with even better accuracy.   
  • Dr. Qi is serving as an Area Chair for ACM Multimedia 2016.   
  • Dr. Qi will serve as a Senior Program Committee Member for KDD 2016.  
  • International Conference on MultiMedia Modeling will go to Miami FL, 4-6 January 2016 [link].   Dr. Qi will serve as program co-chair.  
  • CFP: Special Issue on "Big Media Data: Understanding, Search, and Mining", in IEEE Transactions on Big Data [pdf] (deadline: July 1, 2015). 
  • CFP: "Deep Learning for Multimedia Computing", in IEEE Transactions on Multimedia [pdf] (The new deadline is April 20, 2015).
  • Our full research paper "Weekly-Shared Deep Transfer Networks for Heterogeneous-Domain Knowledge Propagation" has been selected as one of the four best paper candidates to be presented at ACM MM 2015.
  • One paper is accepted by ICCV 2015.  We developed a novel deep LSTM  model for analyzing human actions, where we explore the differential structure over memory states to study the dynamic saliency.
  • One full research paper "Weakly-Shared Deep Transfer Networks for Heterogeneous-Domain Knowledge Propagation" is accepted by ACM MM 2015.  We developed a novel cross-modal label transfer deep network, showing competitive performance on predicting image labels derived from the alignment with text documents.  
  • Dr. Qi is serving as an Area Chair for ACM Multimedia 2015
  • Three papers are accepted by KDD 2015. Congratulations to Vivek, Rohit, Shiyu and Wei!  In these papers, (1) we developed deep networks to reveal the brain neural connectivity by aligning  time-series activiations by neuron fires that are marked by calcium influx;  (2) we invented a new paradigm of dynamic model to select and predict sensors and their readings over time, as compared with the conventional static strategy; and (3) we developed heterogeneous networks to predict the cross-modal relevance between multimodal data.
  • One paper "Temporal-Order Preserving Dynamic Quantization for Human Action Recognition from Multimodal Sensor Streams" accepted by ICMR 2015.  On UTKinect-Action dataset, our best approach has achieved 100% accuracy. Congralulations to Jun and Kai! 
  • One paper "Sparse Composite Quantization" has been accepted by CVPR 2015. Congralutions to Ting!


Back to top

Last updated 00/00/00