Our mission is to enable machines to perceive and understand the real world, so they can intelligently and robustly perform in chanllenging tasks and scenarios.
  • Machine Perception: data acquisition and processing
  • Machine Learning: knowledge modeling and aggregation

Machine Learning

We conduct researches on probabilistic learning and inference, kernel methods and deep Learning, esp. Multimodal Deep Networks

Computer Vision

We work on a wide range of computer vision problems including visual scene understanding, video analysis and understanding and multimodal data analysis

Knowledge Representation

We are interested in several knowledge representation tasks such as discovery of trustworthy knowledge, multi-source knowledge aggregation, and heterogeneous network analysis

Recent News

[July. 2018]
Our paper on "Generalized Loss-Sensitive Adversarial Learning with Manifold Margins" 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.
[July. 2018]
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.
[July. 2018]
Dr. Qi is serving as senior TPC member for AAAI 2019.
[May. 2018]
Our paper on "High sensitivity with tiny candidates for Pulmonary Nodule Detection" was accepted by MICCAI 2018.
[May. 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.
[May. 2018]
Our paper "Interleaved Structured Sparse Convolutional Neural Networks" will appear in CVPR 2018 to present a new compact CNN model.
[Jan. 2018]
Dr. Qi is invited as an area chair for ICPR 2018.
[Jan. 2018]
Dr. Qi is serving as an Associate Editor for IEEE Transaction on Circuits and Systems for Video Technology (CSVT).
[Dec. 2017]
Dr. Qi will serve as Technical Program Co-Chair for ACM Multimedia 2020 at Seattle.
[Oct. 2017]
A paper "Interleaved Group Group Convolutions for Deep Neural Networks" has been accepted by ICCV 2017. We developed a super compact and fast deep convolutional architeture amenable to deployment on mobile devices.
[May. 2017]
Congratulations to Hao and Liheng on their ICML2017 and KDD2017 papers being accepted.
[Mar. 2017]
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 in honor of United States Senator and former presidential candidate Barry Goldwater to support highly qualified college students to pursue careers in STEM.