CHENG Li

Lie-X: Depth Image Based Articulated Object Pose Estimation, Tracking, and Action Recognition on Lie Groups

Published date : 12 Aug 2016

Pose estimation, tracking, and action recognition of articulated objects from depth images are important and challenging problems, which are normally considered separately. In this paper, a unied paradigm based on Lie group theory is proposed, which enables us to collectively address these related problems. Our approach is also applicable to a wide range of articulated objects. Empirically it is evaluated on lab animals including mouse and sh, as well as on human hand. On
these applications, it is shown to deliver competitive results compared to the state-of-the-arts, and non-trivial

type
Journal Paper
journal
International Journal of Computer Vision, 2016
Impact Factor
4.207

Pose Estimation from Line Correspondences: A Complete Analysis and A Series of Solutions

Published date : 20 Jun 2016

In this paper we deal with the camera pose estimation problem from a set of 2D/3D line correspondences, which is also known as PnL (Perspective-n-Line) problem. We carry out our study by comparing PnL with the well-studied PnP (Perspective-n-Point) problem, and our contributions are threefold: (1) We provide a complete 3D configuration analysis for P3L, which includes the well-known P3P problem as well as several existing analyses as special cases.

type
Journal Paper
journal
IEEE Transactions on Pattern Analysis and Machine Intelligence, Issue 99, 2016, doi: 10.1109/TPAMI.2016.2582162
Impact Factor
6.077

NeuronCyto II: An Automatic and Quantitative Solution for Crossover Neural Cells in High Throughput Screening

Published date : 27 May 2016

Microscopy is a fundamental technology driving new biological discoveries. Today microscopy allows a large number of images to be acquired using, for example, High Throughput Screening (HTS) and 4D imaging. It is essential to be able to interrogate these images and extract quantitative information in an automated fashion. In the context of neurobiology, it is important to automatically quantify the morphology of neurons in terms of neurite number, length, branching and complexity, etc.

type
Journal Paper
journal
Cytometry A, Vol. 89, Issue 8, Aug 2016, Pg 747-754 doi: 10.1002/cyto.a.22872
Impact Factor
3.066

Incremental Regularized Least Squares for Dimensionality Reduction of LargeScale Data

Published date : 23 Feb 2016

Over the past few decades, much attention has been drawn to large-scale incremental data analysis, where researchers are faced with huge amount of highdimensional data acquired incrementally. In such a case, conventional algorithms that compute the result from scratch whenever a new sample comes are highly inef-

type
Conference Paper/Poster
journal
SIAM Journal on Scientific Computing 2016
Impact Factor
1.850

Robust Modelling and Analysis of Vascular Geometries from Biomedical Images

Published date : 15 Feb 2016

In this paper, a robust computational framework is proposed for the modelling and analysis of vascular geometries from biomedical images. The approach consists of the segmentation of vascular geometries using an active contour model and the extraction of geometric features. A robust image feature is derived based on geometric interactions between the active contour model and the image object boundaries. The derived image feature uses voxel interactions across the image domain, and gives a coherent representation of the vessel shapes in the image.

type
Conference Paper/Poster
journal
Proceedings of the IASTED International Conference in Biomedical Engineering (BioMed) 2016, 832-024. February 2016

Recognizing Complex Activities by a Probabilistic Interval-based Model

Published date : 12 Feb 2016

A key challenge in complex activity recognition is the fact that a complex activity can often be performed in several different ways, with each consisting of its own configuration of atomic actions and their temporal dependencies. This leads us to define an atomic activity-based probabilistic framework that employs Allen’s interval relations to represent local temporal dependencies. The framework introduces a latent variable from the Chinese Restaurant Process to explicitly characterize these unique internal configurations of a particular complex activity as a variable number of tables.

type
Conference Paper/Poster
journal
AAAI-16, February 12-17, 2016, Phoenix Arizona, USA

A novel imaging method for quantitative Golgi localization reveals differential intra-Golgi trafficking of secretory cargoes

Published date : 13 Jan 2016

Cellular functions of the Golgi are determined by the unique distribution of its resident proteins. Currently, electron microscopy is required for the localization of a Golgi protein at the sub-Golgi level. We developed a quantitative sub-Golgi localization method based on centers of fluorescence masses of nocodazole-induced Golgi ministacks under conventional optical microscopy. Our method is rapid, convenient, and quantitative, and it yields a practical localization resolution of ∼30 nm. The method was validated by the previous electron microscopy data.

type
Journal Paper
journal
Molecular Biology Of The Cell, Vol. 27, No. 5, Mar 1 2016, pg 848-861, doi: 10.1091/mbc
Impact Factor
4.47

Learning to Boost Filamentary Structure Segmentation

Published date : 13 Dec 2015

The challenging problem of filamentary structure segmentation has a broad range of applications in biological and medical fields. A critical yet challenging issue remains on how to detect and restore the small filamentary fragments from backgrounds: The small fragments are of diverse shapes and appearances, meanwhile the backgrounds could be cluttered and ambiguous. Focusing on this issue, this paper proposes an iterative two-step learning-based approach to boost the performance based on a base segmenter arbitrarily chosen from a number of existing segmenters:

type
Conference Paper/Poster
journal
International conference on computer vision (ICCV), 13-16 Dec 2015

author

Robust Multivariate Regression with Grossly Corrupted Observations and Its Application to Personality Prediction

Published date : 21 Nov 2015

We consider the multiple-response regression problem, where the response is subject to sparse gross errors, in the high-dimensional setup. We propose a tractable regularized M-estimator that is robust to such error, where the sum of two individual regularization terms are used: the first one encourages row-sparse regression parameters, and the second one encourages a sparse error term. We obtain non-asymptotical estimation error bounds of the proposed method. To the best of our knowledge, this is the first analysis of the robust multi-task regression problem with gross errors.

type
Conference Paper/Poster
journal
Journal of Machine Learning Research (Workshop and Conference Proceedings) 30:1-15, 2015

A Graph-theoretical Approach for Tracing Filamentary Structures in Neuronal and Retinal Images

Published date : 24 Aug 2015

The aim of this study is about tracing filamentary structures in both neuronal and retinal images. It is often crucial to identify single neurons in neuronal networks, or separate vessel tree structures in retinal blood vessel networks, in applications such as drug screening for neurological disorders or computeraided diagnosis of diabetic retinopathy. Both tasks are challenging as the same bottleneck issue of filament crossovers is commonly encountered, which essentially hinders the ability of existing systems to conduct large-scale drug screening or practical clinical usage.

type
Journal Paper
journal
IEEE Transactions on Medical Imaging, DOI 10.1109/TMI.2015.2465962, vol.35, pp.1-17, 2015
Impact Factor
3.39