arXiv subjects

Junjie Huang

Publications and source records attributed to Junjie Huang.

114 records · Page 7Linked to original sources

arXiv2019

Symmetric graphs of valency seven and their basic normal quotient graphs

A graph $Γ$ is basic if Aut$Γ$ has no normal subgroup $N\ne1$ such that $Γ$ is a normal cover of the normal quotient graph $Γ_N$. In this paper, we completely determine the basic normal quotient graphs of all connected 7-valent symmetric graphs of order $2pq^n$ with $p < q$ odd primes, which consist of an infinite family of dihedrants of order $2p$ with $p\equiv1$(mod 7), and 6 specific graphs with order at most 310. As a consequence, it shows that, for any given positive integer n, there are only finitely many connected 2-arc-transitive 7-valent graphs of order $2pq^n$ with $7\ne p<q$ primes, partially generalizing Theorem 1 of Conder, Li and Potocnik [On the orders of arc-transitive graphs, J. Algebra 421 (2015), 167-186].

math.CO↗

arXiv2018

Action Machine: Rethinking Action Recognition in Trimmed Videos

Existing methods in video action recognition mostly do not distinguish human body from the environment and easily overfit the scenes and objects. In this work, we present a conceptually simple, general and high-performance framework for action recognition in trimmed videos, aiming at person-centric modeling. The method, called Action Machine, takes as inputs the videos cropped by person bounding boxes. It extends the Inflated 3D ConvNet (I3D) by adding a branch for human pose estimation and a 2D CNN for pose-based action recognition, being fast to train and test. Action Machine can benefit from the multi-task training of action recognition and pose estimation, the fusion of predictions from RGB images and poses. On NTU RGB-D, Action Machine achieves the state-of-the-art performance with top-1 accuracies of 97.2% and 94.3% on cross-view and cross-subject respectively. Action Machine also achieves competitive performance on another three smaller action recognition datasets: Northwestern UCLA Multiview Action3D, MSR Daily Activity3D and UTD-MHAD. Code will be made available.

cs.CV↗

arXiv2018

An Efficient Optical Flow Based Motion Detection Method for Non-stationary Scenes

Real-time motion detection in non-stationary scenes is a difficult task due to dynamic background, changing foreground appearance and limited computational resource. These challenges degrade the performance of the existing methods in practical applications. In this paper, an optical flow based framework is proposed to address this problem. By applying a novel strategy to utilize optical flow, we enable our method being free of model constructing, training or updating and can be performed efficiently. Besides, a dual judgment mechanism with adaptive intervals and adaptive thresholds is designed to heighten the system's adaptation to different situations. In experiment part, we quantitatively and qualitatively validate the effectiveness and feasibility of our method with videos in various scene conditions. The experimental results show that our method adapts itself to different situations and outperforms the state-of-the-art real-time methods, indicating the advantages of our optical flow based method.

cs.CV↗

arXiv2018

Optical Flow Based Online Moving Foreground Analysis

Obtained by moving object detection, the foreground mask result is unshaped and can not be directly used in most subsequent processes. In this paper, we focus on this problem and address it by constructing an optical flow based moving foreground analysis framework. During the processing procedure, the foreground masks are analyzed and segmented through two complementary clustering algorithms. As a result, we obtain the instance-level information like the number, location and size of moving objects. The experimental result show that our method adapts itself to the problem and performs well enough for practical applications.

cs.CV↗

arXiv2018

Optical Flow Based Real-time Moving Object Detection in Unconstrained Scenes

Real-time moving object detection in unconstrained scenes is a difficult task due to dynamic background, changing foreground appearance and limited computational resource. In this paper, an optical flow based moving object detection framework is proposed to address this problem. We utilize homography matrixes to online construct a background model in the form of optical flow. When judging out moving foregrounds from scenes, a dual-mode judge mechanism is designed to heighten the system's adaptation to challenging situations. In experiment part, two evaluation metrics are redefined for more properly reflecting the performance of methods. We quantitatively and qualitatively validate the effectiveness and feasibility of our method with videos in various scene conditions. The experimental results show that our method adapts itself to different situations and outperforms the state-of-the-art methods, indicating the advantages of optical flow based methods.

cs.CV↗

arXiv2016

The invertibility of 2X2 operator matrices

In this paper the properties of right invertible row operators, i.e., of 1X2 surjective operator matrices are studied. This investigation is based on a specific space decomposition. Using this decomposition, we characterize the invertibility of a 2X2 operator matrix. As an application, the invertibility of Hamiltonian operator matrices is investigated.

math.FA↗