Human parsing has been extensively studied recently (Yamaguchi et al. 2012;Xia et al. 2017) due to its wide applications in many important scenarios. Mainstream fashion parsing models (i.e., parsers) focus on parsing ...
详细信息
Human parsing has been extensively studied recently (Yamaguchi et al. 2012;Xia et al. 2017) due to its wide applications in many important scenarios. Mainstream fashion parsing models (i.e., parsers) focus on parsing the high-resolution and clean images. However, directly applying the parsers trained on benchmarks of high-quality samples to a particular application scenario in the wild, e.g., a canteen, airport or workplace, often gives non-satisfactory performance due to domain shift. In this paper, we explore a new and challenging cross-domain human parsing problem: Taking the benchmark dataset with extensive pixel-wise labeling as the source domain, how to obtain a satisfactory parser on a new target domain without requiring any additional manual labeling? To this end, we propose a novel and efficient crossdomain human parsing model to bridge the cross-domain differences in terms of visual appearance and environment conditions and fully exploit commonalities across domains. Our proposed model explicitly learns a feature compensation network, which is specialized for mitigating the cross-domain differences. A discriminative feature adversarial network is introduced to supervise the feature compensation to effectively reduces the discrepancy between feature distributions of two domains. Besides, our proposed model also introduces a structured label adversarial network to guide the parsing results of the target domain to follow the high-order relationships of the structured labels shared across domains. The proposed framework is end-to-end trainable, practical and scalable in real applications. Extensive experiments are conducted where LIP dataset is the source domain and 4 different datasets including surveillance videos, movies and runway shows without any annotations, are evaluated as target domains. The results consistently confirm data efficiency and performance advantages of the proposed method for the challenging cross-domain human parsing problem. Copyright
Multi-atlas segmentation approach is one of the most widely-used image segmentation techniques in biomedical applications. There are two major challenges in this category of methods, i.e., atlas selection and label fu...
详细信息
Dear editor,Motivated by Refs.[1–10],we devote to constructing a class of q-variable 1-resilient rotation symmetric functions（RSFs）over the finite field F;={0,1,...,p-1}in this *** this letter,let p and q be differ...
详细信息
Dear editor,Motivated by Refs.[1–10],we devote to constructing a class of q-variable 1-resilient rotation symmetric functions（RSFs）over the finite field F;={0,1,...,p-1}in this *** this letter,let p and q be different odd prime numbers.
An analytical solution is undertaken to describe the wave-induced flow field and the surge motion of a permeable platform structure with fuzzy controllers in an oceanic *** the design procedure of the controller,a par...
详细信息
An analytical solution is undertaken to describe the wave-induced flow field and the surge motion of a permeable platform structure with fuzzy controllers in an oceanic *** the design procedure of the controller,a parallel distributed compensation（PDC） scheme is utilized to construct a global fuzzy logic controller by blending all local state feedback controllers.A stability analysis is carried out for a real structure system by using Lyapunov *** corresponding boundary value problems are then incorporated into scattering and radiation *** are analytically solved,based on separation of variables,to obtain series solutions in terms of the harmonic incident wave motion and surge *** dependence of the wave-induced flow field and its resonant frequency on wave characteristics and structure properties including platform width,thickness and mass has been thus drawn with a parametric *** which mathematical models are applied for the wave-induced displacement of the surge motion.A nonlinearly inverted pendulum system is employed to demonstrate that the controller tuned by swarm intelligence method can not only stabilize the nonlinear system,but has the robustness against external disturbance.
The goal of this paper is three-fold. Firstly, we prove that the Cauchy problem for generalized KP-I equation ut+ |Dx|αθxu + θ-1xθ2yu + 1/2 θx(u2) = 0, α ≥ 4 is locally well-posed in the anisotropic Sobolev spa...
详细信息
The frequent directions (FD) technique is a deterministic approach for online sketching that has many applications in machine learning. The conventional FD is a heuristic procedure that often outputs rank deficient ma...
详细信息
This paper aims to develop a new and robust approach to feature representation. Motivated by the success of Auto-Encoders, we first theoretically analyze and summarize the general properties of all algorithms that are...
详细信息
暂无评论