A method of object detection based on combination of local and spatial information is proposed. Firstly, the categorygiven representative images are chosen through clustering to be templates, and the local and spatial...A method of object detection based on combination of local and spatial information is proposed. Firstly, the categorygiven representative images are chosen through clustering to be templates, and the local and spatial information of template are ex- tracted and generalized as the template feature. At the same time, the codebook dictionary of local contour is also built up. Secondly, based on the codebook dictionary, sliding-window mechanism and the vote algorithm are used to select initial candidate object win- dows. Lastly, the final object windows are got from initial candidate windows based on local and spatial structure feature matching. Experimental results demonstrate that the proposed approach is able to consistently identify and accurately detect the objects with better performance than the existing methods.展开更多
This study aims to illustrate the Japanese electricity supply system after the earthquake with consideration of Japanese uniqueness including its 10 separate grids with weak connections between them and the geographic...This study aims to illustrate the Japanese electricity supply system after the earthquake with consideration of Japanese uniqueness including its 10 separate grids with weak connections between them and the geographical gap between renewable potential and electricity consumptions using GIS data for a TIMES model. We take FIT （feed-in-tariff） as a policy measure to promote renewables. To consider policies to promote renewables, we need a modelling approach where the electricity system of the entire country is represented with extremely disaggregated information on existing stock and future potentials of renewables. By building up technology models based on detailed disaggregate information on existing stocks and future potentials of renewables at the sub-regional level, we can develop renewables-related policies which reflect more realistic conditions. According to the simulation results, high FIT prices do not guarantee more introductions of renewables. High FIT prices make the huge potential of renewables commercially viable, but at the same time, they limit the maximum introduction of renewables. In addition, a high FIT budget does not guarantee more renewable introduction.展开更多
Despite significant developments in 3D multi-view multi-person (3D MM) tracking, current frameworks separately target footprint tracking, or pose tracking. Frameworks designed for the former cannot be used for the lat...Despite significant developments in 3D multi-view multi-person (3D MM) tracking, current frameworks separately target footprint tracking, or pose tracking. Frameworks designed for the former cannot be used for the latter, because they directly obtain 3D positions on the ground plane via a homography projection, which is inapplicable to 3D poses above the ground. In contrast, frameworks designed for pose tracking generally isolate multi-view and multi-frame associations and may not be sufficiently robust for footprint tracking, which utilizes fewer key points than pose tracking, weakening multi-view association cues in a single frame. This study presents a unified multi-view multi-person tracking framework to bridge the gap between footprint tracking and pose tracking. Without additional modifications, the framework can adopt monocular 2D bounding boxes and 2D poses as its input to produce robust 3D trajectories for multiple persons. Importantly, multi-frame and multi-view information are jointly employed to improve association and triangulation. Our framework is shown to provide state-of-the-art performance on the Campus and Shelf datasets for 3D pose tracking, with comparable results on the WILDTRACK and MMPTRACK datasets for 3D footprint tracking.展开更多
The rapid increase of user-generated content （UGC） is a rich source for reputation management of enti- ties, products, and services. Looking at online product re- views as a concrete example, in reviews, customers u...The rapid increase of user-generated content （UGC） is a rich source for reputation management of enti- ties, products, and services. Looking at online product re- views as a concrete example, in reviews, customers usually give opinions on multiple attributes of products, therefore the challenge is to automatically extract and cluster attributes that are mentioned. In this paper, we investigate efficient at- tribute extraction models using a semi-supervised approach. Specifically, we formulate the attribute extraction issue as a sequence labeling task and design a bootstrapped schema to train the extraction models by leveraging a small quantity of labeled reviews and a larger number of unlabeled reviews. In addition, we propose a clustering By committee （CBC） ap- proach to cluster attributes according to their semantic simi- larity. Experimental results on real world datasets show that the proposed approach is effective.展开更多
基金supported by the National Natural Science Foundation of China(60972095)Shaanxi Province Education Office Research Plan(2010JK589)
文摘A method of object detection based on combination of local and spatial information is proposed. Firstly, the categorygiven representative images are chosen through clustering to be templates, and the local and spatial information of template are ex- tracted and generalized as the template feature. At the same time, the codebook dictionary of local contour is also built up. Secondly, based on the codebook dictionary, sliding-window mechanism and the vote algorithm are used to select initial candidate object win- dows. Lastly, the final object windows are got from initial candidate windows based on local and spatial structure feature matching. Experimental results demonstrate that the proposed approach is able to consistently identify and accurately detect the objects with better performance than the existing methods.
文摘This study aims to illustrate the Japanese electricity supply system after the earthquake with consideration of Japanese uniqueness including its 10 separate grids with weak connections between them and the geographical gap between renewable potential and electricity consumptions using GIS data for a TIMES model. We take FIT （feed-in-tariff） as a policy measure to promote renewables. To consider policies to promote renewables, we need a modelling approach where the electricity system of the entire country is represented with extremely disaggregated information on existing stock and future potentials of renewables. By building up technology models based on detailed disaggregate information on existing stocks and future potentials of renewables at the sub-regional level, we can develop renewables-related policies which reflect more realistic conditions. According to the simulation results, high FIT prices do not guarantee more introductions of renewables. High FIT prices make the huge potential of renewables commercially viable, but at the same time, they limit the maximum introduction of renewables. In addition, a high FIT budget does not guarantee more renewable introduction.
文摘Despite significant developments in 3D multi-view multi-person (3D MM) tracking, current frameworks separately target footprint tracking, or pose tracking. Frameworks designed for the former cannot be used for the latter, because they directly obtain 3D positions on the ground plane via a homography projection, which is inapplicable to 3D poses above the ground. In contrast, frameworks designed for pose tracking generally isolate multi-view and multi-frame associations and may not be sufficiently robust for footprint tracking, which utilizes fewer key points than pose tracking, weakening multi-view association cues in a single frame. This study presents a unified multi-view multi-person tracking framework to bridge the gap between footprint tracking and pose tracking. Without additional modifications, the framework can adopt monocular 2D bounding boxes and 2D poses as its input to produce robust 3D trajectories for multiple persons. Importantly, multi-frame and multi-view information are jointly employed to improve association and triangulation. Our framework is shown to provide state-of-the-art performance on the Campus and Shelf datasets for 3D pose tracking, with comparable results on the WILDTRACK and MMPTRACK datasets for 3D footprint tracking.
文摘The rapid increase of user-generated content （UGC） is a rich source for reputation management of enti- ties, products, and services. Looking at online product re- views as a concrete example, in reviews, customers usually give opinions on multiple attributes of products, therefore the challenge is to automatically extract and cluster attributes that are mentioned. In this paper, we investigate efficient at- tribute extraction models using a semi-supervised approach. Specifically, we formulate the attribute extraction issue as a sequence labeling task and design a bootstrapped schema to train the extraction models by leveraging a small quantity of labeled reviews and a larger number of unlabeled reviews. In addition, we propose a clustering By committee （CBC） ap- proach to cluster attributes according to their semantic simi- larity. Experimental results on real world datasets show that the proposed approach is effective.
