Institution
Microsoft
Company•Redmond, Washington, United States•
About: Microsoft is a company organization based out in Redmond, Washington, United States. It is known for research contribution in the topics: User interface & Context (language use). The organization has 49501 authors who have published 86900 publications receiving 4195429 citations. The organization is also known as: MS & MSFT.
Topics: User interface, Context (language use), Object (computer science), Computer science, Cloud computing
Papers published on a yearly basis
Papers
More filters
••
17 Jun 2006
TL;DR: It is demonstrated that this generative model for cosegmentation has the potential to improve a wide range of research: Object driven image retrieval, video tracking and segmentation, and interactive image editing.
Abstract: We introduce the term cosegmentation which denotes the task of segmenting simultaneously the common parts of an image pair. A generative model for cosegmentation is presented. Inference in the model leads to minimizing an energy with an MRF term encoding spatial coherency and a global constraint which attempts to match the appearance histograms of the common parts. This energy has not been proposed previously and its optimization is challenging and NP-hard. For this problem a novel optimization scheme which we call trust region graph cuts is presented. We demonstrate that this framework has the potential to improve a wide range of research: Object driven image retrieval, video tracking and segmentation, and interactive image editing. The power of the framework lies in its generality, the common part can be a rigid/non-rigid object (or scene), observed from different viewpoints or even similar objects of the same class.
541 citations
••
01 Jun 2018TL;DR: This paper proposes to train a semantic segmentation network starting from the discriminative regions and progressively increase the pixel-level supervision using by seeded region growing, and obtains the state-of-the-art performance.
Abstract: This paper studies the problem of learning image semantic segmentation networks only using image-level labels as supervision, which is important since it can significantly reduce human annotation efforts. Recent state-of-the-art methods on this problem first infer the sparse and discriminative regions for each object class using a deep classification network, then train semantic a segmentation network using the discriminative regions as supervision. Inspired by the traditional image segmentation methods of seeded region growing, we propose to train a semantic segmentation network starting from the discriminative regions and progressively increase the pixel-level supervision using by seeded region growing. The seeded region growing module is integrated in a deep segmentation network and can benefit from deep features. Different from conventional deep networks which have fixed/static labels, the proposed weakly-supervised network generates new labels using the contextual information within an image. The proposed method significantly outperforms the weakly-supervised semantic segmentation methods using static labels, and obtains the state-of-the-art performance, which are 63.2% mIoU score on the PASCAL VOC 2012 test set and 26.0% mIoU score on the COCO dataset.
539 citations
••
TL;DR: Four key problems: membership maintenance, network awareness, buffer management,buffer management, and message filtering are described and some preliminary approaches to address them are suggested.
Abstract: Easy to deploy, robust, and highly resilient to failures, epidemic algorithms are a potentially effective mechanism for propagating information in large peer-to-peer systems deployed on Internet or ad hoc networks. It is possible to adjust the parameters of epidemic algorithm to achieve high reliability despite process crashes and disconnections, packet losses, and a dynamic network topology. Although researchers have used epidemic algorithms in applications such as failure detection, data aggregation, resource discovery and monitoring, and database replication, their general applicability to practical, Internet-wide systems remains open to question. We describe four key problems: membership maintenance, network awareness, buffer management, and message filtering, and suggest some preliminary approaches to address them.
539 citations
••
28 Sep 2004
TL;DR: This work presents the BioAmbients calculus, which is suitable for representing various aspects of molecular localization and compartmentalization, including the movement of molecules between compartments, the dynamic rearrangement of cellularcompartments, and the interaction between molecules in a compartmentalized setting.
Abstract: Biomolecular systems, composed of networks of proteins, underlie the major functions of living cells. Compartments are key to the organization of such systems. We have previously developed an abstraction for biomolecular systems using the π-calculus process algebra, which successfully handled their molecular and biochemical aspects, but provided only a limited solution for representing compartments. In this work, we extend this abstraction to handle compartments. We are motivated by the ambient calculus, a process algebra for the specification of process location and movement through computational domains. We present the BioAmbients calculus, which is suitable for representing various aspects of molecular localization and compartmentalization, including the movement of molecules between compartments, the dynamic rearrangement of cellular compartments, and the interaction between molecules in a compartmentalized setting. Guided by the calculus, we adapt the BioSpi simulation system, to provide an extended modular framework for molecular and cellular compartmentalization, and we use it to model and study a complex multi-cellular system.
539 citations
••
23 Apr 2018TL;DR: A Deep Q-Learning based recommendation framework, which can model future reward explicitly, is proposed, which considers user return pattern as a supplement to click / no click label in order to capture more user feedback information.
Abstract: In this paper, we propose a novel Deep Reinforcement Learning framework for news recommendation. Online personalized news recommendation is a highly challenging problem due to the dynamic nature of news features and user preferences. Although some online recommendation models have been proposed to address the dynamic nature of news recommendation, these methods have three major issues. First, they only try to model current reward (e.g., Click Through Rate). Second, very few studies consider to use user feedback other than click / no click labels (e.g., how frequent user returns) to help improve recommendation. Third, these methods tend to keep recommending similar news to users, which may cause users to get bored. Therefore, to address the aforementioned challenges, we propose a Deep Q-Learning based recommendation framework, which can model future reward explicitly. We further consider user return pattern as a supplement to click / no click label in order to capture more user feedback information. In addition, an effective exploration strategy is incorporated to find new attractive news for users. Extensive experiments are conducted on the offline dataset and online production environment of a commercial news recommendation application and have shown the superior performance of our methods.
539 citations
Authors
Showing all 49603 results
Name | H-index | Papers | Citations |
---|---|---|---|
P. Chang | 170 | 2154 | 151783 |
Andrew Zisserman | 167 | 808 | 261717 |
Alexander S. Szalay | 166 | 936 | 145745 |
Darien Wood | 160 | 2174 | 136596 |
Xiang Zhang | 154 | 1733 | 117576 |
Vivek Sharma | 150 | 3030 | 136228 |
Rajesh Kumar | 149 | 4439 | 140830 |
Bernhard Schölkopf | 148 | 1092 | 149492 |
Thomas S. Huang | 146 | 1299 | 101564 |
Christopher D. Manning | 138 | 499 | 147595 |
Nicolas Berger | 137 | 1581 | 96529 |
Georgios B. Giannakis | 137 | 1321 | 73517 |
Luc Van Gool | 133 | 1307 | 107743 |
Eric Horvitz | 133 | 914 | 66162 |
Xiaoou Tang | 132 | 553 | 94555 |