• A CleanRoom approach to bring your own apps 

    Goel, Deepak
    Today, on mobile devices such as smartphones and tablets, hundreds of thousands of software apps provide useful services to users. Users use these apps to search and browse the web, perform financial transactions, emailing, ...
  • A deep learning framework for model-free 6 degree of freedom object tracking 

    Iventosch, Joel William; 0000-0001-8188-7093 (2017-06-22)
    In this work we address the challenging task of 6 degree of freedom (DoF), model-free object tracking. We propose a new deep learning framework that explores the merit of using weakly supervised semantic segmentation as ...
  • A multi-scale framework for graph based machine learning problems 

    Shin, Donghyuk; 0000-0001-8687-0258 (2017-06-20)
    Graph data have become essential in representing and modeling relationships between entities and complex network structures in various domains such as social networks and recommender systems. As a main contributor of the ...
  • Action selection in modular reinforcement learning 

    Zhang, Ruohan (2014-08)
    Modular reinforcement learning is an approach to resolve the curse of dimensionality problem in traditional reinforcement learning. We design and implement a modular reinforcement learning algorithm, which is based on three ...
  • Active learning of an action detector on untrimmed videos 

    Bandla, Sunil (2013-05)
    Collecting and annotating videos of realistic human actions is tedious, yet critical for training action recognition systems. We propose a method to actively request the most useful video annotations among a large set of ...
  • Active visual category learning 

    Vijayanarasimhan, Sudheendra (2011-05)
    Visual recognition research develops algorithms and representations to autonomously recognize visual entities such as objects, actions, and attributes. The traditional protocol involves manually collecting training image ...
  • Activity retrieval in closed captioned videos 

    Gupta, Sonal (2009-08)
    Recognizing activities in real-world videos is a difficult problem exacerbated by background clutter, changes in camera angle & zoom, occlusion and rapid camera movements. Large corpora of labeled videos can be used to ...
  • Ad hoc : overloading and language design 

    Kilpatrick, Scott Lasater, 1984- (2010-08)
    The intricate concepts of ad-hoc polymorphism and overloading permeate the field of programming languages despite their somewhat nebulous definitions. With the perspective afforded by the state of the art, object-oriented ...
  • ADaM: Augmenting Existing Approximate Fast Matching Algorithms with Efficient and Exact Range Queries 

    Clement, Nathan L.; Thompson, Lee P.; Miranker, Daniel P. (2014-05)
    Drug discovery, disease detection, and personalized medicine are fast-growing areas of genomic research. With the advancement of next-generation sequencing techniques, researchers can obtain an abundance of data for many ...
  • Adaptive representations for reinforcement learning 

    Whiteson, Shimon Azariah (2007)
  • Adaptive representations for reinforcement learning 

    Whiteson, Shimon Azariah (2007-05)
    In reinforcement learning, an autonomous agent seeks an effective control policy for tackling a sequential decision task. Unlike in supervised learning, the agent never sees examples of correct or incorrect behavior but ...
  • Adaptive trading agent strategies using market experience 

    Pardoe, David Merrill (2011-05)
    Along with the growth of electronic commerce has come an interest in developing autonomous trading agents. Often, such agents must interact directly with other market participants, and so the behavior of these participants ...
  • Adaptive wireless body medical system 

    Zhu, Xiuming (2013-05)
    Advances in wireless technologies in the last ten years have created considerable opportunities as well as challenges for wireless body medical systems. The foremost challenge is how to build a reliable system connecting ...
  • Addressing the brittleness of knowledge-based question-answering 

    Chaw, Shaw Yi (2009-12)
    Knowledge base systems are brittle when the users of the knowledge base are unfamiliar with its content and structure. Querying a knowledge base requires users to state their questions in precise and complete formal ...
  • Aesthetic image rating (AIR) algorithm 

    Reaves, David (2008-05)
    Rapidly advancing technologies o er a greater volume of people the possi- bility to both create and consume information. And, with this widening of opportunity, the volume of digital information has increased in ...
  • Algebraic and analytic techniques in coding theory 

    Bhowmick, Abhishek (2015-12)
    Error correcting codes are designed to tackle the problem of reliable trans- mission of data through noisy channels. A major challenge in coding theory is to efficiently recover the original message even when many symbols ...
  • Algebraic attacks : a survey 

    Agrawal, Shweta Prem (2007-12)
    Algebraic attacks have recently acquired great importance in the area of cryptography, not only due to the ciphers they have been able to break, but more importantly, because the principle of algebraic attacks is very ...