• A CleanRoom approach to bring your own apps 

      Goel, Deepak (2013-05)
      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 (2017-05)
      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 (2017-05)
      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 ...
    • A second generation of nonrepudiation protocols 

      Ali, Muqeet (2017-09-13)
      A non-repudiation protocol from party S to party R performs two tasks. First, the protocol enables party S to send to party R some text x along with sufficient evidence (that can convince a judge) that x was indeed sent ...
    • 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 and compilation of higher order schema integration queries 

      Barbanson, François Gérard (2005)
      After nearly 30 years, database integration remains the province of engineers and application developers. In an informal proof, Krishnamurthy, Litwin and Kent [KLK91] demonstrated that only higher order relational languages ...
    • 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 ...
    • 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 ...
    • Addressing the memory bottleneck in packet processing systems 

      Mudigonda, Jayaram (2005)
      The design of packet processing systems is guided by two requirements: (1) high packet processing throughput, and (2) ease-of-programming. Meeting these two requirements simultaneously has proved to be challenging primarily ...
    • Advances in statistical script learning 

      Pichotta, Karl; 0000-0001-7062-2970 (2017-08-08)
      When humans encode information into natural language, they do so with the clear assumption that the reader will be able to seamlessly make inferences based on world knowledge. For example, given the sentence ``Mrs. Dalloway ...
    • 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 ...