1. M3RSM: Many-To-Many Multi-Resolution Scan Matching


    M3RSM: Many-to-Many Multi-Resolution Scan Matching Edwin Olson 1 Abstract We describe a new multi-resolution scan matching method that makes exhaustive (and thus local-minimum-proof)

  2. Collaborative Deep Learning for Recommender Systems - arXiv


    Collaborative Deep Learning for Recommender Systems Hao Wang Hong Kong University of Science and Technology hwangaz@cse.ust.hk Naiyan Wang Hong Kong University of

  3. Empathy and Masculinity in Harper Lee's to Kill a Mockingbird


    Harper Lee’s To Kill a Mockingbird illustrates a troubled relationship between lawyering and empathy and between empathy and masculinity. To begin, empathetic u

  4. Geometric Calibration of Micro-Lens-Based Light Field Cameras Using Line Features - IEEE Journals & Magazine - IEEE Xplore …


    Abstract: We present a novel method for the geometric calibration of micro-lens-based light field cameras. Accurate geometric calibration is the basis of various applications. Instead of using sub-aperture images…

  5. www.ncbi.nlm.nih.gov


    Moved Permanently. The document has moved here.

  6. Support Vector Regression Machines

    Harris Drucker · Christopher J C Burges · Linda Kaufman · Alexander J Smola · Vladimir Vapnik

    A new regression technique based on Vapnik's concept of support vectors is introduced. We compare support vector regression (SVR) with a committee regression technique (bagging) based on regression t…

  7. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks

    Shaoqing Ren · Kaiming He · Ross B Girshick · Jian Sun

    State-of-the-art object detection networks depend on region proposal algorithms to hypothesize object locations. Advances like SPPnet [1] and Fast R-CNN [2] have reduced the running time of these detecti…

  8. New tools for studying microglia in the mouse and human CNS


    and activated microglia following systemic inflammation. We added these data to a user-friendly website (www.BrainRNAseq. org). For human study, we identified and validated an anti-human

  9. The Number of Scholarly Documents on the Public Web

    Madian Khabsa · C Lee Giles
    2014 · PLOS ONE|被引数:183

    The number of scholarly documents available on the web is estimated using capture/recapture methods by studying the coverage of two major academic search engines: Google Scholar and Microsoft Acade…

  10. Deep Residual Learning for Image Recognition

    Kaiming He · Xiangyu Zhang · Shaoqing Ren · Jian Sun

    Deeper neural networks are more difficult to train. We present a residual learning framework to ease the training of networks that are substantially deeper than those used previously. We explicitly reformulate t…

  11. 177,000 条结果