Skip to main content
  • Conference proceedings
  • © 2016

Computer Vision – ECCV 2016 Workshops

Amsterdam, The Netherlands, October 8-10 and 15-16, 2016, Proceedings, Part III

Part of the book series: Lecture Notes in Computer Science (LNCS, volume 9915)

Part of the book sub series: Image Processing, Computer Vision, Pattern Recognition, and Graphics (LNIP)

Conference series link(s): ECCV: European Conference on Computer Vision

Conference proceedings info: ECCV 2016.

Buy it now

Buying options

eBook USD 84.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book USD 109.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Other ways to access

This is a preview of subscription content, log in via an institution to check for access.

Table of contents (75 papers)

  1. Front Matter

    Pages I-XXIII
  2. W04 – Brave New Ideas For Motion Representations (Continued)

    1. Front Matter

      Pages 1-2
    2. Back to Basics: Unsupervised Learning of Optical Flow via Brightness Constancy and Motion Smoothness

      • Jason J. Yu, Adam W. Harley, Konstantinos G. Derpanis
      Pages 3-10
    3. Human Action Recognition Without Human

      • Yun He, Soma Shirakabe, Yutaka Satoh, Hirokatsu Kataoka
      Pages 11-17
    4. Motion Representation with Acceleration Images

      • Hirokatsu Kataoka, Yun He, Soma Shirakabe, Yutaka Satoh
      Pages 18-24
    5. Segmentation Free Object Discovery in Video

      • Giovanni Cuffaro, Federico Becattini, Claudio Baecchi, Lorenzo Seidenari, Alberto Del Bimbo
      Pages 25-31
    6. Human Pose Estimation in Space and Time Using 3D CNN

      • Agne Grinciunaite, Amogh Gudi, Emrah Tasli, Marten den Uyl
      Pages 32-39
    7. Temporal Convolutional Networks: A Unified Approach to Action Segmentation

      • Colin Lea, René Vidal, Austin Reiter, Gregory D. Hager
      Pages 47-54
    8. Making a Case for Learning Motion Representations with Phase

      • S. L. Pintea, J. C. van Gemert
      Pages 55-64
  3. W06 – Geometry Meets Deep Learning

    1. Front Matter

      Pages 65-66
    2. gvnn: Neural Network Library for Geometric Computer Vision

      • Ankur Handa, Michael Bloesch, Viorica Pătrăucean, Simon Stent, John McCormac, Andrew Davison
      Pages 67-82
    3. On-Line Large Scale Semantic Fusion

      • Tommaso Cavallari, Luigi Di Stefano
      Pages 83-99
    4. Learning Covariant Feature Detectors

      • Karel Lenc, Andrea Vedaldi
      Pages 100-117
    5. Scene Segmentation Driven by Deep Learning and Surface Fitting

      • Ludovico Minto, Giampaolo Pagnutti, Pietro Zanuttigh
      Pages 118-132
    6. Improving Constrained Bundle Adjustment Through Semantic Scene Labeling

      • Achkan Salehi, Vincent Gay-Bellile, Steve Bourgeois, Frédéric Chausse
      Pages 133-142
    7. A CNN Cascade for Landmark Guided Semantic Part Segmentation

      • Aaron S. Jackson, Michel Valstar, Georgios Tzimiropoulos
      Pages 143-155
    8. Overcoming Occlusion with Inverse Graphics

      • Pol Moreno, Christopher K. I. Williams, Charlie Nash, Pushmeet Kohli
      Pages 170-185
    9. Deep Kinematic Pose Regression

      • Xingyi Zhou, Xiao Sun, Wei Zhang, Shuang Liang, Yichen Wei
      Pages 186-201

About this book

The three-volume set LNCS 9913, LNCS 9914, and LNCS 9915 comprises the refereed proceedings of the Workshops that took place in conjunction with the 14th European Conference on Computer Vision, ECCV 2016, held in Amsterdam, The Netherlands, in October 2016.

The three-volume set LNCS 9913, LNCS 9914, and LNCS 9915 comprises the refereed proceedings of the Workshops that took place in conjunction with the 14th European Conference on Computer Vision, ECCV 2016, held in Amsterdam, The Netherlands, in October 2016.

27 workshops from 44 workshops proposals were selected for inclusion in the proceedings. These address the following themes: Datasets and Performance Analysis in Early Vision; Visual Analysis of Sketches; Biological and Artificial Vision; Brave New Ideas for Motion Representations; Joint ImageNet and MS COCO Visual Recognition Challenge; Geometry Meets Deep Learning; Action and Anticipation for Visual Learning; Computer Vision for Road Scene Understanding and Autonomous Driving; Challenge on Automatic Personality Analysis; BioImage Computing; Benchmarking Multi-Target Tracking: MOTChallenge; Assistive Computer Vision and Robotics; Transferring and Adapting Source Knowledge in Computer Vision; Recovering 6D Object Pose; Robust Reading; 3D Face Alignment in the Wild and Challenge; Egocentric Perception, Interaction and Computing; Local Features: State of the Art, Open Problems and Performance Evaluation; Crowd Understanding; Video Segmentation; The Visual Object Tracking Challenge Workshop; Web-scale Vision and Social Media; Computer Vision for Audio-visual Media; Computer VISion for ART Analysis; Virtual/Augmented Reality for Visual Artificial Intelligence; Joint Workshop on Storytelling with Images and Videos and Large Scale Movie Description and Understanding Challenge.

Editors and Affiliations

  • Microsoft Research Asia, Beijing, China

    Gang Hua

  • Facebook AI Research (FAIR), Menlo Park, USA

    Hervé Jégou

Bibliographic Information

Buy it now

Buying options

eBook USD 84.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book USD 109.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Other ways to access