British Machine Vision Conference (BMVC 2018)

The British Machine Vision Conference 2018 (BMVC 2018) was the 29th British Machine Vision Association (BMVA) annual conference on machine vision, image processing, and pattern recognition. The conference was held in the Northumbria University in Newcastle UK from September 3rd to 6th 2018. Out of 862 paper submissions, 255 papers were accepted (acceptance rate of 29.5%). ¹

📝 Topics

• Statistics and machine learning for vision
• Stereo, calibration, geometric modelling and processing
• Face and gesture recognition
• Early and biologically inspired vision
• Motion, flow and tracking
• Segmentation and grouping
• Model-based vision
• Image processing techniques and methods
• Texture, shape and colour
• Video analysis
• Document processing and recognition
• Vision for quality assurance, medical diagnosis, etc.
• Vision for visualization, interaction, and graphics
• Object detection and recognition
• Shape-from-X
• Video analysis for action and event recognition
• Illumination and reflectance
• Deep learning for vision
• 3D computer vision
• RGBD analysis

🗣 Keynote Speakers

• Rama Chellappa, Learning Along the Edge of Deep Networks
• Sven Dickinson, The Role of Symmetry in Human and Computer Vision
• Shaogang Gong, People Search In Large Scale Videos

🗣 Tutorials

• Vittorio Ferrari, Knowledge transfer and human-machine collaboration for training visual models
• Ivan Laptev, Towards action understanding with less supervision
• Abhinav Gupta, Supersizing and Empowering Visual Learning
• Zeynep Akata, Explaining and Representing Novel Concepts With Minimal Supervision

🗣 Workshops

• Image Analysis for Human Facial and Activity Recognition (IAHFAR2018)
• VIBE - Vision for Interaction and Behaviour undErstanding (VIBE2018)
• Computer Vision Problems in Plant Phenotyping (CVPPP2018)
• Cross-domain Sketch Analysis Using Deep Learning Methods (CDSA 2018)

🏆 Awards

• Best science paper award: Non-smooth M-estimator for Maximum Consensus Estimation by Huu Le, Anders Eriksson, Michael Milford, Thanh-Toan Do, Tat-Jun Chin, David Suter
• Best science paper honourable mention award: Deep Network for Simultaneous Stereo Matching and Dehazing by Taeyong Song, Youngjung Kim, Changjae Oh, Kwanghoon Sohn
• Best industry paper award: Automatic Semantic Content Removal by Learning to Neglect by Siyang Qin, Jiahui Wei, Roberto Manduchi
• Best industry paper honourable mention award: Semantic Priors for Intrinsic Image Decomposition by Saurabh Saini, P. J. Narayanan
• Best student paper award: A Quaternion-based Recurrent Model for Human Motion by Dario Pavllo, David Grangier, Michael Auli
• Best student paper honourable mention: Learning on the Edge: Explicit Boundary Handling in CNNs by Carlo Innamorati, Tobias Ritschel, Tim Weyrich, Niloy Mitra