The ImageNet Object Detection results are out, and we did extremely well!
Last week was the deadline for the ImageNet Large Scale Visual Recognition Challenge (ILSVRC 2015) large-scale object detection task. This is the primary challenge for image-based object detection. The challenge requires that you detect 200 classes of objects in a set of test images.
In another indication that the Machine Learning behind most Computer Vision Problems has more general applicability, we have just had a paper accepted which shows that the approach we developed for pedestrian detection achieves the world’s best performance in predicting protein-protein interactions.
A research team (Dr. Guosheng Lin, Prof. Chunhua Shen, Prof. Ian Reid, Prof. Anton van den Hengel) at the School of Computer Science, The University of Adelaide developed innovative “Deep Structured Learning” techniques that set up the new state-of-the-art semantic image segmentation record in the PASCAL VOC Challenge, which is organised by the University of Oxford. The Adelaide team is the top one currently, outperforming teams from Microsoft Research, Oxford, University of California, Los Angles etc.
Michael Black and Anton van den Hengel are organising the Second Scenes from Video workshop, which will be held in the Colchagua Valley, one of Chile’s pre-eminent wine regions, and will include a variety of functions and excursions exploring the region and its fare.
Prof. Wojciech Chojnacki was recently awarded the permanent state title of Professor conferred by the President of the Republic of Poland.
Researchers at AIML (formerly ACVT) have developed new “Deep Structured Learning” techniques that set up the new state-of-the-art semantic image segmentation record in the PASCAL VOC Challenge, which is organised by Oxford University. Semantic image segmentation is one of the tasks and probably the most challenging one, which is to label each pixel in images.
In conjunction with the success of the Australian Centre for Robotic Vision’s workshops at CVPR2015 in Boston: