News: machine learning
We're number one in VQA 2.0
![BananaVQA](/aiml/sites/default/files/styles/ua_landscape/public/2018-12/BananaVQA-e1498199874511.png?itok=eEieUXsc)
A team led by Damien Teney (AIML) and Peter Anderson (ACRV, ANU, and Microsoft) has just placed first in the VQA 2.0 challenge.
Number one in the world in Visual Question Answering again, for now
Entries for the latest VQA v2 challenge close on Monday morning, and we’re currently number one amongst the entries that have been submitted thus far.
[Read more about Number one in the world in Visual Question Answering again, for now]
Number one in Semantic Segmentation
![VoQ](/aiml/sites/default/files/styles/ua_landscape/public/media/images/2018-12/voc_qual_003.png?h=79cd363a&itok=18Wpx02L)
Congratulations to Zifeng Wu and Chunhua Shen on having made it to the top of the Cityscapes leaderboard again.
AIML medical imaging technology achieves 98% in FDA trials
A ten-week pivotal clinical trial at TriCore Reference Laboratories in New Mexico during July and August 2015 tested APAS against a panel of microbiologists. C
[Read more about AIML medical imaging technology achieves 98% in FDA trials]
Number two in ImageNet Scene Parsing Challenge 2016
We’ve had another great year in the ImageNet competition.
[Read more about Number two in ImageNet Scene Parsing Challenge 2016]
A new Machine Learning result in Quantum Physics
![Quantum](/aiml/sites/default/files/styles/ua_landscape/public/media/images/2018-12/quantum.png?h=04524b67&itok=d3kzsCUa)
John Bastian and Anton van den Hengel are among the authors of a new paper just published in Nature Scientific Reports.
[Read more about A new Machine Learning result in Quantum Physics]
We beat Google at ImageNet Detection
![imagenet](/aiml/sites/default/files/styles/ua_landscape/public/media/images/2018-12/imagenet.png?h=b3cd6cc2&itok=j6aMgVbh)
The ImageNet Object Detection results are out, and we did extremely well!
Great Imagenet detection results
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 deep learning end-to-end training of segmentation is best
![Segmentation](/aiml/sites/default/files/styles/ua_landscape/public/media/images/2018-12/Screen%20Shot%202018-12-14%20at%203.24.52%20pm.png?h=054fc067&itok=2xVE_4JB)
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.
[Read more about In deep learning end-to-end training of segmentation is best]
Second Scenes from Video workshop to be held in Chile
![SFV](/aiml/sites/default/files/styles/ua_landscape/public/media/images/2018-12/Screen%20Shot%202018-12-14%20at%203.21.11%20pm.png?h=ea1f2533&itok=YtttTsv9)
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.
[Read more about Second Scenes from Video workshop to be held in Chile]