News: challenge
Podium finish in global AI race contest
An AIML team has scored double pole positions in a global virtual motor racing event that saw hundreds of AI researchers and engineers compete to build high performance virtual race cars.
2nd place in xVIEW Challenge
A team from AIML featuring Jamie Sherrah and Phil Roberts, and DST Group’s Victor Stamatescu has beaten more than 4000 submissions from around the world to gain second place in the Defense Innovation Unit’s (DIU) xVIEW Challenge.
First place!
Results for the REFUGE Retinal Fundus Glaucoma Challenge are in! First place in the Segmentation leaderboard and also in the Segmentation of Nuclei competition.
We're number one in VQA 2.0
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
Congratulations to Zifeng Wu and Chunhua Shen on having made it to the top of the Cityscapes leaderboard again.
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]
We're in the top 5 groups the world
The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) is double blind reviewed (on full papers), and has the best citation rate in the field of computer vision and pattern recognition, according to the h5-index, a citation measure for the recent five years.
10 PAMIs and 28 CVPRs in just over a year
The AIML (formally ACVT) has had 10 journal articles published in IEEE Pattern Analysis and Machine Intelligence, and 28 papers in the IEEE Conference on Computer Vision and Pattern Recognition, in the 16 months since January 2015.
We beat Google at ImageNet Detection
The ImageNet Object Detection results are out, and we did extremely well!
