Dear Colleagues,
Come take advantage of our labeling effort to show off your algorithms
for object recognition! The goal is to advance performance of
algorithms at large scale with an eye toward image search and
auto-annotation.
This year marks the third consecutive year of the LSVRC event. We will
focus on image categorization and detection for images of 1000 object
categories. In addition to 1.2M images, we provide over 500K bounding
box annotations at your disposal for training, a significant increase
from previous ImageNet challenges.
This year we also introduce a new, standalone task for categorization of
120 dog subcategories. Come showcase your algorithms on fine-grained
recognition, an exciting frontier in recognition research!
All data will be provided from ImageNet as well as from a dataset newly
collected expressly for this challenge -- test and validation data will
come only from the newly collected set.
Results will be presented at the PASCAL VOC workshop held at ECCV 2012.
Prizes may indeed be won. Timelines and more details are available here:
http://www.image-net.org/challenges/LSVRC/2012/
Good Luck!
The ILSVRC2012 team
--
-------------------------------------
Li, Fei-Fei Ph.D.
(publish under L. Fei-Fei)
Assistant Professor
Computer Science Dept.
Stanford University
353 Serra Mall, 2A Room 246
Stanford, CA 94305-9025
Tel: (650)725-3860
Website: http://vision.stanford.edu
--------------------------------------------
_______________________________________________
uai mailing list
uai@ENGR.ORST.EDU
https://secure.engr.oregonstate.edu/mailman/listinfo/uai
