%0 Generic %1 lin2014microsoft %A Lin, Tsung-Yi %A Maire, Michael %A Belongie, Serge %A Bourdev, Lubomir %A Girshick, Ross %A Hays, James %A Perona, Pietro %A Ramanan, Deva %A Zitnick, C. Lawrence %A Dollár, Piotr %D 2014 %K boundingbox dataset mask occlusionprob %T Microsoft COCO: Common Objects in Context %U http://arxiv.org/abs/1405.0312 %X We present a new dataset with the goal of advancing the state-of-the-art in object recognition by placing the question of object recognition in the context of the broader question of scene understanding. This is achieved by gathering images of complex everyday scenes containing common objects in their natural context. Objects are labeled using per-instance segmentations to aid in precise object localization. Our dataset contains photos of 91 objects types that would be easily recognizable by a 4 year old. With a total of 2.5 million labeled instances in 328k images, the creation of our dataset drew upon extensive crowd worker involvement via novel user interfaces for category detection, instance spotting and instance segmentation. We present a detailed statistical analysis of the dataset in comparison to PASCAL, ImageNet, and SUN. Finally, we provide baseline performance analysis for bounding box and segmentation detection results using a Deformable Parts Model.

@misc{lin2014microsoft, abstract = {We present a new dataset with the goal of advancing the state-of-the-art in object recognition by placing the question of object recognition in the context of the broader question of scene understanding. This is achieved by gathering images of complex everyday scenes containing common objects in their natural context. Objects are labeled using per-instance segmentations to aid in precise object localization. Our dataset contains photos of 91 objects types that would be easily recognizable by a 4 year old. With a total of 2.5 million labeled instances in 328k images, the creation of our dataset drew upon extensive crowd worker involvement via novel user interfaces for category detection, instance spotting and instance segmentation. We present a detailed statistical analysis of the dataset in comparison to PASCAL, ImageNet, and SUN. Finally, we provide baseline performance analysis for bounding box and segmentation detection results using a Deformable Parts Model.}, added-at = {2019-04-08T11:49:36.000+0200}, author = {Lin, Tsung-Yi and Maire, Michael and Belongie, Serge and Bourdev, Lubomir and Girshick, Ross and Hays, James and Perona, Pietro and Ramanan, Deva and Zitnick, C. Lawrence and Dollár, Piotr}, biburl = {https://www.bibsonomy.org/bibtex/2f4ab9f41677ee189a8cbc5a92cc0dc74/jannikd}, description = {[1405.0312] Microsoft COCO: Common Objects in Context}, interhash = {a3a26c6fe173264a6b812e3b7b4119bd}, intrahash = {f4ab9f41677ee189a8cbc5a92cc0dc74}, keywords = {boundingbox dataset mask occlusionprob}, note = {cite arxiv:1405.0312Comment: 1) updated annotation pipeline description and figures; 2) added new section describing datasets splits; 3) updated author list}, timestamp = {2019-04-10T05:04:17.000+0200}, title = {Microsoft COCO: Common Objects in Context}, url = {http://arxiv.org/abs/1405.0312}, year = 2014 }