no code implementations • 30 Apr 2019 • Danna Gurari, Yinan Zhao, Suyog Dutt Jain, Margrit Betke, Kristen Grauman
We propose a resource allocation framework for predicting how best to allocate a fixed budget of human annotation effort in order to collect higher quality segmentations for a given batch of images and automated methods.
no code implementations • 11 Aug 2018 • Bo Xiong, Suyog Dutt Jain, Kristen Grauman
We propose an end-to-end learning framework for segmenting generic objects in both images and videos.
no code implementations • CVPR 2017 • Suyog Dutt Jain, Bo Xiong, Kristen Grauman
Our method learns to combine appearance and motion information to produce pixel level segmentation masks for all prominent objects in videos.
no code implementations • 30 Apr 2017 • Danna Gurari, Kun He, Bo Xiong, Jianming Zhang, Mehrnoosh Sameki, Suyog Dutt Jain, Stan Sclaroff, Margrit Betke, Kristen Grauman
We propose the ambiguity problem for the foreground object segmentation task and motivate the importance of estimating and accounting for this ambiguity when designing vision systems.
no code implementations • CVPR 2017 • Suyog Dutt Jain, Bo Xiong, Kristen Grauman
Our method learns to combine appearance and motion information to produce pixel level segmentation masks for all prominent objects in videos.
no code implementations • 19 Jan 2017 • Suyog Dutt Jain, Bo Xiong, Kristen Grauman
We propose an end-to-end learning framework for generating foreground object segmentations.
no code implementations • 5 Jul 2016 • Suyog Dutt Jain, Kristen Grauman
We present a novel form of interactive video object segmentation where a few clicks by the user helps the system produce a full spatio-temporal segmentation of the object of interest.
no code implementations • CVPR 2016 • Suyog Dutt Jain, Kristen Grauman
We propose a semi-automatic method to obtain foreground object masks for a large set of related images.