filename : Per15c.pdf entry : inproceedings conference : The IEEE International Conference on Computer Vision (ICCV), Santiago Chile. pages : year : 2015 month : December title : Fully Connected Object Proposals for Video Segmentation subtitle : author : Perazzi, Federico and Wang, Oliver and Gross, Markus and Sorkine-Hornung, Alexander booktitle : ISSN/ISBN : editor : publisher : IEEE publ.place : volume : issue : language : English keywords : abstract : We present a novel approach to video segmentation using multiple object proposals. The problem is formulated as a minimization of a novel energy function defined over a fully connected graph of object proposals. Our model combines appearance with long-range point tracks, which is key to ensure robustness with respect to fast motion and occlusions over longer video sequences. As opposed to previous approaches based on object proposals, we do not seek the best per-frame object hypotheses to perform the segmentation. Instead, we combine multiple, potentially imperfect proposals to improve overall segmentation accuracy and ensure robustness to outliers. Overall, the basic algorithm consists of three steps. First, we generate a very large number of object proposals for each video frame using existing techniques. Next, we perform an SVM-based pruning step to retain only high quality proposals with sufficiently discriminative power. Finally, we determine the fore- and background classification by solving for the maximum a posteriori of a fully connected conditional random field, defined using our novel energy function. Experimental results on a well established dataset demonstrate that our method compares favorably to several recent state-of-the-art approaches.