A bag-of-objects retrieval model for web image search
Proceedings of the 20th ACM international conference on Multimedia
Submodular video hashing: a unified framework towards video pooling and indexing
Proceedings of the 20th ACM international conference on Multimedia
Segmentation propagation in imagenet
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part VII
Hi-index | 0.00 |
The saliency of regions or objects in an image can be significantly boosted if they recur in multiple images. Leveraging this idea, cosegmentation jointly segments common regions from multiple images. In this paper, we propose CoSand, a distributed cosegmentation approach for a highly variable large-scale image collection. The segmentation task is modeled by temperature maximization on anisotropic heat diffusion, of which the temperature maximization with finite K heat sources corresponds to a K-way segmentation that maximizes the segmentation confidence of every pixel in an image. We show that our method takes advantage of a strong theoretic property in that the temperature under linear anisotropic diffusion is a submodular function; therefore, a greedy algorithm guarantees at least a constant factor approximation to the optimal solution for temperature maximization. Our theoretic result is successfully applied to scalable cosegmentation as well as diversity ranking and single-image segmentation. We evaluate CoSand on MSRC and ImageNet datasets, and show its competence both in competitive performance over previous work, and in much superior scalability.