TY - CONF AB - We study the task of interactive semantic labeling of a segmentation hierarchy. To this end we propose a framework interleaving two components: an automatic labeling step, based on a Conditional Random Field whose dependencies are defined by the inclusion tree of the segmentation hierarchy, and an interaction step that integrates incremental input from a human user. Evaluated on two distinct datasets, the proposed interactive approach efficiently integrates human interventions and illustrates the advantages of structured prediction in an interactive framework. AU - Zankl, Georg AU - Haxhimusa, Yll AU - Ion, Adrian ID - 2971 TI - Interactive labeling of image segmentation hierarchies VL - 7476 ER - TY - CONF AB - We propose a mid-level statistical model for image segmentation that composes multiple figure-ground hypotheses (FG) obtained by applying constraints at different locations and scales, into larger interpretations (tilings) of the entire image. Inference is cast as optimization over sets of maximal cliques sampled from a graph connecting all non-overlapping figure-ground segment hypotheses. Potential functions over cliques combine unary, Gestalt-based figure qualities, and pairwise compatibilities among spatially neighboring segments, constrained by T-junctions and the boundary interface statistics of real scenes. Learning the model parameters is based on maximum likelihood, alternating between sampling image tilings and optimizing their potential function parameters. State of the art results are reported on the Berkeley and Stanford segmentation datasets, as well as VOC2009, where a 28% improvement was achieved. AU - Ion, Adrian AU - Carreira, Joao AU - Sminchisescu, Cristian ID - 3265 TI - Image segmentation by figure-ground composition into maximal cliques ER - TY - CONF AB - We present a joint image segmentation and labeling model (JSL) which, given a bag of figure-ground segment hypotheses extracted at multiple image locations and scales, constructs a joint probability distribution over both the compatible image interpretations (tilings or image segmentations) composed from those segments, and over their labeling into categories. The process of drawing samples from the joint distribution can be interpreted as first sampling tilings, modeled as maximal cliques, from a graph connecting spatially non-overlapping segments in the bag [1], followed by sampling labels for those segments, conditioned on the choice of a particular tiling. We learn the segmentation and labeling parameters jointly, based on Maximum Likelihood with a novel Incremental Saddle Point estimation procedure. The partition function over tilings and labelings is increasingly more accurately approximated by including incorrect configurations that a not-yet-competent model rates probable during learning. We show that the proposed methodologymatches the current state of the art in the Stanford dataset [2], as well as in VOC2010, where 41.7% accuracy on the test set is achieved. AU - Ion, Adrian AU - Carreira, Joao AU - Sminchisescu, Cristian ID - 3266 T2 - NIPS Proceedings TI - Probabilistic joint image segmentation and labeling VL - 24 ER - TY - CONF AB - In this paper, we establish a correspondence between the incremental algorithm for computing AT-models [8,9] and the one for computing persistent homology [6,14,15]. We also present a decremental algorithm for computing AT-models that allows to extend the persistence computation to a wider setting. Finally, we show how to combine incremental and decremental techniques for persistent homology computation. AU - Gonzalez-Diaz, Rocio AU - Ion, Adrian AU - Jimenez, Maria Jose AU - Poyatos, Regina ID - 9648 SN - 03029743 T2 - Computer Analysis of Images and Patterns TI - Incremental-decremental algorithm for computing AT-models and persistent homology VL - 6854 ER - TY - CONF AB - This paper presents a method to create a model of an articulated object using the planar motion in an initialization video. The model consists of rigid parts connected by points of articulation. The rigid parts are described by the positions of salient feature-points tracked throughout the video. Following a filtering step that identifies points that belong to different objects, rigid parts are found by a grouping process in a graph pyramid. Valid articulation points are selected by verifying multiple hypotheses for each pair of parts. AU - Artner, Nicole M. AU - Ion, Adrian AU - Kropatsch, Walter G. ED - Jiang, Xiaoyi ED - Ferrer, Miquel ED - Torsello, Andrea ID - 10907 SN - 0302-9743 T2 - Graph-Based Representations in Pattern Recognition TI - Spatio-temporal extraction of articulated models in a graph pyramid VL - 6658 ER -