Thumbnail
Access Restriction
Open

Author Zhu, Fan ♦ Jiang, Zhuolin ♦ Shao, Ling
Source CiteSeerX
Content type Text
File Format PDF
Subject Domain (in DDC) Computer science, information & general works ♦ Data processing & computer science
Subject Keyword Submodular Object Recognition ♦ Selected Segment ♦ Impressive Recognition Result ♦ Object Recognition ♦ Multiple Figure-ground Hypothesis ♦ Object Category ♦ Unsupervised Manner ♦ Large Object Spatial Support ♦ Tar-get Category ♦ Differ-ent Category-specific Regressors ♦ Segment Category ♦ Facility Location ♦ Pascal Voc ♦ Mid-level Cue ♦ Group Element ♦ Benchmark Datasets ♦ Figure-ground Segment Hypothesis ♦ Novel Object Recognition Framework ♦ Submodular Objective Function ♦ Bottom-up Process ♦ Maximum Regression Value
Abstract We present a novel object recognition framework based on multiple figure-ground hypotheses with a large object spatial support, generated by bottom-up processes and mid-level cues in an unsupervised manner. We exploit the ben-efit of regression for discriminating segments ’ categories and qualities, where a regressor is trained to each category using the overlapping observations between each figure-ground segment hypothesis and the ground-truth of the tar-get category in an image. Object recognition is achieved by maximizing a submodular objective function, which maxi-mizes the similarities between the selected segments (i.e., facility locations) and their group elements (i.e., clients), penalizes the number of selected segments, and more im-portantly, encourages the consistency of object categories corresponding to maximum regression values from differ-ent category-specific regressors for the selected segments. The proposed framework achieves impressive recognition results on three benchmark datasets, including PASCAL VOC 2007, Caltech-101 and ETHZ-shape. 1.
Educational Role Student ♦ Teacher
Age Range above 22 year
Educational Use Research
Education Level UG and PG ♦ Career/Technical Study