Class-Specific, Top-Down Segmentation

Borenstein, Eran; Ullman, Shimon

doi:10.1007/3-540-47967-8_8

Cited by 289 publications

(290 citation statements)

References 15 publications

Supporting

Mentioning

286

Contrasting

Unclassified

Order By: Relevance

“…We first study HCDT's performance on the horse dataset (Borenstein and Ullman 2002) and analyze the computational complexity of the inference. Next we apply HCDT's to determine the pose of baseball players.…”

Section: Methodsmentioning

confidence: 99%

“…We performed the experimental evaluations on two datasets: (i) the Weizmann Horse Dataset (Borenstein and Ullman 2002) and (ii) the Human Baseball dataset (Mori 2005). Some examples from these datasets are shown in Figs.…”

Section: Datasets and Implementation Detailsmentioning

confidence: 99%

“…These parse trees are used as groundtruth to evaluate the ability of the HCDT to parse the horses. There are 328 horse images in Borenstein and Ullman (2002) of which 100 images are used for testing. The remaining 228 images and their parsing groundtruth are used for training.…”

Section: Datasets and Implementation Detailsmentioning

confidence: 99%

See 2 more Smart Citations

Max Margin Learning of Hierarchical Configural Deformable Templates (HCDTs) for Efficient Object Parsing and Pose Estimation

et al. 2010

View full text Add to dashboard Cite

In this paper we formulate a hierarchical configurable deformable template (HCDT) to model articulated visual objects-such as horses and baseball players-for tasks such as parsing, segmentation, and pose estimation. HCDTs represent an object by an AND/OR graph where the OR nodes act as switches which enables the graph topology to vary adaptively. This hierarchical representation is compositional and the node variables represent positions and properties of subparts of the object. The graph and the node variables are required to obey the summarization principle which enables an efficient compositional inference algorithm to rapidly estimate the state of the HCDT. We specify the structure of the AND/OR graph of the HCDT by hand and learn the model parameters discriminatively by extending Max-Margin learning to AND/OR graphs. We illustrate the three main aspects of HCDTs-representation, inference, and learning-on the tasks of segmenting, parsing, and pose (configuration) estimation for horses and hu-

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Datasets and Implementation Detailsmentioning

confidence: 99%

See 1 more Smart Citation

Max Margin Learning of Hierarchical Configural Deformable Templates (HCDTs) for Efficient Object Parsing and Pose Estimation

et al. 2010

View full text Add to dashboard Cite

show abstract

“…It is proposed to interleave classification and segmentation processes via an expanded search landscape in the context of sample supervised segment generation. This proposition is inspired by methods that interleave classification and segmentation for thematic element identification purposes [23,[53][54][55] and methods defining expanded search landscapes in sample supervised segment generation [29,45]. The spatial/spectral aggregation of segmentation is complimented with the discriminative power of a classification process.…”

Section: Exploiting Spectral Data Contained Within Provided Referencementioning

confidence: 99%

Classifier Directed Data Hybridization for Geographic Sample Supervised Segment Generation

Fourie

Schöepfer

2014

Remote Sensing

View full text Add to dashboard Cite

Quality segment generation is a well-known challenge and research objective within Geographic Object-based Image Analysis (GEOBIA). Although methodological avenues within GEOBIA are diverse, segmentation commonly plays a central role in most approaches, influencing and being influenced by surrounding processes. A general approach using supervised quality measures, specifically user provided reference segments, suggest casting the parameters of a given segmentation algorithm as a multidimensional search problem. In such a sample supervised segment generation approach, spatial metrics observing the user provided reference segments may drive the search process. The search is commonly performed by metaheuristics. A novel sample supervised segment generation approach is presented in this work, where the spectral content of provided reference segments is queried. A one-class classification process using spectral information from inside the provided reference segments is used to generate a probability image, which in turn is employed to direct a hybridization of the original input imagery. Segmentation is performed on such a hybrid image. These processes are adjustable, interdependent and form a part of the search problem. Results are presented detailing the performances of four method variants compared to the generic sample supervised segment generation approach, under various conditions in terms of resultant segment quality, required computing time and search process characteristics. Multiple metrics, metaheuristics and segmentation algorithms are tested with this approach. Using the spectral data contained within user OPEN ACCESS Remote Sens. 2014, 6 11853 provided reference segments to tailor the output generally improves the results in the investigated problem contexts, but at the expense of additional required computing time.

show abstract

“…In contrast, object recognition based on dense local "invariant" image features have shown a lot of success recently [8,11,14,19,1,3,6,16,7] for objects with large withinclass variability in shape and appearance. In such approaches objects are modeled as a collection of parts or local features and the recognition is based on inferring object class based on similarity in parts' appearance and their spatial arrangement.…”

Section: Introductionmentioning

confidence: 99%

A Statistically Selected Part-Based Probabilistic Model for Object Recognition

Zhao

Elgammal

2006

Advances in Machine Vision, Image Processing, and Pattern Analysis

View full text Add to dashboard Cite

Abstract. In an object recognition task where an image is represented as a constellation of image patches, often many patches correspond to the cluttered background. If such patches are used for object class recognition, they will adversely affect the recognition rate. In this paper, we present a statistical method for selecting the image patches which characterize the target object class and are capable of discriminating between the positive images containing the target objects and the complementary negative images. This statistical method select those images patches from the positive images which, when used individually, have the power of discriminating between the positive and negative images in the evaluation data. Another contribution of this paper is the part-based probabilistic method for object recognition. This Bayesian approach uses a common reference frame instead of reference patch to avoid the possible occlusion problem. We also explore different feature representation using PCA an 2D PCA. The experiment demonstrates our approach has outperformed most of the other known methods on a popular benchmark data set while approaching the best known results.

show abstract

Class-Specific, Top-Down Segmentation

Cited by 289 publications

References 15 publications

Max Margin Learning of Hierarchical Configural Deformable Templates (HCDTs) for Efficient Object Parsing and Pose Estimation

Max Margin Learning of Hierarchical Configural Deformable Templates (HCDTs) for Efficient Object Parsing and Pose Estimation

Classifier Directed Data Hybridization for Geographic Sample Supervised Segment Generation

A Statistically Selected Part-Based Probabilistic Model for Object Recognition

Contact Info

Product

Resources

About