Covariance profiles: a signature representation for object sets

We consider the problem of extracting a signature representation of similar entities employing covariance descriptors. Covariance descriptors can efficiently represent objects and are robust to scale and pose changes. We posit that covariance descriptors corresponding to similar objects share a common geometrical structure which can be extracted through joint diagonalization. We term this diagonalizing matrix as the Covariance Profile (CP). CP can be used to measure the distance of a novel object to an object set through the diagonality measure. We demonstrate how CP can be employed on images as well as for videos, for applications such as face recognition and object-track clustering.

The Object Agreement Restriction

[EN]This paper deals with the so-called Person Case Constraint (Bonet, 1991), a universal constraint blocking accusative clitics and object agreement morphemes other than third person when a dative is inserted in the same clitic/agreement cluster. The aim of this paper is twofold. First, we argue that the scope of the PCC is considerably broader than assumed in previous work, and that neither its formulation in terms of person (1st/2nd vs. 3rd)-case (accusative vs. dative) restrictions nor its morphological nature are part of the right descriptive generalization.We present evidence (i) that the PCC is triggered by the presence of an animacy feature in the object’s agreement set; (ii) that it is not case dependent, also showing up in languages that lack dative case; and (iii) that it is not morphologically bound. Second, we argue that the PCC, even if it is modified accordingly, still puts together two different properties of the agreement system that should be set apart: (i) a cross linguistic sensitivity of object agreement to animacy and (ii) a similarly widespread restriction on multiple object agreement observed crosslinguistically. These properties lead us to propose a new generalization, the Object Agreement Constraint (OAC): if the verbal complex encodes object agreement, no other argument can be licensed through verbal agreement.

Estimation and inference for grasping and manipulation tasks using vision and kinesthetic sensors

This thesis presents a novel framework for state estimation in the context of robotic grasping and manipulation. The overall estimation approach is based on fusing various visual cues for manipulator tracking, namely appearance and feature-based, shape-based, and silhouette-based visual cues. Similarly, a framework is developed to fuse the above visual cues, but also kinesthetic cues such as force-torque and tactile measurements, for in-hand object pose estimation. The cues are extracted from multiple sensor modalities and are fused in a variety of Kalman filters.

A hybrid estimator is developed to estimate both a continuous state (robot and object states) and discrete states, called contact modes, which specify how each finger contacts a particular object surface. A static multiple model estimator is used to compute and maintain this mode probability. The thesis also develops an estimation framework for estimating model parameters associated with object grasping. Dual and joint state-parameter estimation is explored for parameter estimation of a grasped object's mass and center of mass. Experimental results demonstrate simultaneous object localization and center of mass estimation.

Dual-arm estimation is developed for two arm robotic manipulation tasks. Two types of filters are explored; the first is an augmented filter that contains both arms in the state vector while the second runs two filters in parallel, one for each arm. These two frameworks and their performance is compared in a dual-arm task of removing a wheel from a hub.

This thesis also presents a new method for action selection involving touch. This next best touch method selects an available action for interacting with an object that will gain the most information. The algorithm employs information theory to compute an information gain metric that is based on a probabilistic belief suitable for the task. An estimation framework is used to maintain this belief over time. Kinesthetic measurements such as contact and tactile measurements are used to update the state belief after every interactive action. Simulation and experimental results are demonstrated using next best touch for object localization, specifically a door handle on a door. The next best touch theory is extended for model parameter determination. Since many objects within a particular object category share the same rough shape, principle component analysis may be used to parametrize the object mesh models. These parameters can be estimated using the action selection technique that selects the touching action which best both localizes and estimates these parameters. Simulation results are then presented involving localizing and determining a parameter of a screwdriver.

Lastly, the next best touch theory is further extended to model classes. Instead of estimating parameters, object class determination is incorporated into the information gain metric calculation. The best touching action is selected in order to best discern between the possible model classes. Simulation results are presented to validate the theory.

Computational modeling and psychophysics in low- and mid-level vision

This thesis addresses a series of topics related to the question of how people find the foreground objects from complex scenes. With both computer vision modeling, as well as psychophysical analyses, we explore the computational principles for low- and mid-level vision.

We first explore the computational methods of generating saliency maps from images and image sequences. We propose an extremely fast algorithm called Image Signature that detects the locations in the image that attract human eye gazes. With a series of experimental validations based on human behavioral data collected from various psychophysical experiments, we conclude that the Image Signature and its spatial-temporal extension, the Phase Discrepancy, are among the most accurate algorithms for saliency detection under various conditions.

In the second part, we bridge the gap between fixation prediction and salient object segmentation with two efforts. First, we propose a new dataset that contains both fixation and object segmentation information. By simultaneously presenting the two types of human data in the same dataset, we are able to analyze their intrinsic connection, as well as understanding the drawbacks of today’s “standard” but inappropriately labeled salient object segmentation dataset. Second, we also propose an algorithm of salient object segmentation. Based on our novel discoveries on the connections of fixation data and salient object segmentation data, our model significantly outperforms all existing models on all 3 datasets with large margins.

In the third part of the thesis, we discuss topics around the human factors of boundary analysis. Closely related to salient object segmentation, boundary analysis focuses on delimiting the local contours of an object. We identify the potential pitfalls of algorithm evaluation for the problem of boundary detection. Our analysis indicates that today’s popular boundary detection datasets contain significant level of noise, which may severely influence the benchmarking results. To give further insights on the labeling process, we propose a model to characterize the principles of the human factors during the labeling process.

The analyses reported in this thesis offer new perspectives to a series of interrelating issues in low- and mid-level vision. It gives warning signs to some of today’s “standard” procedures, while proposing new directions to encourage future research.

Incidental Memory of Younger and Older Adults for Objects Encountered in a Real World Context

Effects of context on the perception of, and incidental memory for, real-world objects have predominantly been investigated in younger individuals, under conditions involving a single static viewpoint. We examined the effects of prior object context and object familiarity on both older and younger adults' incidental memory for real objects encountered while they traversed a conference room. Recognition memory for context-typical and context-atypical objects was compared with a third group of unfamiliar objects that were not readily named and that had no strongly associated context. Both older and younger adults demonstrated a typicality effect, showing significantly lower 2-alternative-forced-choice recognition of context-typical than context-atypical objects; for these objects, the recognition of older adults either significantly exceeded, or numerically surpassed, that of younger adults. Testing-awareness elevated recognition but did not interact with age or with object type. Older adults showed significantly higher recognition for context-atypical objects than for unfamiliar objects that had no prior strongly associated context. The observation of a typicality effect in both age groups is consistent with preserved semantic schemata processing in aging. The incidental recognition advantage of older over younger adults for the context-typical and context-atypical objects may reflect aging-related differences in goal-related processing, with older adults under comparatively more novel circumstances being more likely to direct their attention to the external environment, or age-related differences in top-down effortful distraction regulation, with older individuals' attention more readily captured by salient objects in the environment. Older adults' reduced recognition of unfamiliar objects compared to context-atypical objects may reflect possible age differences in contextually driven expectancy violations. The latter finding underscores the theoretical and methodological value of including a third type of objects-that are comparatively neutral with respect to their contextual associations-to help differentiate between contextual integration effects (for schema-consistent objects) and expectancy violations (for schema-inconsistent objects).

Modelling and predictive control: Enabling technologies for reconfiguration

An approach to reconfiguring control systems in the event of major failures is advocated. The approach relies on the convergence of several technologies which are currently emerging: Constrained predictive control, High-fidelity modelling of complex systems, Fault detection and identification, and Model approximation and simplification. Much work is needed, both theoretical and algorithmic, to make this approach practical, but we believe that there is enough evidence, especially from existing industrial practice, for the scheme to be considered realistic. After outlining the problem and proposed solution, the paper briefly reviews constrained predictive control and object-oriented modelling, which are the essential ingredients for practical implementation. The prospects for automatic model simplification are also reviewed briefly. The paper emphasizes some emerging trends in industrial practice, especially as regards modelling and control of complex systems. Examples from process control and flight control are used to illustrate some of the ideas.

Incremental Linear Discriminant Analysis Using Sufficient Spanning Sets and Its Applications

This paper presents an incremental learning solution for Linear Discriminant Analysis (LDA) and its applications to object recognition problems. We apply the sufficient spanning set approximation in three steps i.e. update for the total scatter matrix, between-class scatter matrix and the projected data matrix, which leads an online solution which closely agrees with the batch solution in accuracy while significantly reducing the computational complexity. The algorithm yields an efficient solution to incremental LDA even when the number of classes as well as the set size is large. The incremental LDA method has been also shown useful for semi-supervised online learning. Label propagation is done by integrating the incremental LDA into an EM framework. The method has been demonstrated in the task of merging large datasets which were collected during MPEG standardization for face image retrieval, face authentication using the BANCA dataset, and object categorisation using the Caltech101 dataset. © 2010 Springer Science+Business Media, LLC.

Live 3D shape reconstruction, recognition and registration

We present a video-based system which interactively captures the geometry of a 3D object in the form of a point cloud, then recognizes and registers known objects in this point cloud in a matter of seconds (fig. 1). In order to achieve interactive speed, we exploit both efficient inference algorithms and parallel computation, often on a GPU. The system can be broken down into two distinct phases: geometry capture, and object inference. We now discuss these in further detail. © 2011 IEEE.

Improving statistical machine translation by classifying and generalizing inflected verb forms

This paper introduces a rule-based classification of single-word and compound verbs into a statistical machine translation approach. By substituting verb forms by the lemma of their head verb, the data sparseness problem caused by highly-inflected languages can be successfully addressed. On the other hand, the information of seen verb forms can be used to generate new translations for unseen verb forms. Translation results for an English to Spanish task are reported, producing a significant performance improvement.

Phrase linguistic classification and generalization for improving statistical machine translation

In this paper a method to incorporate linguistic information regarding single-word and compound verbs is proposed, as a first step towards an SMT model based on linguistically-classified phrases. By substituting these verb structures by the base form of the head verb, we achieve a better statistical word alignment performance, and are able to better estimate the translation model and generalize to unseen verb forms during translation. Preliminary experiments for the English - Spanish language pair are performed, and future research lines are detailed. © 2005 Association for Computational Linguistics.

Paraphrastic language models and combination with neural network language models

In natural languages multiple word sequences can represent the same underlying meaning. Only modelling the observed surface word sequence can result in poor context coverage, for example, when using n-gram language models (LM). To handle this issue, paraphrastic LMs were proposed in previous research and successfully applied to a US English conversational telephone speech transcription task. In order to exploit the complementary characteristics of paraphrastic LMs and neural network LMs (NNLM), the combination between the two is investigated in this paper. To investigate paraphrastic LMs' generalization ability to other languages, experiments are conducted on a Mandarin Chinese broadcast speech transcription task. Using a paraphrastic multi-level LM modelling both word and phrase sequences, significant error rate reductions of 0.9% absolute (9% relative) and 0.5% absolute (5% relative) were obtained over the baseline n-gram and NNLM systems respectively, after a combination with word and phrase level NNLMs. © 2013 IEEE.

Viewpoint-Specific Representations in Three-Dimensional Object Recognition

We report a series of psychophysical experiments that explore different aspects of the problem of object representation and recognition in human vision. Contrary to the paradigmatic view which holds that the representations are three-dimensional and object-centered, the results consistently support the notion of view-specific representations that include at most partial depth information. In simulated experiments that involved the same stimuli shown to the human subjects, computational models built around two-dimensional multiple-view representations replicated our main psychophysical results, including patterns of generalization errors and the time course of perceptual learning.

The Practice and Understanding of the Eucharist in the United Church of Christ: A Practical Theological Study

This dissertation explores the complexity of the understanding and practice of the Eucharist in the United Church of Christ as revealed in a textual analysis of the UCC Book of Worship (1986) and a qualitative study of five representative UCC congregations. Little has been written on this topic, save for several brief articles on the history of the theology of the sacrament in the two bodies that merged to form the UCC in 1957: the Congregational Christian Churches (CC) and the Evangelical and Reformed Church (E&R). This dissertation advances the topic through a practical-theological study that brings into critical conversation contemporary eucharistic practices in five congregations and a historical theological analysis of liturgical traditions in the UCC and antecedent denominations. Through this conversation, the study articulates common themes of a UCC eucharistic theology and explores implications for ongoing theology and practice in the denomination. The introduction explicates the methodology employed in this study, guided by Don Browning's work. The first two chapters present the findings of the focus group interviews and an interpretation of those results respectively. Chapter three analyzes the eucharistic liturgies in three historic books of worship used in the E&R heritage. In chapter four, two of the antecedent resources utilized in the CC tradition are analyzed. The short-lived Hymnal of the United Church of Christ, published in 1974, includes liturgies that would find fuller expression in the 1986 Book of Worship. That hymnal is examined in chapter five. Chapter six interprets the two services of "Word and Sacrament" found in the Book of Worship. Chapter seven offers a comparative analysis of the focus group findings and the theology inherent in the Book of Worship. The final chapter offers strategic recommendations for revised theory and practice. The conclusion points toward areas for further research: it propels a critical conversation around the notion of covenant, Christ's presence in the meal, and who can receive and officiate at the Eucharist. This dissertation concludes that the UCC lives within a balance of multiple, complementary theologies and challenges the denomination to make stronger connections between the meal and mission, reconciliation, and tradition.

Color Region Grouping and Shape Recognition with Deformable Models

A new deformable shape-based method for color region segmentation is described. The method includes two stages: over-segmentation using a traditional color region segmentation algorithm, followed by deformable model-based region merging via grouping and hypothesis selection. During the second stage, region merging and object identification are executed simultaneously. A statistical shape model is used to estimate the likelihood of region groupings and model hypotheses. The prior distribution on deformation parameters is precomputed using principal component analysis over a training set of region groupings. Once trained, the system autonomously segments deformed shapes from the background, while not merging them with similarly colored adjacent objects. Furthermore, the recovered parametric shape model can be used directly in object recognition and comparison. Experiments in segmentation and image retrieval are reported.