A fundamental question in visual neuroscience is how to represent image structure. The most common representational schemes rely on differential operators that compare adjacent image regions. While well-suited to encoding local relationships, such operators have significant drawbacks. Specifically, each filter’s span is confounded with the size of its sub-fields, making it difficult to compare small regions across large distances. We find that such long-distance comparisons are more tolerant to common image transformations than purely local ones, suggesting they may provide a useful vocabulary for image encoding. .We introduce the “Dissociated Dipole,” or “Sticks” operator, for encoding non-local image relationships. This operator de-couples filter span from sub-field size, enabling parametric movement between edge and region-based representation modes. We report on the perceptual plausibility of the operator, and the computational advantages of non-local encoding. Our results suggest that non-local encoding may be an effective scheme for representing image structure.

We introduce and explore an approach to estimating statisticalsignificance of classification accuracy, which is particularly usefulin scientific applications of machine learning where highdimensionality of the data and the small number of training examplesrender most standard convergence bounds too loose to yield ameaningful guarantee of the generalization ability of theclassifier. Instead, we estimate statistical significance of theobserved classification accuracy, or the likelihood of observing suchaccuracy by chance due to spurious correlations of thehigh-dimensional data patterns with the class labels in the giventraining set. We adopt permutation testing, a non-parametric techniquepreviously developed in classical statistics for hypothesis testing inthe generative setting (i.e., comparing two probabilitydistributions). We demonstrate the method on real examples fromneuroimaging studies and DNA microarray analysis and suggest atheoretical analysis of the procedure that relates the asymptoticbehavior of the test to the existing convergence bounds.

Alternative pre-messenger RNA splicing affects a majority of human genes and plays important roles in development and disease. Alternative splicing (AS) events conserved since the divergence of human and mouse are likely of primary biological importance, but relatively few such events are known. Here we describe sequence features that distinguish exons subject to evolutionarily conserved AS, which we call 'alternative-conserved exons' (ACEs) from other orthologous human/mouse exons, and integrate these features into an exon classification algorithm, ACEScan. Genome-wide analysis of annotated orthologous human-mouse exon pairs identified ~2,000 predicted ACEs. Alternative splicing was verified in both human and mouse tissues using an RT-PCR-sequencing protocol for 21 of 30 (70%) predicted ACEs tested, supporting the validity of a majority of ACEScan predictions. By contrast, AS was observed in mouse tissues for only 2 of 15 (13%) tested exons which had EST or cDNA evidence of AS in human but were not predicted ACEs, and was never observed for eleven negative control exons in human or mouse tissues. Predicted ACEs were much more likely to preserve reading frame, and less likely to disrupt protein domains than other AS events, and were enriched in genes expressed in the brain and in genes involved in transcriptional regulation, RNA processing and development. Our results also imply that the vast majority of AS events represented in the human EST databases are not conserved in mouse, and therefore may represent aberrant, disease- or allele-specific, or highly lineage-restricted splicing events.

Discriminative learning is challenging when examples are setsof local image features, and the sets vary in cardinality and lackany sort of meaningful ordering. Kernel-based classificationmethods can learn complex decision boundaries, but a kernelsimilarity measure for unordered set inputs must somehow solve forcorrespondences -- generally a computationally expensive task thatbecomes impractical for large set sizes. We present a new fastkernel function which maps unordered feature sets tomulti-resolution histograms and computes a weighted histogramintersection in this space. This ``pyramid match" computation islinear in the number of features, and it implicitly findscorrespondences based on the finest resolution histogram cell wherea matched pair first appears. Since the kernel does not penalize thepresence of extra features, it is robust to clutter. We show thekernel function is positive-definite, making it valid for use inlearning algorithms whose optimal solutions are guaranteed only forMercer kernels. We demonstrate our algorithm on object recognitiontasks and show it to be dramatically faster than currentapproaches.

Numerous psychophysical experiments have shown an important role for attentional modulations in vision. Behaviorally, allocation of attention can improve performance in object detection and recognition tasks. At the neural level, attention increases firing rates of neurons in visual cortex whose preferredstimulus is currently attended to. However, it is not yet known how these two phenomena are linked, i.e., how the visual system could be "tuned" in a task-dependent fashion to improve task performance. To answer this question, we performed simulations with the HMAX model of object recognition in cortex [45].We modulated firing rates of model neurons in accordance with experimental results about effects of feature-based attention on single neurons and measured changes in the model's performance in a variety of object recognition tasks. It turned out that recognition performance could only be improved under very limited circumstances and that attentional influences on the process of object recognition per se tend to display a lack of specificity or raise false alarm rates. These observations lead us to postulate a new role for the observed attention-related neural response modulations.

Recovering a volumetric model of a person, car, or other objectof interest from a single snapshot would be useful for many computergraphics applications. 3D model estimation in general is hard, andcurrently requires active sensors, multiple views, or integration overtime. For a known object class, however, 3D shape can be successfullyinferred from a single snapshot. We present a method for generating a``virtual visual hull''-- an estimate of the 3D shape of an objectfrom a known class, given a single silhouette observed from an unknownviewpoint. For a given class, a large database of multi-viewsilhouette examples from calibrated, though possibly varied, camerarigs are collected. To infer a novel single view input silhouette'svirtual visual hull, we search for 3D shapes in the database which aremost consistent with the observed contour. The input is matched tocomponent single views of the multi-view training examples. A set ofviewpoint-aligned virtual views are generated from the visual hullscorresponding to these examples. The 3D shape estimate for the inputis then found by interpolating between the contours of these alignedviews. When the underlying shape is ambiguous given a single viewsilhouette, we produce multiple visual hull hypotheses; if a sequenceof input images is available, a dynamic programming approach isapplied to find the maximum likelihood path through the feasiblehypotheses over time. We show results of our algorithm on real andsynthetic images of people.

Local descriptors are increasingly used for the task of object recognition because of their perceived robustness with respect to occlusions and to global geometrical deformations. Such a descriptor--based on a set of oriented Gaussian derivative filters-- is used in our recognition system. We report here an evaluation of several techniques for orientation estimation to achieve rotation invariance of the descriptor. We also describe feature selection based on a single training image. Virtual images are generated by rotating and rescaling the image and robust features are selected. The results confirm robust performance in cluttered scenes, in the presence of partial occlusions, and when the object is embedded in different backgrounds.

We formulate and interpret several multi-modal registration methods inthe context of a unified statistical and information theoretic framework. A unified interpretation clarifies the implicit assumptionsof each method yielding a better understanding of their relativestrengths and weaknesses. Additionally, we discuss a generativestatistical model from which we derive a novel analysis tool, the"auto-information function", as a means of assessing and exploiting thecommon spatial dependencies inherent in multi-modal imagery. Weanalytically derive useful properties of the "auto-information" aswell as verify them empirically on multi-modal imagery. Among theuseful aspects of the "auto-information function" is that it canbe computed from imaging modalities independently and it allows one todecompose the search space of registration problems.

Autonomous vehicles are increasingly being used in mission-critical applications, and robust methods are needed for controlling these inherently unreliable and complex systems. This thesis advocates the use of model-based programming, which allows mission designers to program autonomous missions at the level of a coach or wing commander. To support such a system, this thesis presents the Spock generative planner. To generate plans, Spock must be able to piece together vehicle commands and team tactics that have a complex behavior represented by concurrent processes. This is in contrast to traditional planners, whose operators represent simple atomic or durative actions. Spock represents operators using the RMPL language, which describes behaviors using parallel and sequential compositions of state and activity episodes. RMPL is useful for controlling mobile autonomous missions because it allows mission designers to quickly encode expressive activity models using object-oriented design methods and an intuitive set of activity combinators. Spock also is significant in that it uniformly represents operators and plan-space processes in terms of Temporal Plan Networks, which support temporal flexibility for robust plan execution. Finally, Spock is implemented as a forward progression optimal planner that walks monotonically forward through plan processes, closing any open conditions and resolving any conflicts. This thesis describes the Spock algorithm in detail, along with example problems and test results.

This paper investigates how people return to information in a dynamic information environment. For example, a person might want to return to Web content via a link encountered earlier on a Web page, only to learn that the link has since been removed. Changes can benefit users by providing new information, but they hinder returning to previously viewed information. The observational study presented here analyzed instances, collected via a Web search, where people expressed difficulty re-finding information because of changes to the information or its environment. A number of interesting observations arose from this analysis, including that the path originally taken to get to the information target appeared important in its re-retrieval, whereas, surprisingly, the temporal aspects of when the information was seen before were not. While people expressed frustration when problems arose, an explanation of why the change had occurred was often sufficient to allay that frustration, even in the absence of a solution. The implications of these observations for systems that support re-finding in dynamic environments are discussed.