Recent advances in artificial intelligence (AI), including the widespread adoption of foundational models, have triggered changes across Computing Science (CS) programs. Developments include, but are not limited to, revisions to assessment practices, updates to academic integrity policies, curriculum redesign to integrate emerging concepts, and the growing use of conversational agents to support instruction. These developments aim to address effective preparation of graduates for an evolving AI innovation landscape.

Human-computer interaction (HCI) courses can be taught in many different ways. The course at our institution is an advanced Computer Science option, and therefore is required to have a significant programming component. While the focus is on design and various modes of interaction, students are encouraged to try out various interaction devices and use them in their half-semester long final project. One of the main tenets of an HCI course is that the programmer is not the average user. However, most textbooks fail to discuss categories of users that are generally underrepresented in computing. In recent offerings of our course, we added a module that covers users with diverse abilities, genders, and races. Since we are not experts in this area, our goal was to raise students' awareness through guest lectures, to encourage them to explore further through directed readings and conversations, and to get them to practice by requiring an accessibility component in their final project. The students were very receptive and their knowledge of these topics improved significantly.

In this paper, we describe how a multidisciplinary undergraduate course in Conducting Robots becomes a venue for fostering creativity and teaching strategies for creativity enhancement. We perform a number of creativity measurements and explain our results in the context of creativity research.

In this paper, we describe an ongoing multidisciplinary undergraduate seminar that we have developed, in which student teams build non-human systems that conduct our college orchestra. Students and faculty in the course come from four disciplines: computer science, interactive multimedia, music, and mechanical engineering. This paper describes the course structure, computer science components, final projects, team dynamics, and assessments. We evaluate the results to-date and discuss ongoing revisions and expectations for the future.

This paper describes a learning-based approach to recognizing shapes in video sequences using spatial and temporal features of the shape. The spatial characteristics are encoded in the mean frame, while the temporal characteristics are extracted using the Iwasawa decomposition of the shape sequence. Training is done using logistic regression, namely the LogitBoost algorithm. The method obtains good results on outdoor surveillance datasets.

This paper describes a simple and novel algorithm for detecting foreground objects in video sequences using just two consecutive frames. The method isdivided in three layers: the perceptual layer detects regions of interest by looking for pixels whose values change significantly between the two frames. The memory layer allows for the detection of objects that may become stationary (these objects are added to the background after a period of time). The perceptual layer builds on information from the perceptual layer and from the previous iteration's memory layer to extract the actual foreground objects. Background edges are detected and removed first, followed by a level-set method that shrinks the boundary of the region of interest to the boundary of the object. The method is tested on a variety of sequences taken with different cameras in different environments, and obtains very good results.

Various local descriptors have been used successfully in a variety of tasks including object recognition. Although different descriptors have been shown to have different strengths, they haven¿t been used in combination. In this paper we show that by combining local image descriptors at the feature level, we can significantly improve object recognition performance. Our system uses keyed context patches and SIFT, two descriptors that have been shown to have a somewhat uncorrelated performance [9]. By requiring hypotheses generated by both types of descriptors to satisfy the same consistency constraints, we were able to significantly reduce the error rate on recognition and categorization tasks.

Image patches have become increasingly popular in a variety of applications, due to their resistance to clutter and partial occlusion, as well as their partial insensitivity to object pose. Recently Mikolajczyk and Schmid compared a number of local descriptors and concluded that the SIFT-based ones perform best in image matching tasks. In this paper we analyze the performance of three patch descriptors in the context of 3D object recognition: SIFT, PCA-SIFT and keyed context patches. We use a data set containing images of six objects on clean and cluttered backgrounds, taken around the whole viewing sphere, and we look at individual and fused performances. Individually, the keyed context patches perform best overall, but they are outperformed for some objects by SIFT and PCA-SIFT. Recognition is improved by fusing the rankings generated by these classifiers.

Appearance-based object recognition systems rely on training from imagery, which allows the recognition of objects without requiting a 3D geometric model. It has been little explored whether such systems can be trained from imagery that is unlabeled, and whether they can be trained from imagery that is not trivially segmentable. In this paper we present a method for minimally supervised training of a previously developed recognition system from unlabeled and unsegmented imagery. We show that the system can successfully extend an object representation extracted from one black background image to contain object features extracted from unlabeled cluttered images and can use the extended representation to improve recognition performance on a test set.

Object recognition from a single view fails when the available features are not sufficient to determine the identity of a single object, either because of similarity with another object or because of feature corruption due to clutter and occlusion. Active object recognition systems have addressed this problem successfully, but they require complicated systems with adjustable viewpoints that are not always available. In this paper we investigate the performance gain available by combining the results of a single view object recognition system applied to imagery obtained from multiple fixed cameras. In particular, we address performance in cluttered scenes with varying degrees of information about relative camera pose. We argue that a property common to many computer vision recognition systems, which we term a weak target error, is responsible for two interesting limitations of multi-view performance enhancement: the lack of significant improvement in systems whose single-view performance is weak, and the plateauing of performance improvement as additional multi-view constraints are added.

In this paper we explorer the problem of training a general, 3D abject recognition system from unlabeled imagery. In particular, we attempt to identify critical issues and stumbling blocks associated with minimizing the supervision necessary to train such a system. As class learning seems to be a relatively slow and resource intensive process even for people, we consider approaches and perform experiments that entail on the order of 10/sup 1/5 basic operations, even for relatively small databases. This is the current practical limit of the computation that can be achieved. For experiments, we use a recognition system developed previously.

Appearance-based object recognition systems are currently the most successful approach for dealing with 3D recognition of arbitrary objects in the presence of clutter and occlusion. However, no current system seems directly scalable to human performance levels in this domain. In this paper we describe a series of experiments on a previously described object recognition system that try to see which, if any design axes of such systems hold the greatest potential for improving performance. We look at the potential effect of different design modifications and we conclude that the greatest leverage lies at the level of intermediate feature construction. 1.

In this paper we consider the problem of 3D object recognition and the role that perceptual grouping processes must play. In particular, we argue that reliance on a single level of perceptual grouping is inadequate, since it is responsible for the specific weaknesses of several well-known recognition techniques. Instead, recognition must use a hierarchy of perceptual grouping processes. We describe an appearance-based system that uses four distinct levels of perceptual grouping to represent 3D objects in a form that allows not only recognition, but reasoning about 3D manipulation of a sort that has been supported in the past only by 3D geometric models. The results of the algorithms have been previously reported, and the main contribution of this paper is the development of the perceptual organization hierarchy.

We describe an appearance-based object recognition system using a keyed, multi-level contest representation reminiscent of certain aspects of cubist art. Specifically, we utilize distinctive intermediate-level features in this case automatically extracted 2-D boundary fragments, as keys, which are then verified within a local contest, and assembled within a loose global contest to evoke an overall percept. This system demonstrates good recognition of a variety of 3-D shapes, ranging from sports cars and fighter planes to snakes and lizards with full orthographic invariance. We report the results of large-scale tests, involving over 2000 separate test images, that evaluate performance with increasing number of items in the database, in the presence of clutter, background change, and occlusion, and also the results of some generic classification experiments where the system is tested on objects never previously seen or modeled. To our knowledge, the results we report are the best in the literature for full-sphere tests of general shapes with occlusion and clutter resistance.