Human activity anticipation is a pillar of new interactive multimedia technologies. It enables better human-computer interaction and creative sensory experience in all types of virtual reality-based multimedia applications. Human behaviors are hierarchically constituted in terms of low-level and high-level activities. Fine-grained activities play a substantial role in the early recognition of simple and complex human movements in real-time with low latency, allowing longer predictions in the future. In this paper, a new objective function is proposed to anticipate fine-grained human activities using IMU data, which still suffers from an imbalance problem. Four customized objective surrogate functions are applied in unidirectional and bidirectional recurrent neural networks and compared to efficiently optimize the model considering the loss of individual classes. The experiments on five datasets across proposed loss functions show that the proposed model significantly outperforms the counterpart methods and advances the state-of-the-art. The proposed model shows accuracy scores of up to 98% and 96% for high-level and low-level activities, respectively.Note to Practitioners—There are a large number of methods that can be used for the recognition of human activity in assisted living, smart home technologies, and pervasive healthcare applications. However, studies on these methods tend to focus on recognition rather than anticipation of human activity. Furthermore, they use either vision-based or egocentric video data, which can make it challenging to collect and evaluate in virtual reality-based scenarios. To enable more natural interaction with physical and virtual reality environments, virtual reality-based technologies require built-in algorithms capable of consistently identifying complex and varied human movements. Fine-grained activities are paramount in predicting activities at an early stage to adequately characterize human behaviors. In this paper, a study is conducted to anticipate fine-grained human activity based on IMU (Inertial Measurement Unit) data, which are still subject to the negative effects of an imbalanced sample distribution. The proposed model is evaluated on different benchmarks and compared with baseline methods. The results show that the proposed model outperforms all baselines. These results have important implications for human activity prediction problems.

Creativity is often highlighted as one of the most relevant competencies or skills of the 21st century. Teaching about theoretical underpinnings of creativity has therefore become relevant in numerous fields, from computer science to business management. If we consider creativity as a literacy, like writing or programming, it is important that people from different backgrounds can learn about the basic creativity concepts and how these might be manifested in practice. This article presents the design rationale of The Creativity Game, a simple online game intended to teach the player about some of the very basic properties or concepts in creativity theory: exploration, value, novelty, constraints, and transformation. The Creativity Game is a prototype presented here to spark conversation about how we teach creativity theory in a tangible way.

Artificial intelligence and machine learning work very well for solving problems in domains where the optimal solution can be characterized precisely or in terms of adequate training data. However, when humans perform problem solving, they do not necessarily know how to characterize an optimal solution. We propose a framework for human-AI collaboration that gives humans ultimate control of the results of a problem solving task while playing to the strengths of the AI by persisting an agent's search trees and allowing humans to explore and search this search tree. This allows the use of AI in exploratory problem solving contexts. We demonstrate this framework applied to algebraic problem solving, and show that it enables a unique mode of interaction with symbolic computer algebra through the automatic completion and correction of traditional derivations, both in digital ink and textual keyboard input.

We describe the design and a trial run of an integrated course of instruction in reading, writing, and computer programming, in order to assess potential synergies of learning them together. Twelve pre-teen students diagnosed with dyslexia each took a sequence of lessons of approximately 90 minutes each over a 3-month period. In addition to computer learning activities in handwriting, word reading, word spelling, sentence and text reading comprehension, there were coding activities using “Kokopelli's World,” a blocks-style visual language with its own microworld. The results suggest that the potential synergies from this form of integrated instruction in written language and computer programming include increased student motivation, complementary pedagogical affordances and increased awareness of the relationship between written language and technology.

When the classical theory of problem solving is put into practice, a sequence of operator applications must be found that transforms an initial problem state into a goal state. This is equivalent to finding a path through the graph of possible problem states from an initial node to a goal node. The search is usually conducted by an algorithm or by a human through an iterative process of selecting and applying operators to states found so far. Here, I demonstrate examples of searching in problem spaces via interactive drawing. The demonstrations help to elucidate issues in the design of new problem-solving affordances that may enhance the abilities of human solvers to understand and solve problems. This opens up new ways to conceptualize the process of solving problems, and it suggests new ways to teach a form of computational thinking.

Many subjects such as languages, history, biology, geography, law, and medicine require the memorization of large numbers of unstructured facts and vocabulary. While there are many techniques and tools for memorizing such information, sustaining motivation remains a major barrier towards progress in these subjects. In order to help fill this gap, we brainstormed, experimented, and paper-prototyped to create Picard, a Facebook game that intertwines creative and social elements to turn rote learning into a creative, engaging experience. Picard, inspired by Pictionary, encourages players to come up with creative stories and images to help remember a particular card. Players compete and cooperate with their friends on Facebook to create the most memorable and funny mnemonics, called Picards, gaining points when they help themselves or others remember flashcards. Players use these Picards to learn and prove knowledge of the material at spaced intervals, which research has shown to be maximally effective for learning. Our game is the novel combination of an established learning methodology with player creativity and social support for learning. Picard increases player investment in the process of learning by allowing players to create and share useful visual mnemonics, while at the same time motivating and structuring their study habits through spaced-repetition quizzes.

Recently there has been a trend toward online collaborative problem-solving. However, many systems either lack enough structure for participants to know where they can contribute or are too restrictive to allow collaborative solving. In this paper, we present our research prototype, CoSolve, a website that helps users cooperatively solve problems in a novel manner: solving sessions are represented visually as state-space search trees which solvers collaboratively generate, traverse and interact with online. We describe the problem-posing and problem-solving processes in our system, and present the affordances we designed for encouraging self-reflection and collaboration in the problem-solving process. Finally, we present observations from a user study conducted with teams of solvers who used CoSolve to solve a city-building problem. Users found CoSolve easy to use and helpful in problem solving. In addition, the study provides evidence that the state-space-search organization of problem-solving activity can serve effectively as the framework for human interaction in a computer-supported collaborative problem-solving system.

We explore modeling problem solving and design using state-space-search methodology by engaging in the design of an educational game. We also explore how online communication tools (OCTs) could be used to support collaborative design using two online tools: 1) CoSolve, a collaborative problem-solving environment we developed, and 2) INFACT, a discussion forum that we built for use in education. We used these tools to design GoAtom, a chemistry game. Using our game design experience as an example, we present a method for modeling design processes using state-space-search, and reflect on our use of OCTs.

This paper explores how to incorporate the expressiveness and learning benefits of diagrams with the computing power and scalability available in online learning. As a first step toward a framework for automated assessment of student diagrams in online learning environments, we propose a new feature for the INF ACT system's Sketch Tool. This "Blobs, Links and Labels" (BLL) feature eliminates ambiguity in diagrams by imposing a flexible, graph- inspired structure to the diagrams. Specifying assessment will be done in the style of programming- by-demonstration, where the instructor uses the system to provide examples of correct or incorrect student diagrams, which are then used by the assessment tool. In designing the BLL feature, we aim to strike a balance between diagrams' expressive power versus ease of use and ease of automated assessment.

A formalism called sequential Input graphical model assessment (SIGMA) diagrams is introduced. It shares with conventional graphical models features for specifying probabilistic inferences. In addition, it provides facilities for describing temporal patterns of evidence. The formalism was motivated by a need for transparent representations of assessment processes in the INFACT online learning environment. An editor and interpreter for SIGMA diagrams have been implemented and embedded in INFACT. The interpreter works with either stored event data, real-time event processing, or a combination of both. Examples diagrams are given, and the expressive power of the formalism is discussed.

Unobtrusive educational assessment is a means of measuring student progress using the byproducts of authentic learning activities. It is difficult to perform well. Using a new technology based on graphical models, unobtrusive assessment can become more practical. We describe how we apply our techniques in teaching image processing to undergraduates. Our methods for unobtrusive assessment are applicable when learning activities are computer-based and involve the manipulation of tools such as construction kits, simulations, and programming languages.

As part of a larger solution to the problem of diagram assessment in online education, this paper explores how to allow students to "show their work" in the creation of a sketch, the same way they might show their work on, say, a math problem. We propose a Snapshot feature as an extension to our web-based Sketch Tool. This feature allows students to capture individual steps of sketch creation and then play them back. Instructors then have more information with which to assess student knowledge. Additionally, this paves the way for automated assessment-instead of a software tool having to go through every sketch and try to determine the relevant ones, it can focus on the steps students have labeled as important. Students could also use the feature as a rudimentary animation tool, or work collaboratively by adding on to other students' Snapshot sequences.

The presence of transparency in an online learning environment may potentially enhance the educational value of the system, yet there are many aspects to transparency, and the configuration of these features can prove both difficult and daunting for educators. In this paper we propose a framework for controlling transparency in an online learning environment taking into account the task, learner model and learner preferences. These characteristics was dynamically mapped onto a transparency configuration, allowing the system to adjust its presentation on-the-fly via a form of end-user programming. We describe the kinds of transparency our framework addresses, how users control transparency, and how the settings of multiple users are resolved into a single transparency configuration.

We present in this paper a general-purpose approach for articulated object recognition. We split the recognition process in two distinct phases. In the former we use standard model-based techniques in order to recognize and localize in the input image the rigid components the articulated object is composed of. In the second phase the spatial configurations formed by the recognized components are analyzed and compared with the valid configurations of the object we are searching. The comparison is based on a constraint satisfaction method which can deal with both missing components and false positives. The proposed method is based on a redundant set of constraints which represent the valid spatial configurations of the object's components. Such constraints are not embedded in the system nor are domain-specific but they are learned during a suitable training phase. We show how this approach can be used in different scenarios with different kinds of articulated objects and we present a case study concerning a robotic application.

Throughout the history of computer science education there has been debate on what should be the appropriate mathematics background for computer science majors. The first computer science instructors were mathematicians and the first curriculums were just modifications of mathematics curriculums. However, as the discipline has grown and matured there has developed several areas of computer science where traditional undergraduate mathematics is not used and traditional mathematics preparation may not be appropriate. Although logic and problem solving skills are valued by the Computer Science community, exactly how many hours of mathematics and what areas of mathematics should be required, needs to be addressed. This panel was convened to discuss this issue from a variety of viewpoints. We hope that discussion will give the listeners new ideas on just what should be the appropriate courses and topics for their institution and program. The panel was chosen to present a wide range of view representing a variety of schools (large and small, public and private, traditional and non-traditional, preparation for the workplace or for disciplines (E-commerce, distributed computing, artificial intelligence, software engineering and graphics) viewpoints (both young and old, industrial and academic).

We present a combination of techniques which can improve recall in image retrieval systems: a fast image segmentation algorithm suitable for color images which enables one to describe images in a database using multiple segmentations. A simple example shows that the use of a "rich description" satisfies a broader range of queries.

The subject matter of computer vision and pattern recognition can play a useful role in the education of mathematics for students in middle school. New standards in education call for new content relevant to students' lives, and new pedagogical methods involving construction, group work, discovery, and the use of new technology. The project "Mathematics Experiences Through Image Processing" at the University of Washington has developed software and learning activities that enable middle school and high school students to use mathematical tools and concepts to explore some exciting ideas of image processing. This paper describes these materials and discusses how the ideas of computer vision and pattern recognition can be integrated into the curriculum. Not only do we use 2D topics such as digital geometry and edge detection, but also 3D topics such as surface construction and stereogram generation.

Search of discrete spaces is important in combinatorial optimization. Such problems arise in artificial intelligence, computer vision, operations research, and other areas. For realistic problems, the search spaces to be processed are usually huge, necessitating long computation times, pruning heuristics, or massively parallel processing. We present an algorithm that reduces the computation time for graph matching by employing both branch-and-bound pruning of the search tree and massively-parallel search of the as-yet-unpruned portions of the space. Most research on parallel search has assumed that a multiple-instruction-stream/multiple-data-stream (MIMD) parallel computer is available. Since massively parallel stream (SIMD) computers are much less expensive than MIMD systems with equal numbers of processors, the question arises as to whether SIMD systems can efficiently handle state-space search problems. We demonstrate that the answer is yes, and in particular, that graph matching has a natural and efficient implementation on SIMD machines.

Image processing by computer can play an important motivational role in middle-school mathematics. The fact that digital images are represented by arrays of numbers attests to the relevance of mathematics in the exciting realm of visual imagery. The project "Mathematics Experiences Through Image Processing" has developed software and activities that offer alternative experiences in arithmetic, algebra, problem-solving, geometric transformations, and digital representation. The paper describes some of the software, learning activities, issues faced and insights gained from experiences.>

The two-dimensional mesh computer architecture has proven to be an appropriate means to apply parallel computation to problems in image processing. However, this is most often done using local-neighbourhood operations to accomplish image filtering and morphological transformations. The discovery of structures in an image such as repetitions and symmetries is another form of visual analysis, and yet relatively little has been done to apply mesh computers to this problem. In this paper, we apply the primitive operations of prefix scanning and sorting to efficiently implement a repetition finding algorithm for arrays. The computational complexity of the algorithm on a n×n mesh is O(n log k) where k is the width of the largest repeated block in the array. The algorithm was implemented on a MasPar MP-1 computer. We describe variations of the algorithm for solving several related problems including the detection of partial symmetries in an image and repetitions in images modulo pixel-value transformations.

The findings of a workshop, the goals of which were to identify applications, research problems, and designs of high performance computing and communications (HPCC) systems for supporting applications are discussed. In computer vision, the main scientific issues are machine learning, surface reconstruction, inverse optics and integration, model acquisition, and perception and action. In speech and natural language processing (SNLP), issues were identified statistical analysis in corpus-based speech and language understanding, search strategies for language analysis, auditory and vocal-tract modeling, integration of multiple levels of speech and language analyses, and connectionist systems. In AI, important issues that need immediate attention include the development of efficient machine learning and heuristic search methods that can adapt to different architectural configurations, and the design and construction of scalable and verifiable knowledge bases, active memories, and artificial neural networks.>

Some recent developments in computer memories are discussed, and proposals are made to enhance the memory systems of highly parallel SIMD (single instruction multiple data) computers. The topics covered include increases in density and speed; adding new logic functions to memory chips; local autonomy in addressing; a parallel indexed RAM (PIRAM); impact of memory on numerical computation in SIMD; routing data among processing elements (PEs); bottlenecks; iconic and symbolic processing; a mesh-interfacing memory chip; bimodal memory system; and local address autonomy using PIRAMs.>

Several types of parallelism that may be exploited in vision algorithms based on a state-space search are identified. A method called the V* algorithm, which generates the successors of a state in parallel, is presented. In machine vision, this part of the search process is very expensive, and thus V* permits substantial speedup. An experimental evaluation of V* which is based on a simulation of a character-recognition algorithm is presented. The simulation runs on a Sequent Balance 21000, using 16 out of 20 processors.>

A data structure for image processing is presented that is conceptually a pyramid of hexagonal levels, each level composed of equilateral triangles. Physically, it is implemented as a two-dimensional array. First, the mapping from conceptual to physical data structures is shown, and then several accessing algorithms for the data structure are presented. Finally, a simple edge detection process that has been implemented for a demonstration program is explained; the explanations are accompanied by edge detection results.

This paper presents the architecture of a parallel computer called a pyramid machine. The system consists of a pyramidal array of processing elements, each of which executes the instructions broadcast by a controller. Each processing element except those on the outside of the array is directly connected to thirteen neighboring elements: eight on the same level, four on the next finer level and one on the next coarser level. The architecture combines features of tree machines and features of mesh-connected parallel computers. As a result it is able to rapidly perform computations of local and global processing. The main areas of application are image processing, graphics and spatial problem solving. The motivation, basic structure, and applications of the system are discussed.

K-trees are developed as a K-dimensional analog of quad-trees and oct-trees. K-trees can be used for modeling K-dimensional data. A fast algorithm is given for finding the boundary size of a K-dimensional object represented by a K-tree. For K considered as con-stant; the algorithm provides a method for computing the perimeter of a quad-tree encoded image or the surface area of an oct-tree encoded object in worst case time proportional to the number of nodes in the tree. This improves upon the expected-case linear-time method of Samet [10] for the perimeter problem. Our method has been implemented in Pascal, and a computational example is given.

The artificial intelligence aspects of computer vision make LISP appropriate for some vision re search needs. At the University of Washington an experimental image understanding system has been implemented in MACLISP. Since MACLISP supports arrays and compiles into reasonably efficient code, it has been convenient for the project. The major subsystems are the following: preprocessing, region growing, feature computation, and control. A novel aspect of the system is its control structure which consists of a "task agenda" which is processed by procedures each based on heuristics relevant to image analysis. Processing one task may create other tasks and the system is designed to suggest alternatives during the course of analyzing an image. Tasks are ordered by their heuristically-computed "priority" values. The system has been applied to the problem of segmenting aerial photographs of an airport. Design issues and possible extensions for further work are discussed.

The transmission of high resolution raster images over low-bandwidth communication lines requires a great amount of time. User interaction in such a transmission environment can be frustrating. The problem can be eased somewhat by transmitting a series of low resolution approximations which converge to the final image. Several methods of computing such a series of images are presented. Each is related to a particular type of pyramid data structure. They rely on the ability of the local display device to overpaint an existing image, and generally require some transmission and computation overhead. However, one of the methods requires no transmission overhead and only a small amount of local computation. A notation is introduced that permits concise descriptions of the image refinement processes.

article Some Matching Problems for Bipartite Graphs Share on Authors: Steven L. Tanimoto Department of Computer Science, University of Washington, Seattle, WA and University of Connecticut, Storrs, Connecticut Department of Computer Science, University of Washington, Seattle, WA and University of Connecticut, Storrs, ConnecticutView Profile , Alon Itai Computer Science Department, Techmon-Israel Institute of Technology, Haifa, Israel Computer Science Department, Techmon-Israel Institute of Technology, Haifa, IsraelView Profile , Michael Rodeh IBM Israel Scientific Center, Haifa, Israel IBM Israel Scientific Center, Haifa, IsraelView Profile Authors Info & Claims Journal of the ACMVolume 25Issue 4Oct. 1978 pp 517–525https://doi.org/10.1145/322092.322093Online:01 October 1978Publication History 51citation1,847DownloadsMetricsTotal Citations51Total Downloads1,847Last 12 Months80Last 6 weeks7 Get Citation AlertsNew Citation Alert added!This alert has been successfully added and will be sent to:You will be notified whenever a record that you have chosen has been cited.To manage your alert preferences, click on the button below.Manage my AlertsNew Citation Alert!Please log in to your account Save to BinderSave to BinderCreate a New BinderNameCancelCreateExport CitationPublisher SiteGet Access

The description of texture is an important problem in image analysis. Several methods in the literature require that local two-dimensional discrete Fourier transforms be computed as a first step in the texture description process. A chief limitation in these approaches has been the computational complexity of the transform calculation which has tended to limit the resolution of subsequent description and/or segmentation. It is shown here that through a suitable ordering of calculations, the transforms over a complete set of overlapping "texture windows" can be obtained efficiently. An algorithm is given and is shown to be time-optimal to within a constant factor.

Efficient visible surface (hidden surface) algorithms must make use of information about the structure of the environment, constraints on viewpoint locations and the coherence between successive views in a sequence. Here the visible surface problem is posed as a problem in graph theory. A new technique based on 'updating cut-sets in a graph is presented as a means to streamline the culling of back faces during visible surface computations. The technique can be used for general environments that contain some convex polyhedra. Since the method saves the most computation when convex polyhedra having many faces appear in the environment, it is particularly appropriate for handling geodesic domes and polyhedral approximations to spheres. A direct extension for nonconvex polyhedra is suggested.