Abstract: Image descriptor quantization technique embodiments are presented which quantize an image descriptor defined by a vector of number elements. This is generally accomplished by lowering the number of bits per number element to a prescribed degree. The resulting quantized image descriptor exhibits minimal loss of matching reliability while at the same time reducing the amount of storage space needed to store the descriptor in a database. Lowering the number of bits per number element also allows for increased matching speed.

Abstract: The system provides a tristable environment that effects reorientation of horizontal and vertical surfaces at a human scale. The system allows the engagement and disengagement of the effect via movement of the observer without loss of the intensity of the effect. The system also provides a combined vection/motion induced blindness environment at human scale with interactivity available to non-trained participants.

Abstract: Mobile device assisted secure computer network communications embodiments are presented that employ a mobile device (e.g., a mobile phone, personal digital assistant (PDA), and the like) to assist in user authentication. In general, this is accomplished by having a user enter a password into a client computer which is in contact with a server associated with a secure Web site. This password is integrated with a secret value, which is generated in real time by the mobile device. The secret value is bound to both the mobile device's hardware and the secure Web site being accessed, such that it is unique to both. In this way, a different secret value is generated for each secure Web site accessed, and another user cannot impersonate the user and log into a secure Web site unless he or she knows the password and possesses the user's mobile device simultaneously.

Abstract: A media recommendation and sharing technique that employs agents on media players/devices to expand the scope of media sharing scenarios. The technique assists a user in discovering media items, such as, for example, music, recordings, play lists, pictures, video games, on nearby media players or devices (devices which are capable of receiving, storing and playing media) which are interesting to the user. The collaborative media recommendation and sharing technique contemporaneously determines a user's media preferences based on media stored on a pair of media devices and recommends media for potential sharing based on these determined user preferences.

Abstract: Multi-spline image blending technique embodiments are presented which generally employ a separate low-resolution offset field for every image region being blended, rather than a single (piecewise smooth) offset field for all the regions to produce a visually consistent blended image. Each of the individual offset fields is smoothly varying, and so is represented using a low-dimensional spline. A resulting linear system can be rapidly solved because it involves many fewer variables than the number of pixels being blended.

Abstract: A flexible query hints system and method for discovering and expressing query hints in a database management system. Embodiments of the flexible query hints system and method include a power hints (Phints) language that enables the specification of constraints to influence a query optimizer. Phints expressions are defined as tree patterns annotated with constraints. Embodiments of the flexible query hints system and method also include techniques to incorporate the power hints language expressions into an extended query optimizer. Theses techniques include computing a directed acyclic graph for Phints expression, deriving candidate matches using the Phints expression and the graph, computing candidate matches, and extracting a revised execution plan having a lowest cost and satisfying constraints of the Phints expression. Embodiments of the flexible query hints system and method include a flexible query hint user interface that allow users to interactively adjust query hints.

Abstract: A simultaneous semantic and structure threaded discussion modeling system and method for generating a model of a discussion thread and using the model to mine data from the discussion thread. Embodiments of the system and method generate a model that contains both semantic terms and structure terms. The model simultaneously models both semantics and structure of the discussion thread. A model generator includes a semantic module generates two semantic terms for the model and a structure module generates two structure terms for the model. The generator combines the two semantic terms and the two structure terms to generate the simultaneous semantic and structure model. Embodiments of the system and method include an applications module, which contains three application that use the model to reconstruct reply relations among posts in the discussion thread, identify junk posts in the discussion thread, and find experts in each sub-board of web forums.

Abstract: An exact cardinality query optimization system and method for optimizing a query having a plurality of expressions to obtain a cardinality-optimal query execution plan for the query. Embodiments of the system and method use various techniques to shorten the time necessary to obtain the cardinality-optimal query execution plan, which contains the query execution plan when all cardinalities are exact. Embodiments of the system and method include a covering queries technique that leverages query execution feedback to obtain an unordered subset of relevant expressions for the query, an early termination technique that bounds the cardinality to determine whether the processing can be terminate before each of the expressions are executed, and an expressions ordering technique that finds an ordering of expressions that yields the greatest reduction in time to obtain the cardinality-optimal query execution plan.

Abstract: A “request scheduler” provides techniques for batching and scheduling buffered thread requests for access to shared memory in a general-purpose computer system. Thread-fairness is provided while preventing short- and long-term thread starvation by using “request batching.” Batching periodically groups outstanding requests from a memory request buffer into larger units termed “batches” that have higher priority than all other buffered requests. Each “batch” may include some maximum number of requests for each bank of the shared memory and for some or all concurrent threads. Further, average thread stall times are reduced by using computed thread rankings in scheduling request servicing from the shared memory. In various embodiments, requests from higher ranked threads are prioritized over requests from lower ranked threads. In various embodiments, a parallelism-aware memory access scheduling policy improves intra-thread bank-level parallelism.

Abstract: An accelerated screen codec technique is described that provides a general screen compression framework, which, in one embodiment, is Graphics Processor Unit (GPU) friendly. In one embodiment, in order to compress screen data, blocks in a compound screen image containing both images and text are segmented into text blocks and pictorial blocks using a simple gradient-based procedure. The text and pictorial blocks are then compressed respectively via different compression techniques. Additionally, a GPU acceleration architecture of one embodiment of the accelerated screen codec technique provides a screen codec that maximally exploits a GPU's high parallelism and reduces the download bandwidth from GPU to Computer Processing Unit (CPU).

Abstract: A “Wearable Electromyography-Based Controller” includes a plurality of Electromyography (EMG) sensors and provides a wired or wireless human-computer interface (HCl) for interacting with computing systems and attached devices via electrical signals generated by specific movement of the user's muscles. Following initial automated self-calibration and positional localization processes, measurement and interpretation of muscle generated electrical signals is accomplished by sampling signals from the EMG sensors of the Wearable Electromyography-Based Controller. In operation, the Wearable Electromyography-Based Controller is donned by the user and placed into a coarsely approximate position on the surface of the user's skin. Automated cues or instructions are then provided to the user for fine-tuning placement of the Wearable Electromyography-Based Controller.

Abstract: An octree GPU construction system and method for constructing a complete octree data structure on a graphics processing unit (GPU). Embodiments of the octree GPU construction system and method first defines a complete octree data structure as forming a complete partition of the 3-D space and including a vertex, edge, face, and node arrays, and neighborhood information. Embodiments of the octree GPU construction system and method input a point cloud and construct a node array. Next, neighboring nodes are computed for each of the nodes in the node arrays by using at least two pre-computed look-up tables (such as a parent look-up table and a child look-up table). Embodiments of the octree GPU construction system and method then use the neighboring nodes and neighborhood information to compute a vertex array, edge array, and face array are computed by determining owner information and self-ownership information based on the neighboring nodes.

Abstract: An adaptive interpolation technique with artifact reduction is described that technique generates digital images with full-color RGB (red, green, blue) information, from raw pictures (e.g., Bayer-mosaiced single-color images) created by single-CCD digital cameras. The technique employs an improved criterion for choosing the interpolation criterion, which takes into account an output interpolated value. It employs small changes to filter coefficients, for better results and accommodation of “correction attenuation”. In one embodiment, the technique further employs a “correction attenuation” step, which reduces “color sprinkling” artifacts for certain kinds of diagonal edges. The technique makes only a single pass over the image; all colors are interpolated during that pass, vice the multiple passes required by other better performing algorithms (in some cases over ten).

Abstract: An interactive concept learning image search technique that allows end-users to quickly create their own rules for re-ranking images based on the image characteristics of the images. The image characteristics can include visual characteristics as well as semantic features or characteristics, or may include a combination of both. End-users can then rank or re-rank any current or future image search results according to their rule or rules. End-users provide examples of images each rule should match and examples of images the rule should reject. The technique learns the common image characteristics of the examples, and any current or future image search results can then be ranked or re-ranked according to the learned rules.

Abstract: A method for compressing a high dynamic range (HDR) texture. A first block of texels of the HDR texture in a red-green-blue (RGB) space may be transformed to a second block of texels in a luminance-chrominance space. The first block may have red values, green values and blue values. The second block may have luminance values and chrominance values. The chrominance values may be based on a sum of the red values, a sum of the green values and a sum of the blue values. The luminance values and the chrominance values may be converted to an 8-bit integer format. The luminance values may be modified to restore a local linearity property to the second block. The second block may be compressed.

Abstract: Automatic programming, scheduling, and control of planned activities at “worker nodes” in a distributed environment are provided by a “real-time self tuner” (RTST). The RTST provides self-tuning of controlled interoperation among an interconnected set of distributed components (i.e., worker nodes) including, for example, home appliances, security systems, lighting, sensor networks, medical electronic devices, wearable computers, robotics, industrial controls, wireless communication systems, audio nets, distributed computers, toys, games, etc. The RTST acts as a centralized “planner” that is either one of the nodes or a dedicated computing device. A set of protocols allow applications to communicate with the nodes, and allow one or more nodes to communicate with each other.

Abstract: A “Rational Z-Buffer” provides various techniques for reducing artifacts when rendering graphics using z-buffers. In particular, the Rational Z-Buffer reduces the likelihood of z-buffer collisions when using hardware or software z-buffer algorithms to render graphics by delaying homogenous division of pixels until after occlusion testing. Further, occlusion testing between any two pixels, p0 and p1, is accomplished by comparing rational depth values, r0={z0, w0} and r1={z1, w1}, for pixel p0 and p1 to determine which pixels are visible. Depth values are compared by determining whether the expression z0w1<z1w0 is true. If true, then pixel p0 occludes pixel p1 in clipping cube space relative to an image-plane defined by a particular viewpoint and the field of view.

Abstract: An efficient symbolic differentiation method and system that automatically computes one or more derivatives of a function using a computing device. A derivative graph is used to graphically represent the derivative of a function. Repeated factorization of the derivative graph yields a factored derivative graph. The derivative is computed by summing the products along all product paths in the factored derivative graph. The efficient symbolic differentiation method and system operates on both single input/single output and multiple input/multiple output functions. For a single input/single output function, the order of the factoring does not matter. However, for a multiple input/multiple output function, the factoring order is such that the factor subgraph appearing most frequently in the derivative graph is factored first. The method and system also use a product pairs priority queue to avoid the re-computing of sub-strings that are common between product paths.

Abstract: An approach to enrich skeleton-driven animations with physically-based secondary deformation in real time is described. To achieve this goal, the technique described employs a surface-based deformable model that can interactively emulate the dynamics of both low- and high-frequency volumetric effects. Given a surface mesh and a few sample sequences of its physical behavior, a set of motion parameters of the material are learned during an off-line preprocessing step. The deformable model is then applicable to any given skeleton-driven animation of the surface mesh. Additionally, the described dynamic skinning technique can be entirely implemented on GPUs and executed with great efficiency. Thus, with minimal changes to the conventional graphics pipeline, the technique can drastically enhance the visual experience of skeleton-driven animations by adding secondary deformation in real time.

Abstract: Presented are embodiments for nonlocal mean filtering that provide a robust and efficient method for reducing noise in digital images and video frames. These embodiments build on a separable property of neighborhood filtering to offer a fast, parallel and vectorized implementation in contemporary shared memory computer architectures while minimizing theoretical computational complexity. In practice, this approach is fast and scales linearly with image size.