Abstract: Described is a technology for computing visual and textual summaries for tagged image collections. Heterogeneous affinity propagation is used to together identify both visual and textual exemplars. The heterogeneous affinity propagation finds the exemplars for relational heterogeneous data (e.g., images and words) by considering the relationships (e.g., similarities) within pairs of images, pairs of words, and relationships of words to images (affinity) in an integrated manner.

Abstract: In some examples, a physical keyboard is used with a computing device. For instance, the physical keyboard can be integrated with a bottom bezel area of a tablet computing device. Gesture sensors can also be integrated with the physical keyboard to provide functionality associated with thumb gestures. To illustrate, thumb gestures can be used for spacebar functionality, zooming in and out of an area on a display, or rotating an area on a display. In some instances, touch sensors can also be integrated with one or more keys of the physical keyboard to provide additional input to the computing device for determining keyboard input. In an implementation, touch sensors can be integrated on a top surface of a key or on one or more sides of a key.

Abstract: Techniques for identifying a salient object with respect to its context are described. A process receives an input image that includes a salient object. The process segments the input image into multiple regions and calculates a saliency value for each of the segmented regions based on scale image levels. The process constructs saliency maps based at least in part on the calculated saliency value, and combines the saliency maps to construct a total saliency map. Next, the process connects a set of line segments computed from the input image and utilizes the total saliency map to compute a closed boundary, which forms a shape prior from the closed boundary, and extracts the salient object from the total saliency map and the shape prior.

Abstract: A swiveling body is installed on a base in a swivelable manner. An electric motor for swiveling swivels the swiveling body. An inverter supplies electric power to the electric motor for swiveling. An obstacle detector detects an obstacle around the base and transmits a detected result to a control unit. When the obstacle detector detects the obstacle, the control unit determines whether or not the obstacle is present within a monitoring region, and when the obstacle is present inside the monitoring region, the control unit stops the electric motor for swiveling. In order to avoid danger, the swiveling operation can be stopped more safely.

Abstract: This document describes tools associated with symbol entry control functions. In some implementations, the tools identify a first finger that is in tactile contact with a touch screen. The first finger can select a subset of symbols from a plurality of symbols that can be entered via the touch screen. The tools can also identify whether one or more other fingers are in concurrent tactile contact with the first finger on the touch screen. The tools can select an individual symbol from the subset based on whether the one or more other fingers are in concurrent tactile contact with the first finger on the touch screen.

Abstract: In some examples, a layered encoding component and a layered decoding component provide for different ways to encode and decode, respectively, video streams transmitted between devices. For instance, in encoding a video stream, a layered encoding component may analyze the content of successive video frames and determine different types of encoding techniques to use for different ones of the video frames. Further, in some cases, some of the encoding techniques may be used on less than an entire video frame. In another example, in decoding a video stream, a layered decoding component may receive video frames encoded with different types of encoding. The layered decoding component may decode the differently encoded video frames and combine them to reconstruct a video stream.

Abstract: In some examples, a layered encoding component and a layered decoding component provide for different ways to encode and decode, respectively, video streams transmitted between devices. For instance, in encoding a video stream, video frames may be analyzed across multiple video frames to determine temporal characteristics, and analyzed spatially within a single given video frame. Further, based at partly on the analysis of the video frames, some video frames may be encoded with a first encoding and portions of other video frames may be encoded using a second layer encoding, where the second layer encoding may use a different type of encoding for different portions of a single given video frame. To decode an encoded video stream, both the base layer encoded video frames and the second layer encoded video frames may be transmitted, decoded, and combined at a destination device into a reconstructed video stream.

Abstract: In one embodiment, a communication is established between two endpoints. The communication session may be a video call or an audio call. The communication session may be managed by a call manager using, for example, voice over internet protocol and session initiation protocol. One of the endpoints initiates recording the communication session. The call manager facilitates recording the communication session based on a recording policy associated with the initiating endpoint. The recording policy may specify far end recording, near end recording, or a prioritized order of far and near end recording. The call manager selected an anchor network device for copying the communication session based on the recording policy.

Abstract: This document describes tools associated with symbol entry control functions. In some implementations, the tools identify a first finger that is in tactile contact with a touch screen. The first finger can select a subset of symbols from a plurality of symbols that can be entered via the touch screen. The tools can also identify whether one or more other fingers are in concurrent tactile contact with the first finger on the touch screen. The tools can select an individual symbol from the subset based on whether the one or more other fingers are in concurrent tactile contact with the first finger on the touch screen.

Abstract: Several improvements for use with Bidirectionally Predictive (B) pictures within a video sequence are provided. In certain improvements Direct Mode encoding and/or Motion Vector Prediction are enhanced using spatial prediction techniques. In other improvements Motion Vector prediction includes temporal distance and subblock information, for example, for more accurate prediction. Such improvements and other presented herein significantly improve the performance of any applicable video coding system/logic.

Abstract: A system, method or computer readable storage device to enable mobile devices in capturing high quality photos by using both the rich context available from mobile devices and crowd-sourced social media on the Web. Considering the flexible and adaptive adoption of photography principles with different content and context composition rules and exposure principles are learned from the community-contributed images. Leveraging a mobile device user's scene context and social context, the proposed socialized mobile photography system is able to suggest optimal view enclosure to achieve appealing composition. Due to the complex scene content and a number of shooting-related contexts to exposure parameters, exposure learning is applied to suggest appropriate camera parameters.

Abstract: Several improvements for use with Bidirectionally Predictive (B) pictures within a video sequence are provided. In certain improvements Direct Mode encoding and/or Motion Vector Prediction are enhanced using spatial prediction techniques. In other improvements Motion Vector prediction includes temporal distance and subblock information, for example, for more accurate prediction. Such improvements and other presented herein significantly improve the performance of any applicable video coding system/logic.

Abstract: Dominant color names may be extracted from an image by analyzing spatial-context of pixels contained in the image. A dominant color region may be defined by taking a double-threshold approach that addresses ambiguous color regions and a degree of confidence that each pixel belongs in the dominant color region. Affiliation maps and binary maps may be used to generate the dominant color region. Images may be converted to a saliency map, from which a region of interest may be assigned a dominant color name. Image search results may be filtered by the dominant color name associated with the image.

Abstract: Systems and methods provide image compression based on parameter-assisted inpainting. In one implementation of an encoder, an image is partitioned into blocks and the blocks classified as smooth or unsmooth, based on the degree of visual edge content and chromatic variation in each block. Image content of the unsmooth blocks is compressed, while image content of the smooth blocks is summarized by parameters, but not compressed. The parameters, once obtained, may also be compressed. At a decoder, the compressed image content of the unsmooth blocks and the compressed parameters of the smooth blocks are each decompressed. Each smooth block is then reconstructed by inpainting, guided by the parameters in order to impart visual detail from the original image that cannot be implied from the image content of neighboring blocks that have been decoded.

Abstract: An image display apparatus for a shovel that includes a lower-part traveling body, an upper-part turning body turnably placed on the lower-part traveling body, and an attachment mounted on the upper-part turning body, and performs work in a work area by driving the attachment, includes an image display part configured to display the work area to be subjected to the work. An image of the work area captured with an image capturing device is subjected to image processing to add and indicate a distribution of depressions and elevations of the work area, and is displayed on the image display part.

Abstract: A user behavior model provides personalized recommendations based in part on time and location, particularly to users of mobile devices. Entity types are ranked according to relevance to the user. Example entity types are restaurant, hotel, etc. The relevance may be based on reference to a large-scale database containing queries from other users. Additionally, entities within each entity type may be ranked based on relevance to the user and the time and location context. A user interface may display a ranked list of entity types, such as restaurant, hotel, etc., wherein each entity type is represented by a highest-ranked entity with the entity type. Thus, the user interface may display a highest-ranked restaurant, a highest-ranked hotel, etc. Upon user selection of one such entity type the user interface is replaced with a second user interface, for example showing a ranked hierarchy of restaurants, headed by the highest-ranked restaurant.

Abstract: A rotation type working machine includes: an attachment mounted so as to be able to rotate with respect to a base body; a rotation mechanism which rotates the attachment; a control device which controls the rotation mechanism; and an entering object detection device which detects a position of an entering object entered into a work area, in which the control device controls a rotation operation of the attachment based on a first physical amount related to at least one of a current angular velocity of the attachment and a current moment of inertia of the attachment, and the position of the entering object detected by the entering object detection device.

Abstract: A set of data points is divided into a plurality of subsets of data points. A set of cluster closures is generated based at least in part on the subset of data points. Each cluster closure envelopes a corresponding cluster of a set of clusters and is comprised of data points of the enveloped cluster and data points neighboring the enveloped cluster. A k-Means approximator iteratively assigns data points to a cluster of the set of clusters and updates a set of cluster centroids corresponding to the set of clusters. The k-Means approximator assigns data points based at least in part on the set of cluster closures.

Abstract: An input image, which may include a salient object, is received by a salient object detection and localization system. The system may be trained to detect whether the input image includes a salient object. If the system fails to detect a salient object in the input image, the system may provide the sender of the input with a null result or an indication that the input image does not contain a salient object. If the system detects a salient object in the input image, the system may localize the salient object within the input image. The system may generate an output image based at least in part on the localization of the salient object. The system may provide the sender of the input image with information pertaining to the detected salient object.

Abstract: A user may perform an image search on an object shown in an image. The user may use a mobile device to display an image. In response to displaying the image, the client device may send the image to a visual search system for image segmentation. Upon receiving a segmented image from the visual search system, the client device may display the segmented image to the user who may select one or more segments including an object of interest to instantiate a search. The visual search system may formulate a search query based on the one or more selected segments and perform a search using the search query. The visual search system may then return search results to the client device for display to the user.