Hewlett-packard Development Company, L.p.

Conduent Business Services, LLC

Ebay, Incorporated

Sriganesh Madhvanath

Prasenjit Dey

Dinesh Mandalapu

Anbumani Subramanian

Shekhar Ramachandra Borgaonkar

Ramadevi Vennelakanti

Anjaneyulu Seetha Rama Kuchibhotla

Krishnan Ramanathan

Suryaprakash Kompalli

Sabrina Kwan

Rahul Ajmera

Rama Vennelakanti

Dustin Freeman

Naveen Sundar Govindarajulu

Raja Bala

Edgar A Bernal

Parthasarathy Ranganathan

Palghat Srinivas Ramesh

Ajay Gupta

Jayant Kumar

Geetha Manjunath

Qun Li

Manish Kumar

Gyanit Singh

Prashant Asthana

Robert B Taylor

Sandeep Matti Prabhu

Praphul Chandra

Sitaram Ramachandrula

Srinivasu Godavari

Yogesh Sankarasubramaniam

Narendra Annamaneni

Hyun Joo Kim

Saratchandra Indrakanti

Balasubramanian Anand

Pam Lennan

Bruce Williams

Deepu Vijayasenan

Guruprasad Hedge

Godavari Srinivasu

Kiran Kumar Bhuvanagiri

Luke Tratnik

Ankit Shekhawat

Thomas Olszewicki

Balaji Raghavan

Wieslaw Marian Suchy

Muralikrishna Sridhar

Mudit Agrawal

Prashanth Pandit

Xitong Yang

Chandra Praphul

Generating themes for different item offers is described. An item listing system receives a request for a target item and generates themes for the target item by grouping offers based on their properties. The item listing system then determines a display order for the themes based on user behavior data. The item listing system then communicates the themes and display order to a client device from which the request was received, causing the client device to display an interface including at least a subset of the themes, arranged according to the display order. Themes including offers determined to be more appealing to the user of the client device are displayed more prominently relative to other themes. The item listing system is further configured to dynamically modify the display order in real-time based on offer changes, such that the interface continuously provides correct information describing available offers for the target item.

Method, medium, and system for ranking themes using machine learning

In one example of the disclosure, establishment data for a plurality of hotspots is accessed, with each hotspot being linked to a hotspot payoff. Presence data indicative of a mobile device detecting a target hotspot is received via a network. An alternatives list for the target hotspot is determined based on an identification of the target hotspot and the establishment data. The hotspot payoff is caused to be sent to the mobile device for display, the payoff including the alternatives list.

Media hotspot payoffs with alternatives lists

In one example of the disclosure, navigation data indicative of sequencing and spatial relationship among a plurality of media hotspots is accessed. Each of the hotspots is included within a medium and includes a spatial address. Data indicative of a mobile device's detection of a target hotspot and the mobile device's provision of a display of the target hotspot is received via a network. A recommendation for navigation to an associated hotspot is determined based on the navigation data. The associated hotspot is an immediate predecessor or successor relative to the target hotspot. The recommendation is provided to the device for display.

Media navigation recommendations

A system receives a user identifier and a link identifier to identify a machine-readable link in an image captured by a first device. In response to determining that the user identifier indicates a user having an administrative privilege with respect to the machine-readable link, the system sends, to the first device, a response containing information to allow performance of management with respect to the machine-readable link.

Response to a machine-readable link

The disclosed embodiments illustrate a composite navigational method and system for the automatic configuration management of application software by a computing server. The method includes extracting a plurality of previous configuration values from a storage device. The method further includes generating a plurality of abstract syntax trees (ASTs) based on parsing of the plurality of previous configuration values. The method further includes performing one or more pre-specified operations on the generated plurality of ASTs. The method further includes determining a configuration value of a current configuration parameter based on a navigation pattern, such as hierarchical navigation or variable-based filtering navigation. Further, the navigation pattern is determined using the performed one or more pre-specified operations, based on at least user preferences and the extracted plurality of previous configuration values. The method further comprising controlling the configuration of the application software based on the determined configuration value of the current configuration parameter.

Composite navigation method and system for automatic configuration management of application software

A continuous electronic data stream of unlabeled data instances is received and fed into both a stream-based selection strategy and a pool-based selection strategy. The stream-based selection strategy is continuously applied to each of the unlabeled data instances to continually select stream-based data instances that are to be annotated. Additionally, the pool-based selection strategy is periodically applied to a pool of data obtained from the unlabeled data instances, to periodically select pool-based data instances that are to be annotated. Each time the pool-based selection strategy is applied, these methods automatically replace the stream-based data instances with the pool-based data instances. Also, these methods provide, on demand, access to allow a user to annotate the stream-based data instances and the pool-based data instances.

Hybrid active learning for non-stationary streaming data with asynchronous labeling

A multimodal sensing system includes various devices that work together to automatically classify an action. A video camera captures a sequence of digital images. At least one other sensor device captures other sensed data (e.g., motion data). The system will extract video features from the digital images so that each extracted image feature is associated with a time period. It will extract other features from the other sensed data so that each extracted other feature is associated with a time period. The system will fuse a group of the extracted video features and a group of the extracted other features to create a fused feature representation for a time period. It will then analyze the fused feature representation to identify a class, access a data store of classes and actions to identify an action that is associated with the class, and save the identified action to a memory device.

Temporal fusion of multimodal data from multiple data acquisition systems to automatically recognize and classify an action

Embodiments of the present invention disclose a multimodal and gestural control system. According to one embodiment, the multimodal and gestural control system is configured to detect a gesture command from a user via at least one device of a plurality of devices. A control operation and a destination device are both determined based on the gesture command such that the determined control operation is executed on the determined destination device.

Method and system for multimodal and gestural control

Provided is a method of routing a message using a home gateway. A message is received at a message originating gateway, which identifies a home gateway of the sender of the message and routes the message thereto. A message communication preference of a receiver of the message is determined and the message is translated into the message communication preference of the receiver. The message is then routed to the receiver.

Message routing using a home gateway

In one example, a method for multimodal human-machine interaction includes sensing a body posture of a participant using a camera () and evaluating the body posture to determine a posture-based probability of communication modalities from the participant (). The method further includes detecting control input through a communication modality from the participant to the multimedia device () and weighting the control input by the posture-based probability ().

Multimodal interactions based on body postures

A method for executing a qualified command including detecting a hand gesture input for identifying a command, detecting one or more non-hand gesture inputs to qualify the command, and configuring a processor to execute the qualified command on a machine in response to the hand gesture input and one or more non-hand gesture inputs.

Qualified command

Presented is method and system for processing a gesture performed by a user of an input device. The method comprises detecting the gesture and determining a distance of the input device from a predetermined location. A user command is then determined based on the detected gesture and the determined distance.

Gesture processing

Provided is a method of detecting lip activity. The method determines magnitude of optical flow in lip region and at least one non-lip region of a detected face. The ratio of magnitude of optical flow in lip region and at least one non-lip region is compared against a threshold. If the ratio is found to be greater than the threshold, lip activity of the detected face is recognized.

Lip activity detection

A method and apparatus for joint profiling for identifying one or more common interests of members of a group and recommending items accordingly. The method comprises receiving a user profile for each member, the user profile comprising a set of one or more topics of interest to that member; automatically mapping at least one topic from each of the profiles to a concept; deriving a group profile, in dependence upon the concepts and the topics; and generating a list of recommended items for the group based on the group profile. Also presented is a method and apparatus for joint profiling wherein a joint weight for each topic is calculated by: for each user, calculating the reciprocal of a weight associated with the topic for that user; calculating the sum of the resulting reciprocals; and calculating the joint weight as the reciprocal of the resulting sum.

Content recommendation for groups

Provided is a multimodal graphical user interface. The multimodal graphical user interface includes a menu with at least one menu item, wherein the at least one menu item is displayed as command name along with a unique hand shape, wherein the at least one menu item is configured to receive a combination of cursor and selection gesture input.

Multimodal interface

Growing community of inventors

Bengaluru, India

Sriganesh Madhvanath