Patents by Inventor Suresh Joshi
Suresh Joshi has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Publication number: 20180025749Abstract: Described are various technologies that pertain to automatically generating looped videos or cinemagraphs by selecting objects to animate from an input video. In one implementation a group of semantically labeled objects from an input video is received. Candidate objects from the input video that can appear as a moving object in an output cinemagraph or looped video are identified. Candidate video loops are generated using the selected candidate objects. One or more of these candidate video loops are then selected to create a final cinemagraph. The selection of candidate video loops used to create the final cinemagraph can be made by a user or by a predictive model trained to evaluate the subjective attractiveness of the candidate video loops.Type: ApplicationFiled: September 14, 2016Publication date: January 25, 2018Inventors: Tae-Hyun Oh, Sing Bing Kang, Neel Suresh Joshi, Baoyuan Wang
-
Publication number: 20170359548Abstract: Various technologies described herein pertain to creation of an output hyper-lapse video from an input video. Values indicative of overlaps between pairs of frames in the input video are computed. A value indicative of an overlap between a pair of frames can be computed based on a sparse set of points from each of the frames in the pair. Moreover, a subset of the frames from the input video are selected based on the values of the overlaps between the pairs of the frames in the input video and a target frame speed-up rate. Further, the output hyper-lapse video is generated based on the subset of the frames. The output hyper-lapse video can be generated without a remainder of the frames of the input video other than the subset of the frames.Type: ApplicationFiled: August 2, 2017Publication date: December 14, 2017Inventors: Neel Suresh Joshi, Wolf Kienzle, Michael A. Toelle, Matthieu Uyttendaele, Michael F. Cohen
-
Publication number: 20170323174Abstract: A “Food Logger” provides various approaches for learning or training one or more image-based models (referred to herein as “meal models”) of nutritional content of meals. This training is based on one or more datasets of images of meals in combination with “meal features” that describe various parameters of the meal. Examples of meal features include, but are not limited to, food type, meal contents, portion size, nutritional content (e.g., calories, vitamins, minerals, carbohydrates, protein, salt, etc.), food source (e.g., specific restaurants or restaurant chains, grocery stores, particular pre-packaged foods, school meals, meals prepared at home, etc.). Given the trained models, the Food Logger automatically provides estimates of nutritional information based on automated recognition of new images of meals provided by (or for) the user. This nutritional information is then used to enable a wide range of user-centric interactions relating to food consumed by individual users.Type: ApplicationFiled: April 17, 2017Publication date: November 9, 2017Applicant: Microsoft Technology Licensing, LLCInventors: Neel Suresh Joshi, Siddharth Khullar, T Scott Saponas, Daniel Morris, Oscar Beijbom
-
Patent number: 9779774Abstract: A cinemagraph is generated that includes one or more video loops. A cinemagraph generator receives an input video, and semantically segments the frames to identify regions that correspond to semantic objects and the semantic object depicted in each identified region. Input time intervals are then computed for the pixels of the frames of the input video. An input time interval for a particular pixel includes a per-pixel loop period and a per-pixel start time of a loop at the particular pixel. In addition, the input time interval of a pixel is based, in part, on one or more semantic terms which keep pixels associated with the same semantic object in the same video loop. A cinemagraph is then created using the input time intervals computed for the pixels of the frames of the input video.Type: GrantFiled: September 14, 2016Date of Patent: October 3, 2017Assignee: MICROSOFT TECHNOLOGY LICENSING, LLCInventors: Sing Bing Kang, Neel Suresh Joshi, Hugues Hoppe, Tae-Hyun Oh, Baoyuan Wang
-
Patent number: 9762846Abstract: Various technologies described herein pertain to creation of an output hyper-lapse video from an input video. Values indicative of overlaps between pairs of frames in the input video are computed. A value indicative of an overlap between a pair of frames can be computed based on a sparse set of points from each of the frames in the pair. Moreover, a subset of the frames from the input video are selected based on the values of the overlaps between the pairs of the frames in the input video and a target frame speed-up rate. Further, the output hyper-lapse video is generated based on the subset of the frames. The output hyper-lapse video can be generated without a remainder of the frames of the input video other than the subset of the frames.Type: GrantFiled: May 8, 2015Date of Patent: September 12, 2017Assignee: Microsoft Technology Licensing, LLCInventors: Neel Suresh Joshi, Wolf Kienzle, Michael A. Toelle, Matthieu Uyttendaele, Michael F. Cohen
-
Publication number: 20170154458Abstract: Various technologies described herein pertain to generating a video loop. An input video can be received, where the input video includes values at pixels over a time range. An optimization can be performed to determine a respective input time interval within the time range of the input video for each pixel from the pixels in the input video. The respective input time interval for a particular pixel can include a per-pixel loop period and a per-pixel start time of a loop at the particular pixel within the time range from the input video. Moreover, an output video can be created based upon the values at the pixels over the respective input time intervals for the pixels in the input video.Type: ApplicationFiled: December 8, 2016Publication date: June 1, 2017Inventors: Hugues Hoppe, Neel Suresh Joshi, Zicheng Liao
-
Patent number: 9659225Abstract: A “Food Logger” provides various approaches for learning or training one or more image-based models (referred to herein as “meal models”) of nutritional content of meals. This training is based on one or more datasets of images of meals in combination with “meal features” that describe various parameters of the meal. Examples of meal features include, but are not limited to, food type, meal contents, portion size, nutritional content (e.g., calories, vitamins, minerals, carbohydrates, protein, salt, etc.), food source (e.g., specific restaurants or restaurant chains, grocery stores, particular pre-packaged foods, school meals, meals prepared at home, etc.). Given the trained models, the Food Logger automatically provides estimates of nutritional information based on automated recognition of new images of meals provided by (or for) the user. This nutritional information is then used to enable a wide range of user-centric interactions relating to food consumed by individual users.Type: GrantFiled: February 12, 2014Date of Patent: May 23, 2017Assignee: Microsoft Technology Licensing, LLCInventors: Neel Suresh Joshi, Siddharth Khullar, T Scott Saponas, Daniel Morris, Oscar Beijbom
-
Patent number: 9547927Abstract: Various technologies described herein pertain to generating a video loop. An input video can be received, where the input video includes values at pixels over a time range. An optimization can be performed to determine a respective input time interval within the time range of the input video for each pixel from the pixels in the input video. The respective input time interval for a particular pixel can include a per-pixel loop period and a per-pixel start time of a loop at the particular pixel within the time range from the input video. Moreover, an output video can be created based upon the values at the pixels over the respective input time intervals for the pixels in the input video.Type: GrantFiled: May 30, 2016Date of Patent: January 17, 2017Assignee: Microsoft Technology Licensing, LLCInventors: Hugues Hoppe, Neel Suresh Joshi, Zicheng Liao
-
Patent number: 9501154Abstract: The subject disclosure is directed towards modifying the apparent camera path from an existing video into a modified, stylized video. Camera motion parameters such as horizontal and vertical translation, rotation and zoom may be individually modified, including by an equalizer-like set of interactive controls. Camera motion parameters also may be set by loading preset data, such as motion data acquired from another video clip.Type: GrantFiled: April 21, 2014Date of Patent: November 22, 2016Assignee: Microsoft Technology Licensing, LLCInventors: Neel Suresh Joshi, Daniel Scott Morris, Michael F. Cohen
-
Publication number: 20160330399Abstract: Various technologies described herein pertain to creation of an output hyper-lapse video from an input video. Values indicative of overlaps between pairs of frames in the input video are computed. A value indicative of an overlap between a pair of frames can be computed based on a sparse set of points from each of the frames in the pair. Moreover, a subset of the frames from the input video are selected based on the values of the overlaps between the pairs of the frames in the input video and a target frame speed-up rate. Further, the output hyper-lapse video is generated based on the subset of the frames. The output hyper-lapse video can be generated without a remainder of the frames of the input video other than the subset of the frames.Type: ApplicationFiled: May 8, 2015Publication date: November 10, 2016Inventors: Neel Suresh Joshi, Wolf Kienzle, Michael A. Toelle, Matthieu Uyttendaele, Michael F. Cohen
-
Publication number: 20160275714Abstract: Various technologies described herein pertain to generating a video loop. An input video can be received, where the input video includes values at pixels over a time range. An optimization can be performed to determine a respective input time interval within the time range of the input video for each pixel from the pixels in the input video. The respective input time interval for a particular pixel can include a per-pixel loop period and a per-pixel start time of a loop at the particular pixel within the time range from the input video. Moreover, an output video can be created based upon the values at the pixels over the respective input time intervals for the pixels in the input video.Type: ApplicationFiled: May 30, 2016Publication date: September 22, 2016Inventors: Hugues Hoppe, Neel Suresh Joshi, Zicheng Liao
-
Publication number: 20160202451Abstract: A lens assembly includes a plurality of component lens elements, and a fiber optic face plate having a back surface and a non-planar front surface. The plurality of component lens elements are configured to direct a focused image onto the non-planar front surface of the fiber optic face plate, and the fiber optic face plate is configured to transmit the focused image through the back surface.Type: ApplicationFiled: March 24, 2016Publication date: July 14, 2016Applicant: Microsoft Technology Licensing, LLCInventors: Brian Kevin Guenter, Neel Suresh Joshi, Changyin Zhou
-
Patent number: 9378578Abstract: Various technologies described herein pertain to generating a video loop. An input video can be received, where the input video includes values at pixels over a time range. An optimization can be performed to determine a respective input time interval within the time range of the input video for each pixel from the pixels in the input video. The respective input time interval for a particular pixel can include a per-pixel loop period and a per-pixel start time of a loop at the particular pixel within the time range from the input video. Moreover, an output video can be created based upon the values at the pixels over the respective input time intervals for the pixels in the input video.Type: GrantFiled: February 15, 2016Date of Patent: June 28, 2016Assignee: Microsoft Technology Licensing, LLCInventors: Hugues Hoppe, Neel Suresh Joshi, Zicheng Liao
-
Publication number: 20160163085Abstract: Various technologies described herein pertain to generating a video loop. An input video can be received, where the input video includes values at pixels over a time range. An optimization can be performed to determine a respective input time interval within the time range of the input video for each pixel from the pixels in the input video. The respective input time interval for a particular pixel can include a per-pixel loop period and a per-pixel start time of a loop at the particular pixel within the time range from the input video. Moreover, an output video can be created based upon the values at the pixels over the respective input time intervals for the pixels in the input video.Type: ApplicationFiled: February 15, 2016Publication date: June 9, 2016Inventors: Hugues Hoppe, Neel Suresh Joshi, Zicheng Liao
-
Patent number: 9292956Abstract: Various technologies described herein pertain to generating a video loop. An input video can be received, where the input video includes values at pixels over a time range. An optimization can be performed to determine a respective input time interval within the time range of the input video for each pixel from the pixels in the input video. The respective input time interval for a particular pixel can include a per-pixel loop period and a per-pixel start time of a loop at the particular pixel within the time range from the input video. Moreover, an output video can be created based upon the values at the pixels over the respective input time intervals for the pixels in the input video.Type: GrantFiled: May 3, 2013Date of Patent: March 22, 2016Assignee: Microsoft Technology Licensing, LLCInventors: Hugues Hoppe, Neel Suresh Joshi, Zicheng Liao
-
Publication number: 20150302158Abstract: Aspects of the subject disclosure are directed towards a video-based pulse/heart rate system that may use motion data to reduce or eliminate the effects of motion on pulse detection. Signal quality may be computed from (e.g., transformed) video signal data, such as by providing video signal feature data to a trained classifier that provides a measure of the quality of pulse information in each signal. Based upon the signal quality data, corresponding waveforms may be processed to select one for extracting pulse information therefrom. Heart rate data may be computed from the extracted pulse information, which may be smoothed into a heart rate value for a time window based upon confidence and/or prior heart rate data.Type: ApplicationFiled: April 21, 2014Publication date: October 22, 2015Applicant: Microsoft CorporationInventors: Daniel Scott Morris, Siddharth Khullar, Neel Suresh Joshi, Timothy Scott Saponas, Desney S. Tan
-
Publication number: 20150304560Abstract: The subject disclosure is directed towards modifying the apparent camera path from an existing video into a modified, stylized video. Camera motion parameters such as horizontal and vertical translation, rotation and zoom may be individually modified, including by an equalizer-like set of interactive controls. Camera motion parameters also may be set by loading preset data, such as motion data acquired from another video clip.Type: ApplicationFiled: April 21, 2014Publication date: October 22, 2015Applicant: Microsoft CorporationInventors: Neel Suresh Joshi, Daniel Scott Morris, Michael F. Cohen
-
Publication number: 20150228062Abstract: A “Food Logger” provides various approaches for learning or training one or more image-based models (referred to herein as “meal models”) of nutritional content of meals. This training is based on one or more datasets of images of meals in combination with “meal features” that describe various parameters of the meal. Examples of meal features include, but are not limited to, food type, meal contents, portion size, nutritional content (e.g., calories, vitamins, minerals, carbohydrates, protein, salt, etc.), food source (e.g., specific restaurants or restaurant chains, grocery stores, particular pre-packaged foods, school meals, meals prepared at home, etc.). Given the trained models, the Food Logger automatically provides estimates of nutritional information based on automated recognition of new images of meals provided by (or for) the user. This nutritional information is then used to enable a wide range of user-centric interactions relating to food consumed by individual users.Type: ApplicationFiled: February 12, 2014Publication date: August 13, 2015Applicant: Microsoft CorporationInventors: Neel Suresh Joshi, Siddharth Khullar, T Scott Saponas, Daniel Morris, Oscar Beijbom
-
Patent number: 8949850Abstract: Server load-balancing operation-related data, such as data associated with a system configured for global server load balancing (GSLB) that orders IP addresses into a list based on a set of performance metrics, is tracked. Such operation-related data includes inbound source IP addresses (e.g., the address of the originator of a DNS request), the requested host and zone, identification of the selected “best” IP addresses resulting from application of a GSLB algorithm and the selection metric used to decide on an IP address as the “best” one. Furthermore, the data includes a count of the selected “best” IP addresses selected via application of the GSLB algorithm, and for each of these IP addresses, the list of deciding performance metrics, along with a count of the number of times each of these metrics in the list was used as a deciding factor in selection of this IP address as the best one.Type: GrantFiled: May 5, 2006Date of Patent: February 3, 2015Assignee: Brocade Communications Systems, Inc.Inventors: Prajakta Suresh Joshi, Sunanda Lakshmi Kommula
-
Publication number: 20150002393Abstract: The mobile image viewing technique described herein provides a hands-free interface for viewing large imagery (e.g., 360 degree panoramas, parallax image sequences, and long multi-perspective panoramas) on mobile devices. The technique controls the imagery displayed on a display of a mobile device by movement of the mobile device. The technique uses sensors to track the mobile device's orientation and position, and front facing camera to track the user's viewing distance and viewing angle. The technique adjusts the view of a rendered imagery on the mobile device's display according to the tracked data. In one embodiment the technique can employ a sensor fusion methodology that combines viewer tracking using a front facing camera with gyroscope data from the mobile device to produce a robust signal that defines the viewer's 3D position relative to the display.Type: ApplicationFiled: September 16, 2014Publication date: January 1, 2015Inventors: Michael F. Cohen, Neel Suresh Joshi