-
公开(公告)号：US10339421B2
公开(公告)日：2019-07-02
申请号：US15474027
申请日：2017-03-30
Inventor： Xue Mei , Danil V. Prokhorov , Haibin Ling
Abstract: Described herein are systems and methods for multimodal recurrent network processing. In an embodiment, a system for evaluating multimodal data comprising a multimodal data input and a multimodal processing module is described. The multimodal data input may comprise the multimodal data, the multimodal data may comprise a first modality and a second modality. The multimodal processing module may be configured to receive the multimodal data comprising the first modality and the second modality; evaluate the first modality using a first recursive neural network comprising a first transformation matrix; evaluate the second modality using a second recursive neural network comprising the first transformation matrix; and determine an output based, at least in part, on evaluating the first modality and the second modality.
-
2.发明申请
公开(公告)号：US20160125249A1
公开(公告)日：2016-05-05
申请号：US14528528
申请日：2014-10-30
Inventor： Xue Mei , Yi Wu , Danil V. Prokhorov , Haibin Ling
CPC classification number: G06K9/00791 , G06K9/00805 , G06K9/4642 , G06K9/6249 , G06K2209/21 , G06T7/277 , G06T2207/30252
Abstract: A method and apparatus for tracking an object across a plurality of sequential images, where certain of the images contain motion blur. A plurality of normal templates of a clear target object image and a plurality of blur templates of the target object are generated. In the next subsequent image frame, a plurality of bounding boxes are generated of potential object tracking positions about the target object location in the preceding image frame. For each bounding box image frame, a reconstruction error is generated that one bounding box has a maximum probability that it is the object tracking result in the subsequent image frame.
Abstract translation: 一种用于在多个顺序图像中跟踪对象的方法和装置，其中某些图像包含运动模糊。 产生清晰目标对象图像的多个正常模板和目标对象的多个模糊模板。 在接下来的后续图像帧中，生成关于前一图像帧中的目标对象位置的潜在对象跟踪位置的多个边界框。 对于每个边界框图像帧，产生重建误差，一个边界框具有在随后的图像帧中作为对象跟踪结果的最大概率。
-
公开(公告)号：US20180285689A1
公开(公告)日：2018-10-04
申请号：US15474027
申请日：2017-03-30
Inventor： Xue Mei , Danil V. Prokhorov , Haibin Ling
CPC classification number: G06N3/08 , G06K9/00791 , G06K9/6273 , G06K9/6289 , G06N3/0445 , G06N3/0454 , H04N7/183
Abstract: Described herein are systems and methods for multimodal recurrent network processing. In an embodiment, a system for evaluating multimodal data comprising a multimodal data input and a multimodal processing module is described. The multimodal data input may comprise the multimodal data, the multimodal data may comprise a first modality and a second modality. The multimodal processing module may be configured to receive the multimodal data comprising the first modality and the second modality; evaluate the first modality using a first recursive neural network comprising a first transformation matrix; evaluate the second modality using a second recursive neural network comprising the first transformation matrix; and determine an output based, at least in part, on evaluating the first modality and the second modality.
-
公开(公告)号：US09355320B2
公开(公告)日：2016-05-31
申请号：US14528528
申请日：2014-10-30
Inventor： Xue Mei , Yi Wu , Danil V. Prokhorov , Haibin Ling
CPC classification number: G06K9/00791 , G06K9/00805 , G06K9/4642 , G06K9/6249 , G06K2209/21 , G06T7/277 , G06T2207/30252
Abstract: A method and apparatus for tracking an object across a plurality of sequential images, where certain of the images contain motion blur. A plurality of normal templates of a clear target object image and a plurality of blur templates of the target object are generated. In the next subsequent image frame, a plurality of bounding boxes are generated of potential object tracking positions about the target object location in the preceding image frame. For each bounding box image frame, a reconstruction error is generated that one bounding box has a maximum probability that it is the object tracking result in the subsequent image frame.
Abstract translation: 一种用于在多个顺序图像中跟踪对象的方法和装置，其中某些图像包含运动模糊。 产生清晰目标对象图像的多个正常模板和目标对象的多个模糊模板。 在接下来的后续图像帧中，生成关于前一图像帧中的目标对象位置的潜在对象跟踪位置的多个边界框。 对于每个边界框图像帧，产生重建误差，一个边界框具有在随后的图像帧中作为对象跟踪结果的最大概率。
