University of Illinois

Samsung Electronics Co., Ltd.

International Business Machines Corporation

Raymond Alexander Yeh

Jihye Kim

Alexander Gerhard Schwing

Jaejoon Han

Rogerio Schmidt Feris

Jinjun Xiong

Minh Do

Dhiraj Joshi

Colin Graber

Yuan-Ting Hu

Khoi-Nguyen C Mac

A segmentation method and segmentation apparatus are provided, where the segmentation method includes receiving image frames comprising a current frame and an adjacent frame to the current frame, determining a feature map to aggregate the image frames based on temporal information between the current frame and the adjacent frame, extracting a feature of a region of interest (ROI) corresponding to instances included in the current frame from the feature map, predicting a class of an object corresponding to the ROI based on the feature of the ROI, and segmenting the instances by correcting an amodal mask predicted corresponding to the class of the object based on the feature of the ROI.

Segmentation method and segmentation apparatus

An image processing method includes defining relations between entities of a target of which a motion is to be predicted from an image of a first time point based on a feature vector of the entities, estimating a dynamic interaction between the entities at the first time point based on the defined relations between the entities, predicting a motion of the entities changing at a second time point based on the estimated dynamic interaction, and outputting a result to which the motion predicted at the second time point is applied.

Image processing method and apparatus

Techniques regarding action detection based on motion in receptive fields of a neural network model are provided. For example, one or more embodiments described herein can comprise a system, which can comprise a memory that can store computer executable components. The system can also comprise a processor, operably coupled to the memory, and that can execute the computer executable components stored in the memory. The computer executable components can comprise a motion component that can extract a motion vector from a plurality of adaptive receptive fields in a deformable convolution layer of a neural network model. The computer executable components can also comprise an action detection component that can generate a spatio-temporal feature by concatenating the motion vector with a spatial feature extracted from the deformable convolution layer.

Action detection by exploiting motion in receptive fields

Growing community of inventors

Urbana, IL, United States of America

Raymond Alexander Yeh