Yissum Research Development Company of the Hebrew University of Jerusalem Ltd.

Indian Institute of Technology Delhi

International Institute of Information Technology, Hyderabad

Indian Institute of Technology Hyderabad

Chetan Arora

Shmuel Peleg

Tavi Halperin

Yair Poleg

C V Jawahar

Rohit Saluja

Vaishnavi Mohan Khindkar

Vineeth N Balasubramanian

A method for detecting object in an image in a target environment that is adapted to a source environment using a machine learning model is provided. The method includes (i) extracting features from source image associated with source environment and target image associated with target environment, (ii) generating a feature map based on the features, (iii) generating a pixel-wise probability output map (iv) determining a first environment invariant feature map by combining the feature map with the pixel-wise probability output map, (v) determining a second environment invariant feature map by combining the first environment invariant feature map and the features, (vi) generating environment invariant feature maps at different instances, (vii) extracting environment invariant features based on the environment invariant feature maps, (viii) detecting the object in the image in the target environment that is adapted to the source environment by training the machine learning model using the environment invariant features.

System and method for detecting object in an adaptive environment using a machine learning model

A method and a system for generating adaptive fast forward of egocentric videos are provided here. The method may include the following steps: obtaining a video footage containing a sequence of image frames captured by a non-stationary capturing device; estimating a moving direction of the non-stationary capturing device for a plurality of frames in the sequence of image frames; and generating a shortened video footage having fewer frames than said video footage, by sampling the sequence of image frames, wherein the sampling is carried out by selecting specific image frames and that minimize an overall cost associated with a deviation from a specific direction related to the moving direction, calculated for each of said plurality of image frames.

Method and system for generating adaptive fast forward of egocentric videos

Growing community of inventors

New Delhi, India

Chetan Arora