Adobe, Inc.

Other

Atishay Jain

Arian Behzadi

Geoffrey Charles Dowd

Kumar Ayush

Joseph Michael Andolina

Shamit Kumar Mehta

Stakshi Jindal Garg

David Ericksen

Harnish Lakhani

Pankaj Chaurasia

Raghav Gupta

Nitesh Chourasia

Ansh Chaurasia

A location-sensitive saliency prediction neural network generates location-sensitive saliency data for an image. The location-sensitive saliency prediction neural network includes, at least, a filter module, an inception module, and a location-bias module. The filter module extracts visual features at multiple contextual levels, and generates a feature map of the image. The inception module generates a multi-scale semantic structure, based on multiple scales of semantic content depicted in the image. In some cases, the inception block performs parallel analysis of the feature map, such as by parallel multiple layers, to determine the multiple scales of semantic content. The location-bias module generates a location-sensitive saliency map of location-dependent context of the image based on the multi-scale semantic structure and on a bias map. In some cases, the bias map indicates location-specific weights for one or more regions of the image.

Center-biased machine learning techniques to determine saliency in digital images

Systems and methods for content-based video retrieval are described. The systems and methods may break a video into multiple frames, generate a feature vector from the frames based on the temporal relationship between them, and then embed the feature vector into a vector space along with a vector representing a search query. In some embodiments, the video feature vector is converted into a text caption prior to the embedding. In other embodiments, the video feature vector and a sentence vector are each embedded into a common space using a join video sentence embedding model. Once the video and the search query are embedded into a common vector space, a distance between them may be calculated. After calculating the distance between the search query and set of videos, the distances may be used to select a subset of the videos to present as the result of the search.

Video retrieval based on encoding temporal relationships among video frames

The technology described herein is directed to object compatibility-based identification and replacement of objects in digital representations of real-world environments for contextualized content delivery. In some implementations, an object compatibility and retargeting service that selects and analyzes a viewpoint (received from a user's client device) to identify objects that are the least compatible with other surrounding real-world objects in terms of style compatibility with the surrounding real-world objects and color compatibility with the background is described. The object compatibility and retargeting service also generates recommendations for replacing the least compatible object with objects/products having more style/design compatibility with the surrounding real-world objects and color compatibility with the background. Furthermore, the object compatibility and retargeting service can create personalized catalogues with the recommended objects/products embedded in the viewpoint in place of the least compatible object with similar pose and scale for retargeting the user.

Compatibility-based identification of incompatible objects in digital representations of real-world environments

In various implementations, a computing device is configured to provide a live preview of salient contours generated on a live digital video feed. In particular, a designer can use a computing device with a camera, such as a smart phone, to view a real-time preview of salient contours generated from edges detected in frames of a live digital video feed prior to capture, thereby eliminating the unpredictability of salient contours generated from a previously captured image. In some implementations, the salient contours are overlaid on a greyscale conversion of the live digital video feed for improved processing and visual contrast. Other implementations modify aspects of edge-detecting or post-processing filters for improved performance on mobile computing devices.

Generation of salient contours using live video

A ball detection and tracking system including one or more visual sensors and a detection and tracking agent that ranks a plurality of blob detection algorithms based on a detection metric and uses a selected base detection algorithm to identify one or more candidate blobs. Based on this, the agent is able to generate a track for the candidate blobs and assign one or more subsequent candidate blobs to a best ranked one of the tracks if the assignment satisfies a cost threshold.

Ball detection and tracking device, system and method

Growing community of inventors

Delhi, India

Atishay Jain