Abstract: Systems that search databases of videos or images to identify similar products in a given video or image of a product are disclosed. The content of the given video is represented by a feature vector used to measure the given video's similarity to either a video or an image. When the system is deployed to recognize particular fashion items in videos, some such videos are taken in uncontrolled settings, and as a result, may have low resolution, poor contrast, minimal focus, motion blur, or low lighting. By recognizing and removing poor quality video frames from the image recognition pipeline, associating products across video frames to form tracklets of each product, and enriching the feature representation of each item for best retrieval result by fusing information from multiple video frames depicting the item, the system addresses the aforementioned shortcomings.

Abstract: An image processing system identifies objects within images or video segments. To identify an object within an image, the system identifies one or more regions of an image that contain an object. In some examples, a tracklet is used to track an object though a plurality of image frames within a video segment allowing more than one image frame to be used in object detection, and thereby increasing detection accuracy. Various embodiments utilize a deep learning based object detection framework and similar object search framework that models the correlations present between various object categories. The system determines a category for each object detected using a hierarchical tree of categories to learn the visual similarities between various object categories. The hierarchical tree is estimated by analyzing the errors of an object detector which does not use any correlation between the object categories.

Abstract: Methods and systems for training a metric learning convolutional neural network (CNN)-based model for cross-domain image retrieval are disclosed. The methods and systems perform steps of generating a plurality of batches sampled from a cross-domain training dataset to train the CNN-based model to match images of different sub-categories from one domain to another, and training the CNN-based model using the generated batches. The CNN-based model comprises various pooling, normalization, and concatenation layers that enable it to concatenate the normalized outputs of multiple concatenation layers. Use of the generated batches comprises executing a loss function based on one or more batches, where the loss function is a triplet, contrastive, or cluster loss function. Embodiments of the present invention enable the CNN-based model to summarize information from multiple convolutional layers, thus improving visual search. Also disclosed are benefits of the new methods, and alternative embodiments of implementation.

Abstract: A system and a method for associating network connected device displayed screen content are disclosed. The method includes providing the network connected device having a display screen. A search query is prepared based on a selection of information from a portion of the display screen using an artificial perimeter. The selection of information corresponds to at least one of underlying pixels, meta-data, and media components of the content within the artificial perimeter. The search query is sent over a network to a visual search processor for retrieving a search result. The search result is retrieved upon matching of the information present in the search query with data accessible to the visual search processor. The search result is forwarded by the visual search processor to the network connected device. Further, the search result is received by the network connected device and thereafter is displayed on the display screen.