公开(公告)号：US20230162260A1

公开(公告)日：2023-05-25

申请号：US17970666

申请日：2022-10-21

Applicant: Tata Consultancy Services Limited

Inventor： Jayavardhana Rama GUBBI LAKSHMINARASIMHA ,  Gaurab BHATTACHARYA ,  Balamuralidhar PURUSHOTHAMAN ,  Bagyalakshmi VASUDEVAN ,  Nikhil KILARI

IPC: G06Q30/06 ,  G06F16/56

CPC classification number: G06Q30/0631 ,  G06Q30/0621 ,  G06F16/56

Abstract: Product recommendation is a very important aspect of e-commerce applications. Traditional product recommendation systems recommend products similar to a query image provided by a user and allows minimum or no personalization. It is challenging to incorporate personalization due to the presence of overlapping fine-grained attributes, variations in attribute style and visual appearance, small inter-class variation and class imbalance in the images of products. Embodiments of present disclosure address these challenges by a method of personalized substitute product recommendation using Personalized Attribute Search Networks (PAtSNets) comprising neural network layers interleaved with Attentive Style Embedding (ASE) modules to generate attribute-aware feature representation vector of a query image provided by the user and conforming to the personalization instructions specified by the user. This feature representation vector is then used to recommend substitute products to the user. Thus, embodiments of present disclosure enable accurate substitute product recommendation suiting user requirements.

公开(公告)号：US20240013522A1

公开(公告)日：2024-01-11

申请号：US18209094

申请日：2023-06-13

Applicant: Tata Consultancy Services Limited

Inventor： Jayavardhana Rama GUBBI LAKSHMINARASIMHA ,  Vartika SENGAR ,  Vivek Bangalore SAMPATHKUMAR ,  Gaurab BHATTACHARYA ,  Balamuralidhar PURUSHOTHAMAN ,  Arpan PAL

IPC: G06V10/776 ,  G06V10/774 ,  G06V10/82 ,  G06T11/00 ,  G06N3/0455 ,  G06N3/08

CPC classification number: G06V10/776 ,  G06V10/774 ,  G06V10/82 ,  G06T11/001 ,  G06N3/0455 ,  G06N3/08

Abstract: This disclosure relates generally to identification and mitigation of bias while training deep learning models. Conventional methods do not provide effective methods for bias identification, and they require pre-defined concepts and rules for bias mitigation. The embodiments of the present disclosure train an auto-encoder to produce a generalized representation of an input image by decomposing into a set of latent embedding. The set of latent embedding are used to learn the shape and color concepts of the input image. The feature specialization is done by training an auto-encoder to reconstruct the input image using the shape embedding modulated by color embedding. To identify the bias, permutation invariant neural network is trained for classification task and attribution scores corresponding to each concept embedding are computed. The method also performs de-biasing the classifier by training it with a set of counterfactual images generated by modifying the latent embedding learned by the auto-encoder.

公开(公告)号：US20240422281A1

公开(公告)日：2024-12-19

申请号：US18740734

申请日：2024-06-12

Applicant: Tata Consultancy Services Limited

Inventor： Gaurab BHATTACHARYA ,  Jayavardhana Rama GUBBI LAKSHMINARASIMHA ,  Bagya Lakshmi VASUDEVAN ,  Gaurav SHARMA ,  Kuruvilla ABRAHAM ,  Arpan PAL ,  Balamuralidhar PURUSHOTHAMAN ,  Nikhil KILARI

IPC: H04N1/60 ,  G06T7/11 ,  G06T7/90 ,  G06V10/44 ,  G06V10/56 ,  G06V10/762

Abstract: State of the art techniques have challenges for recoloring a product, which includes non-realistic images, incorrect color mapping, structural distortion, color spilling into background, and in handling multi-color, multi-apparel and multi-product scenario images. Embodiments of the present disclosure provide a method and system for recoloring a product using a dual attention (DA) U-Net based on a generative adversarial network (GAN) framework to generate a recolored product with a target color from an input image. The disclosed DAU-Net enables recoloring (i) a single-color in a single-product scenario, (ii) a plurality of colors in a single-product scenario, and (iii) multi-product scenario with a human model. The DAU net uses (i) a product components aware feature (PCAF) extraction to generate feature representations comprising information of the target color with finer details, and (b) a critical feature selection (CFS) mechanism applied on the feature representation, to generate enhanced feature representations.

公开(公告)号：US20240420215A1

公开(公告)日：2024-12-19

申请号：US18666920

申请日：2024-05-17

Applicant: Tata Consultancy Services Limited

Inventor： Vivek Bangalore SAMPATHKUMAR ,  Jayavardhana Rama GUBBI LAKSHMINARASIMHA ,  Gaurab BHATTACHARYA ,  Bagya Lakshmi VASUDEVAN ,  Arpan PAL ,  Balamuralidhar PURUSHOTHAMAN

IPC: G06Q30/0601

Abstract: Unlike visual similarity, visual compatibility is a complex concept. Existing approaches for outfit compatibility prediction does not focus on methods with personalization. The present disclosure proposes a novel approach to model the user's preference for different styles. The outfit compatibility prediction module is a critical component of an outfit recommendation system. An outfit is said to be compatible if all the items are visually compatible and match the user's preferences. The present disclosure represents the outfit as a graph and uses Graph Neural Network (GNN) with attention mechanism to capture the inter-relationship between the items. A graph read-out layer generates the final outfit embedding. The proposed approach efficiently models the preferences of the users for different styles. Finally, the outfit compatibility score is generated by computing the similarity between the outfit embedding and the user embedding.