公开(公告)号：US11195048B2

公开(公告)日：2021-12-07

申请号：US16750478

申请日：2020-01-23

Applicant: Adobe Inc.

Inventor： Trung Huu Bui ,  Zhe Lin ,  Hao Tan ,  Franck Dernoncourt ,  Mohit Bansal

IPC: G06K9/62 ,  G06F40/10 ,  G06K9/46

Abstract: In implementations of generating descriptions of image relationships, a computing device implements a description system which receives a source digital image and a target digital image. The description system generates a source feature sequence from the source digital image and a target feature sequence from the target digital image. A visual relationship between the source digital image and the target digital image is determined by using cross-attention between the source feature sequence and the target feature sequence. The system generates a description of a visual transformation between the source digital image and the target digital image based on the visual relationship.

公开(公告)号：US20210279622A1

公开(公告)日：2021-09-09

申请号：US16813098

申请日：2020-03-09

Applicant: ADOBE INC.

Inventor： Trung Huu Bui ,  Tong Sun ,  Natwar Modani ,  Lidan Wang ,  Franck Dernoncourt

IPC: G06N7/00 ,  G06N20/00 ,  G06F40/205 ,  G06F40/279 ,  G06F40/30

Abstract: Methods for natural language semantic matching performed by training and using a Markov Network model are provided. The trained Markov Network model can be used to identify answers to questions. Training may be performed using question-answer pairs that include labels indicating a correct or incorrect answer to a question. The trained Markov Network model can be used to identify answers to questions from sources stored on a database. The Markov Network model provides superior performance over other semantic matching models, in particular, where the training data set includes a different information domain type relative to the input question or the output answer of the trained Markov Network model.

公开(公告)号：US11113323B2

公开(公告)日：2021-09-07

申请号：US16420764

申请日：2019-05-23

Applicant: ADOBE INC.

Inventor： Seung-hyun Yoon ,  Franck Dernoncourt ,  Trung Huu Bui ,  Doo Soon Kim ,  Carl Iwan Dockhorn ,  Yu Gong

IPC: G06F7/00 ,  G06F16/332 ,  G06N20/00 ,  G06F16/33

Abstract: Embodiments of the present invention provide systems, methods, and computer storage media for techniques for identifying textual similarity and performing answer selection. A textual-similarity computing model can use a pre-trained language model to generate vector representations of a question and a candidate answer from a target corpus. The target corpus can be clustered into latent topics (or other latent groupings), and probabilities of a question or candidate answer being in each of the latent topics can be calculated and condensed (e.g., downsampled) to improve performance and focus on the most relevant topics. The condensed probabilities can be aggregated and combined with a downstream vector representation of the question (or answer) so the model can use focused topical and other categorical information as auxiliary information in a similarity computation. In training, transfer learning may be applied from a large-scale corpus, and the conventional list-wise approach can be replaced with point-wise learning.

公开(公告)号：US20200349464A1

公开(公告)日：2020-11-05

申请号：US16401548

申请日：2019-05-02

Applicant: Adobe Inc.

Inventor： Zhe Lin ,  Trung Huu Bui ,  Scott Cohen ,  Mingyang Ling ,  Chenyun Wu

IPC: G06N20/00

Abstract: Techniques and systems are provided for training a machine learning model using different datasets to perform one or more tasks. The machine learning model can include a first sub-module configured to perform a first task and a second sub-module configured to perform a second task. The first sub-module can be selected for training using a first training dataset based on a format of the first training dataset. The first sub-module can then be trained using the first training dataset to perform the first task. The second sub-module can be selected for training using a second training dataset based on a format of the second training dataset. The second sub-module can then be trained using the second training dataset to perform the second task.

公开(公告)号：US10453455B2

公开(公告)日：2019-10-22

申请号：US15820874

申请日：2017-11-22

Applicant: Adobe Inc.

Inventor： Ramesh Radhakrishna Manuvinakurike ,  Trung Huu Bui ,  Walter W. Chang

IPC: G10L15/22 ,  G10L25/57 ,  G10L15/26 ,  G10L15/06 ,  G10L25/87 ,  G10L15/04 ,  G06F3/16 ,  G10L25/78

Abstract: A technique for multiple turn conversational task assistance includes receiving data representing a conversation between a user and an agent. The conversation includes a digitally recorded video portion and a digitally recorded audio portion, where the audio portion corresponds to the video portion. Next, the audio portion is segmented into a plurality of audio chunks. For each of the audio chunks, a transcript of the respective audio chunk is received. Each of the audio chunks is grouped into one or more dialog acts, where each dialog act includes at least one of the respective audio chunks, the validated transcript corresponds to the respective audio chunks, and a portion of the video portion corresponds to the respective audio chunk. Each of the dialog acts is stored in a data corpus.

公开(公告)号：US10334202B1

公开(公告)日：2019-06-25

申请号：US15907497

申请日：2018-02-28

Applicant: Adobe Inc.

Inventor： Yipin Zhou ,  Zhaowen Wang ,  Chen Fang ,  Trung Huu Bui

IPC: H04N5/60 ,  G06N3/04 ,  G06N3/08

Abstract: Techniques are disclosed for generating audio based on visual information. In some examples, an audio generation system is trained using supervised learning using a training set generated from videos. The trained audio generation system is able to infer audio for provided silent video based on the visual contents of the silent video, and generate raw waveform samples that represent the inferred audio.

公开(公告)号：US12242820B2

公开(公告)日：2025-03-04

申请号：US17651555

申请日：2022-02-17

Applicant: Adobe Inc.

Inventor： Cesa Salaam ,  Seunghyun Yoon ,  Trung Huu Bui ,  Franck Dernoncourt

IPC: G10L15/22 ,  G06F40/47 ,  G06F40/58 ,  G06N3/045 ,  G06N3/08

Abstract: Techniques for training a language model for code switching content are disclosed. Such techniques include, in some embodiments, generating a dataset, which includes identifying one or more portions within textual content in a first language, the identified one or more portions each including one or more of offensive content or non-offensive content; translating the identified one or more salient portions to a second language; and reintegrating the translated one or more portions into the textual content to generate code-switched textual content. In some cases, the textual content in the first language includes offensive content and non-offensive content, the identified one or more portions include the offensive content, and the translated one or more portions include a translated version of the offensive content. In some embodiments, the code-switched textual content is at least part of a synthetic dataset usable to train a language model, such as a multilingual classification model.

公开(公告)号：US12210825B2

公开(公告)日：2025-01-28

申请号：US17455533

申请日：2021-11-18

Applicant: ADOBE INC.

Inventor： Jaemin Cho ,  Seunghyun Yoon ,  Ajinkya Gorakhnath Kale ,  Trung Huu Bui ,  Franck Dernoncourt

IPC: G06F40/253 ,  G06F16/583 ,  G06F18/21 ,  G06F18/214 ,  G06K9/62

Abstract: Systems and methods for image captioning are described. One or more aspects of the systems and methods include generating a training caption for a training image using an image captioning network; encoding the training caption using a multi-modal encoder to obtain an encoded training caption; encoding the training image using the multi-modal encoder to obtain an encoded training image; computing a reward function based on the encoded training caption and the encoded training image; and updating parameters of the image captioning network based on the reward function.

公开(公告)号：US12182524B2

公开(公告)日：2024-12-31

申请号：US17453562

申请日：2021-11-04

Applicant: ADOBE INC.

Inventor： Jianguo Zhang ,  Trung Huu Bui ,  Seunghyun Yoon ,  Xiang Chen ,  Quan Hung Tran ,  Walter W. Chang

IPC: G06F40/40 ,  G06F40/284 ,  G06F40/30 ,  G06V30/19

Abstract: Systems and methods for natural language processing are described. One or more aspects of a method, apparatus, and non-transitory computer readable medium include receiving a text phrase; encoding the text phrase using an encoder to obtain a hidden representation of the text phrase, wherein the encoder is trained during a first training phrase using self-supervised learning based on a first contrastive loss and during a second training phrase using supervised learning based on a second contrastive learning loss; identifying an intent of the text phrase from a predetermined set of intent labels using a classification network, wherein the classification network is jointly trained with the encoder in the second training phase; and generating a response to the text phrase based on the intent.

公开(公告)号：US12147771B2

公开(公告)日：2024-11-19

申请号：US17361878

申请日：2021-06-29

Applicant: ADOBE INC.

Inventor： Sangwoo Cho ,  Franck Dernoncourt ,  Timothy Jeewun Ganter ,  Trung Huu Bui ,  Nedim Lipka ,  Varun Manjunatha ,  Walter Chang ,  Hailin Jin ,  Jonathan Brandt

IPC: G06F40/35 ,  G06F40/279

Abstract: System and methods for a text summarization system are described. In one example, a text summarization system receives an input utterance and determines whether the utterance should be included in a summary of the text. The text summarization system includes an embedding network, a convolution network, an encoding component, and a summary component. The embedding network generates a semantic embedding of an utterance. The convolution network generates a plurality of feature vectors based on the semantic embedding. The encoding component identifies a plurality of latent codes respectively corresponding to the plurality of feature vectors. The summary component identifies a prominent code among the latent codes and to select the utterance as a summary utterance based on the prominent code.