公开(公告)号：US12079731B2

公开(公告)日：2024-09-03

申请号：US17969848

申请日：2022-10-20

Applicant: International Business Machines Corporation

Inventor： Chuang Gan ,  Yang Zhang

IPC: G06V20/40 ,  G06N3/045 ,  G06N3/088 ,  G06V10/764 ,  G06V10/82

CPC classification number: G06N3/088 ,  G06N3/045 ,  G06V10/764 ,  G06V10/82 ,  G06V20/41 ,  G06V20/46 ,  G06V20/48

Abstract: A method (and structure and computer product) for an audiovisual source separation processing, including receiving video data including images of a plurality of sound sources, receiving an optical flow data of the video data, the optical flow data indicating motions of pixels between frames of the video data, and encoding the received video data into video localization data comprising information associating pixels in the frames of video data with different channels of sound.

公开(公告)号：US12051243B2

公开(公告)日：2024-07-30

申请号：US17516119

申请日：2021-11-01

Applicant: International Business Machines Corporation

Inventor： Bo Wu ,  Chuang Gan ,  Zhenfang Chen ,  Dakuo Wang

IPC: G06F40/284 ,  G06F18/21 ,  G06F40/205 ,  G06N3/044 ,  G06N3/045 ,  G06V20/40

CPC classification number: G06V20/41 ,  G06F18/21 ,  G06F40/205 ,  G06F40/284 ,  G06N3/044 ,  G06N3/045 ,  G06V20/46

Abstract: A processor may receive a video including a plurality of video frames in sequence and a question regarding the video. For a video frame in the plurality of video frames, a processor may parse the video frame into objects and relationships between the objects, and create a subgraph of nodes representing objects and edges representing the relationships, where parsing and creating are performed for each video frame in the plurality of video frames, where a plurality of subgraphs can be created. A processor may create a hypergraph connecting subgraphs by learning relationships between the nodes of the subgraphs, where a hyper-edge is created to represent a relationship between at least one node of one subgraph and at least one node of another subgraph in the plurality of subgraphs. A processor may generate an answer to the question based on the hypergraph.

公开(公告)号：US12026613B2

公开(公告)日：2024-07-02

申请号：US16806626

申请日：2020-03-02

Applicant: International Business Machines Corporation

Inventor： Dakuo Wang ,  Ming Tan ,  Chuang Gan ,  Jason Tsay ,  Gregory Bramble

IPC: G06N3/08 ,  G06N3/045 ,  G06N20/20

CPC classification number: G06N3/08 ,  G06N3/045 ,  G06N20/20

Abstract: Techniques regarding transferring learning outcomes across machine learning tasks in automated machine learning systems are provided. For example, one or more embodiments described herein can comprise a system, which can comprise a memory that can store computer executable components. The system can also comprise a processor, operably coupled to the memory, and that can execute the computer executable components stored in the memory. The computer executable components can comprise a transfer learning component that can executes a machine learning task using an existing artificial intelligence model on a sample dataset based on a similarity between the sample dataset and a historical dataset. The existing artificial intelligence model can be generated by automated machine learning and trained on the historical dataset.

公开(公告)号：US20240004443A1

公开(公告)日：2024-01-04

申请号：US17852699

申请日：2022-06-29

Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION

Inventor： Xin Zhang ,  Shun Zhang ,  Shaoze Fan ,  Xiaoxiao Guo ,  Chuang Gan

IPC: G06F1/26 ,  G06N20/00

CPC classification number: G06F1/26 ,  G06N20/00

Abstract: Described aspects include a system for optimizing performance of a functional circuit unit, a method of optimizing performance of a functional circuit unit, and a computer program product. In one embodiment, the system may include a functional circuit unit having an associated cooling device and power converter, one or more sensors for the functional circuit unit, the one or more sensors including a power sensor and a temperature sensor, and a first machine learning model. The first machine learning model may be adapted to receive temperature data and power data from the one or more sensors, and to generate control signals for the cooling device and the power converter to optimize performance of the functional circuit unit.

公开(公告)号：US11741722B2

公开(公告)日：2023-08-29

申请号：US17012463

申请日：2020-09-04

Applicant: International Business Machines Corporation

Inventor： Bo Wu ,  Chuang Gan ,  Yang Zhang ,  Dakuo Wang

IPC: G06V20/58 ,  G06V30/194

CPC classification number: G06V20/584 ,  G06V30/194

Abstract: A vehicle light signal detection and recognition method, system, and computer program product include bounding, using a coarse attention module, one or more regions of an image of an automobile including at least one of a brake light and a signal light generated by automobile signals which include illuminated sections to generate one or more bounded region, removing, using a fine attention module, noise from the one or more bounded regions to generate one or more noise-free bounded regions, and identifying the at least one of the brake light and the signal light from the one or more noise-free bounded regions.

公开(公告)号：US11736423B2

公开(公告)日：2023-08-22

申请号：US17307175

申请日：2021-05-04

Applicant: International Business Machines Corporation

Inventor： Dakuo Wang ,  Mo Yu ,  Chuang Gan ,  Bo Wu

IPC: G06F15/16 ,  H04L51/04 ,  G06F11/30 ,  G06F40/30 ,  G06F18/21

CPC classification number: H04L51/04 ,  G06F11/302 ,  G06F18/2178 ,  G06F40/30

Abstract: Systems, computer-implemented methods, and/or computer program products facilitating a process to identify and respond to a primary electronic message are provided. According to an embodiment, a system can comprise a memory that stores computer executable components and a processor that executes the computer executable components stored in the memory. The computer executable components can include a determination component can determine that a primary electronic message has not received a response electronic message. An analysis component can generate a generated electronic message addressing the informational or emotional content of the primary electronic message. In one or more embodiments, an updating component can update the analytical model based on one or more feedbacks to the generated electronic message, where the analytical model can remain active while being updated. The one or more feedbacks can comprise a feedback from an entity-in-the-loop monitoring outputs of the analytical model including the generated electronic message.

公开(公告)号：US11727686B2

公开(公告)日：2023-08-15

申请号：US17481248

申请日：2021-09-21

Applicant: International Business Machines Corporation

Inventor： Chuang Gan ,  Ming Tan ,  Yang Zhang ,  Dakuo Wang

IPC: G06V20/40 ,  G06N3/08 ,  G06F18/2323 ,  G06F18/2413 ,  G06V10/764 ,  G06V10/82 ,  G06V10/44

CPC classification number: G06V20/41 ,  G06F18/2323 ,  G06F18/24147 ,  G06N3/08 ,  G06V10/454 ,  G06V10/764 ,  G06V10/82 ,  G06V20/44

Abstract: Systems and techniques that facilitate few-shot temporal action localization based on graph convolutional networks are provided. In one or more embodiments, a graph component can generate a graph that models a support set of temporal action classifications. Nodes of the graph can correspond to respective temporal action classifications in the support set. Edges of the graph can correspond to similarities between the respective temporal action classifications. In various embodiments, a convolution component can perform a convolution on the graph, such that the nodes of the graph output respective matching scores indicating levels of match between the respective temporal action classifications and an action to be classified. In various embodiments, an instantiation component can input into the nodes respective input vectors based on a proposed feature vector representing the action to be classified. In various cases, the respective temporal action classifications can correspond to respective example feature vectors, and the respective input vectors can be concatenations of the respective example feature vectors and the proposed feature vector.

公开(公告)号：US11689488B2

公开(公告)日：2023-06-27

申请号：US17313995

申请日：2021-05-06

Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION

Inventor： Ming Tan ,  Haoyu Wang ,  Dakuo Wang ,  Chuang Gan

IPC: H04L51/216 ,  G06F40/30 ,  H04L51/42 ,  G06F40/35

CPC classification number: H04L51/216 ,  G06F40/30 ,  G06F40/35 ,  H04L51/42

Abstract: A deep learning module classifies messages received from a plurality of entities into one or more conversation threads. In response to receiving a subsequent message, the deep learning module determines which of the one or more conversation threads and a new conversation thread is contextually a best fit for the subsequent message. The subsequent message is added to the determined conversation thread.

公开(公告)号：US20230027713A1

公开(公告)日：2023-01-26

申请号：US17381408

申请日：2021-07-21

Applicant: International Business Machines Corporation

Inventor： Bo Wu ,  Chuang Gan ,  Dakuo Wang ,  Zhenfang Chen

IPC: G06N5/04 ,  G06K9/00 ,  G06F40/205 ,  G06F40/284 ,  G06N5/02 ,  G06N20/20

Abstract: Mechanisms are provided for performing artificial intelligence-based video question answering. A video parser parses an input video data sequence to generate situation data structure(s), each situation data structure comprising data elements corresponding to entities, and first relationships between entities, identified by the video parser as present in images of the input video data sequence. First machine learning computer model(s) operate on the situation data structure(s) to predict second relationship(s) between the situation data structure(s). Second machine learning computer model(s) execute on a received input question to predict an executable program to execute to answer the received question. The program is executed on the situation data structure(s) and predicted second relationship(s). An answer to the question is output based on results of executing the program.

公开(公告)号：US11341598B2

公开(公告)日：2022-05-24

申请号：US16894343

申请日：2020-06-05

Applicant: International Business Machines Corporation ,  Rensselaer Polytechnic Institute

Inventor： Ao Liu ,  Sijia Liu ,  Abhishek Bhandwaldar ,  Chuang Gan ,  Lirong Xia ,  Qi Cheng Li

IPC: G06T1/00 ,  G06T5/00 ,  G06T5/20 ,  G06N3/02 ,  G06T5/50

Abstract: Interpretation maps of deep neural networks are provided that use Renyi differential privacy to guarantee the robustness of the interpretation. In one aspect, a method for generating interpretation maps with guaranteed robustness includes: perturbing an original digital image by adding Gaussian noise to the original digital image to obtain m noisy images; providing the m noisy images as input to a deep neural network; interpreting output from the deep neural network to obtain m noisy interpretations corresponding to the m noisy images; thresholding the m noisy interpretations to obtain a top-k of the m noisy interpretations; and averaging the top-k of the m noisy interpretations to produce an interpretation map with certifiable robustness.