中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

12 records (took 0.025 seconds)

    BOX DETECTION FOR OBJECT ATTACHMENT
    1.
    发明公开
    BOX DETECTION FOR OBJECT ATTACHMENT 审中-公开

    公开(公告)号：US20230252752A1

    公开(公告)日：2023-08-10

    申请号：US17666045

    申请日：2022-02-07

    Applicant: Lemon Inc.

    Inventor： Shuo Cheng ,  Peng Wang

    IPC: G06V10/25 ,  G06T7/50 ,  G06T7/70 ,  G06N3/04

    CPC classification number: G06V10/25 ,  G06N3/0454 ,  G06T7/50 ,  G06T7/70 ,  G06T2207/20076

    Abstract: The present disclosure describes techniques for determining a bounding box. An image may be received. An X-frame, a Y-frame, and a normal frame may be estimated based on the image using a first neural network. At least one planar region may be detected from the image using a second neural network. A vanishing point detection may be performed on each of the at least one planar region. Output of the first neural network may be fused with results of the vanishing point detection. A depth value of each pixel in at least one plane corresponding to the at least one planar region may be determined based at least in part on a result of the fusing. A location of a bounding box may be determined based at least in part on the depth value of each pixel in the at least one plane.

    Dual-level model for segmentation
    3.
    发明授权
    Dual-level model for segmentation 有权

    公开(公告)号：US12254631B2

    公开(公告)日：2025-03-18

    申请号：US17585301

    申请日：2022-01-26

    Applicant: Lemon Inc.

    Inventor： Peng Wang ,  Xueqing Deng ,  Xiaochen Lian

    IPC: G06T7/11 ,  G06T3/40

    Abstract: The techniques for dual-level semantic segmentation are provided. Data may be input to a first segmentation network. The input data comprises an image and label information associated with the image. The image may be captured at nighttime and may comprise a plurality of regions. At least one region among the plurality of regions may be determined based at least in part on output of the first segmentation network. The at least one region of the image may be cropped. The cropped at least one region may be input to a second segmentation network. A final output may be produced based on the output of the first segmentation network and output of the second segmentation network.

    Lightweight transformer for high resolution images
    4.
    发明授权
    Lightweight transformer for high resolution images 有权

    公开(公告)号：US11983239B2

    公开(公告)日：2024-05-14

    申请号：US17342483

    申请日：2021-06-08

    Applicant: Lemon Inc.

    Inventor： Xiaochen Lian ,  Mingyu Ding ,  Linjie Yang ,  Peng Wang ,  Xiaojie Jin

    IPC: G06V20/56 ,  G06F18/213 ,  G06F18/24 ,  G06N3/04 ,  G06N3/08 ,  G06V10/32 ,  G06V10/82

    CPC classification number: G06F18/213 ,  G06F18/24 ,  G06N3/04 ,  G06N3/08 ,  G06V10/82

    Abstract: Systems and methods for obtaining attention features are described. Some examples may include: receiving, at a projector of a transformer, a plurality of tokens associated with image features of a first dimensional space; generating, at the projector of the transformer, projected features by concatenating the plurality of tokens with a positional map, the projected features having a second dimensional space that is less than the first dimensional space; receiving, at an encoder of the transformer, the projected features and generating encoded representations of the projected features using self-attention; decoding, at a decoder of the transformer, the encoded representations and obtaining a decoded output; and projecting the decoded output to the first dimensional space and adding the image features of the first dimensional space to obtain attention features associated with the image features.

    Box detection for object attachment
    5.
    发明授权
    Box detection for object attachment 有权

    公开(公告)号：US12190554B2

    公开(公告)日：2025-01-07

    申请号：US17666045

    申请日：2022-02-07

    Applicant: Lemon Inc.

    Inventor： Shuo Cheng ,  Peng Wang

    IPC: G06V10/25 ,  G06N3/045 ,  G06T7/50 ,  G06T7/70

    Abstract: The present disclosure describes techniques for determining a bounding box. An image may be received. An X-frame, a Y-frame, and a normal frame may be estimated based on the image using a first neural network. At least one planar region may be detected from the image using a second neural network. A vanishing point detection may be performed on each of the at least one planar region. Output of the first neural network may be fused with results of the vanishing point detection. A depth value of each pixel in at least one plane corresponding to the at least one planar region may be determined based at least in part on a result of the fusing. A location of a bounding box may be determined based at least in part on the depth value of each pixel in the at least one plane.

    DUAL-LEVEL MODEL FOR SEGMENTATION
    7.
    发明公开
    DUAL-LEVEL MODEL FOR SEGMENTATION 审中-公开

    公开(公告)号：US20230237662A1

    公开(公告)日：2023-07-27

    申请号：US17585301

    申请日：2022-01-26

    Applicant: Lemon Inc.

    Inventor： Peng Wang ,  Xueqing Deng ,  Xiaochen Lian

    IPC: G06T7/11 ,  G06T3/40

    CPC classification number: G06T7/11 ,  G06T3/40 ,  G06T2207/20132 ,  G06T2207/20084

    Abstract: The present disclosure describes techniques for dual-level semantic segmentation. Data may be input to a first segmentation network. The input data comprises an image and label information associated with the image. The image may be captured at nighttime and may comprise a plurality of regions. At least one region among the plurality of regions may be determined based at least in part on output of the first segmentation network. The at least one region of the image may be cropped. The cropped at least one region may be input to a second segmentation network. A final output may be produced based on the output of the first segmentation network and output of the second segmentation network.

    EFFICIENT VIDEO PROCESSING VIA TEMPORAL PROGRESSIVE LEARNING
    8.
    发明公开
    EFFICIENT VIDEO PROCESSING VIA TEMPORAL PROGRESSIVE LEARNING 审中-公开

    公开(公告)号：US20230206067A1

    公开(公告)日：2023-06-29

    申请号：US18111756

    申请日：2023-02-20

    Applicant: Lemon Inc.

    Inventor： Peng Wang ,  Heng Wang ,  Xianhang Li ,  Xinyu Li

    IPC: G06N3/08 ,  G06N3/0455 ,  G06V10/75 ,  G06V10/771 ,  G06V10/77 ,  G06V10/82 ,  G06V20/40

    CPC classification number: G06N3/08 ,  G06N3/0455 ,  G06V10/751 ,  G06V10/771 ,  G06V10/7715 ,  G06V10/82 ,  G06V20/46

    Abstract: Systems and methods for performing temporal progressive learning for video processing are provided herein. Some examples include receiving a video that includes a plurality of frames, extracting a first subset of frames from the plurality of frames, and inputting the first subset of frames into a model that includes an encoder and a decoder. The examples further include comparing a first output of the model to the first subset of frames and updating the encoder, thereby training the encoder, and extracting a second subset of frames from the plurality of frames. The second subset of frames includes a number of frames that is larger than a number of frames in the first subset of frames. The examples further include inputting the second subset of frames into the model, comparing a second output of the model to the second subset of frames and updating the encoder, thereby further training the encoder.

    OPTIMAL KNOWLEDGE DISTILLATION SCHEME
    10.
    发明公开
    OPTIMAL KNOWLEDGE DISTILLATION SCHEME 审中-公开

    公开(公告)号：US20230196067A1

    公开(公告)日：2023-06-22

    申请号：US17554656

    申请日：2021-12-17

    Applicant: Lemon Inc.

    Inventor： Peng Wang ,  Dawei Sun ,  Xiaochen Lian

    IPC: G06N3/04 ,  G06V10/776

    CPC classification number: G06N3/0427 ,  G06N3/0454 ,  G06V10/776

    Abstract: The present disclosure describes techniques of identifying optimal scheme of knowledge distillation (KD) for vision tasks. The techniques comprise configuring a search space by establishing a plurality of pathways between a teacher network and a student network and assigning an importance factor to each of the plurality of pathways; searching the optimal KD scheme by updating the importance factor and parameters of the student network during a process of training the student network; and performing KD from the teacher network to the student network by retraining the student network based at least in part on the optimized importance factors.

Patent Agency Ranking