-
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
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.
-
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
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.
-
Patent Agency Ranking
公开(公告)号：US12243292B2
公开(公告)日：2025-03-04
申请号：US17929449
申请日：2022-09-02
Applicant: Lemon Inc.
Inventor： Shuo Cheng , Wanchun Ma , Linjie Luo
IPC: G06K9/62 , G06N3/0455 , G06N3/09 , G06V10/44 , G06V10/764 , G06V10/766 , G06V10/774 , G06V10/776 , G06V10/778 , G06V10/82 , G06V10/96 , G06V40/16
Abstract: Systems and methods for multi-task joint training of a neural network including an encoder module and a multi-headed attention mechanism are provided. In one aspect, the system includes a processor configured to receive input data including a first set of labels and a second set of labels. Using the encoder module, features are extracted from the input data. Using a multi-headed attention mechanism, training loss metrics are computed. A first training loss metric is computed using the extracted features and the first set of labels, and a second training loss metric is computed using the extracted features and the second set of labels. A first mask is applied to filter the first training loss metric, and a second mask is applied to filter the second training loss metric. A final training loss metric is computed based on the filtered first and second training loss metrics.
-
公开(公告)号：US12112573B2
公开(公告)日：2024-10-08
申请号：US17402344
申请日：2021-08-13
Applicant: Lemon Inc.
Inventor： Michael Leong Hou Tay , Wanchun Ma , Shuo Cheng , Chao Wang , Linjie Luo
CPC classification number: G06V40/176 , G06F18/2193 , G06T7/251 , G06T13/40 , G06T13/80 , G06V10/242 , G06V40/171 , G06T2207/20084 , G06T2207/30201
Abstract: The present disclosure describes techniques for facial expression recognition. A first loss function may be determined based on a first set of feature vectors associated with a first set of images depicting facial expressions and a first set of labels indicative of the facial expressions. A second loss function may be determined based on a second set of feature vectors associated with a second set of images depicting asymmetric facial expressions and a second set of labels indicative of the asymmetric facial expressions. The first loss function and the second loss function may be used to determine a maximum loss function. The maximum loss function may be applied during training of a model. The trained model may be configured to predict at least one asymmetric facial expression in a subsequently received image.
-
公开(公告)号：US20240078792A1
公开(公告)日：2024-03-07
申请号：US17929449
申请日：2022-09-02
Applicant: Lemon Inc.
Inventor： Shuo Cheng , Wanchun Ma , Linjie Luo
IPC: G06V10/774 , G06V10/764 , G06V10/776 , G06V10/82 , G06V10/96 , G06V40/16
CPC classification number: G06V10/774 , G06V10/764 , G06V10/776 , G06V10/82 , G06V10/96 , G06V40/171 , G06V40/174
Abstract: Systems and methods for multi-task joint training of a neural network including an encoder module and a multi-headed attention mechanism are provided. In one aspect, the system includes a processor configured to receive input data including a first set of labels and a second set of labels. Using the encoder module, features are extracted from the input data. Using a multi-headed attention mechanism, training loss metrics are computed. A first training loss metric is computed using the extracted features and the first set of labels, and a second training loss metric is computed using the extracted features and the second set of labels. A first mask is applied to filter the first training loss metric, and a second mask is applied to filter the second training loss metric. A final training loss metric is computed based on the filtered first and second training loss metrics.
-
公开(公告)号：US11803996B2
公开(公告)日：2023-10-31
申请号：US17390440
申请日：2021-07-30
Applicant: Lemon Inc.
Inventor： Wanchun Ma , Shuo Cheng , Chao Wang , Michael Leong Hou Tay , Linjie Luo
CPC classification number: G06T13/40 , G06N3/08 , G06V40/162 , G06V40/171 , G06V40/176
Abstract: Techniques for face tracking comprise receiving landmark data associated with a plurality of images indicative of at least one facial part. Representative images corresponding to the plurality of images may be generated based on the landmark data. Each representative image may depict a plurality of segments, and each segment may correspond to a region of the at least one facial part. The plurality of images and corresponding representative images may be input into a neural network to train the neural network to predict a feature associated with a subsequently received image comprising a face. An animation associated with a facial expression may be controlled based on output from the trained neural network.
-
公开(公告)号：US20230046286A1
公开(公告)日：2023-02-16
申请号：US17402344
申请日：2021-08-13
Applicant: Lemon Inc.
Inventor： Michael Leong Hou Tay , Wanchun Ma , Shuo Cheng , Chao Wang , Linjie Luo
Abstract: The present disclosure describes techniques for facial expression recognition. A first loss function may be determined based on a first set of feature vectors associated with a first set of images depicting facial expressions and a first set of labels indicative of the facial expressions. A second loss function may be determined based on a second set of feature vectors associated with a second set of images depicting asymmetric facial expressions and a second set of labels indicative of the asymmetric facial expressions. The first loss function and the second loss function may be used to determine a maximum loss function. The maximum loss function may be applied during training of a model. The trained model may be configured to predict at least one asymmetric facial expression in a subsequently received image.
-
-
-
-
-
-
Search Results
7
records
(took 0.016 seconds)
