Patents by Inventor Xiang Long
Xiang Long has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Publication number: 20240249555Abstract: A method for detecting a human behavior includes: obtaining an image to be detected; obtaining a plurality of key points and a plurality of pieces of position information respectively corresponding to the plurality of key points by key-point recognition on the image to be detected; grouping the plurality of key points based on the plurality of pieces of position information to obtain a plurality of key-point groups, the plurality of key-point groups at least including a part of the plurality of key points; and determining a target human behavior based on key points in the plurality of key-point groups.Type: ApplicationFiled: April 20, 2022Publication date: July 25, 2024Applicant: BEIJING BAIDU NETCOM SCIENCE TECHNOLOGY CO., LTD.Inventors: Song Xue, Yuan Feng, Ying Xin, Bin Zhang, Chao Li, Xiaodi Wang, Yunhao Wang, Yi Gu, Xiang Long, Honghui Zheng, Yan Peng, Zhuang Jia, Shumin Han
-
Publication number: 20240193923Abstract: A method of training a target object detection model includes: extracting a plurality of feature maps of a sample image according to a training parameter, fusing the plurality of feature maps to obtain at least one fused feature map, and obtaining an information of a target object based on the at least one fused feature map, by using the target object detection model; determining a loss of the target object detection model based on the information of the target object and a tag information of the sample image, and adjusting the training parameter according to the loss of the target object detection model. A method of detecting a target object and an apparatus are also provided.Type: ApplicationFiled: January 29, 2022Publication date: June 13, 2024Inventors: Xiaodi WANG, Shumin HAN, Yuan FENG, Ying XIN, Yi GU, Bin ZHANG, Chao LI, Xiang LONG, Honghui ZHENG, Yan PENG, Zhuang JIA, Yunhao WANG
-
Patent number: 11921276Abstract: Provided are a method and apparatus for evaluating image relative definition, a device and a medium, relating to technologies such as computer vision, deep learning and intelligent medical. A specific implementation solution is: extracting a multi-scale feature of each image in an image set, where the multi-scale feature is used for representing definition features of objects having different sizes in an image; and scoring relative definition of each image in the image set according to the multi-scale feature by using a relative definition scoring model pre-trained, where the purpose for training the relative definition scoring model is to learn a feature related to image definition in the multi-scale feature.Type: GrantFiled: July 19, 2021Date of Patent: March 5, 2024Assignee: Beijing Baidu Netcom Science and Technology Co., Ltd.Inventors: Xiang Long, Yan Peng, Shufei Lin, Ying Xin, Bin Zhang, Pengcheng Yuan, Xiaodi Wang, Yuan Feng, Shumin Han
-
Patent number: 11893708Abstract: Provided are an image processing method and apparatus, a device, and a storage medium, relating to the technical field of image processing, in particular to the artificial intelligence fields such as computer vision and deep learning. The specific implementation scheme is as follows: inputting a to-be-processed image into an encoding network to obtain a basic image feature, wherein the encoding network includes at least two cascaded overlapping encoding sub-networks which perform encoding and fusion processing on input data at at least two resolutions; and inputting the basic image feature into a decoding network to obtain a target image feature for pixel point classification, wherein the decoding network includes at least one cascaded overlapping decoding sub-network to perform decoding and fusion processing on input data at at least two resolutions respectively.Type: GrantFiled: October 20, 2021Date of Patent: February 6, 2024Assignee: Beijing Baidu Netcom Science Technology Co., Ltd.Inventors: Jian Wang, Xiang Long, Hao Sun, Zhiyong Jin, Errui Ding
-
Patent number: 11734809Abstract: Embodiments of the present disclosure provide a method and apparatus for processing an image, and relates to the field of computer vision technology. The method may include: acquiring a value to be processed, where the value to be processed is associated with an image to be processed; and processing the value to be processed by using a quality scoring model to generate a score of the image to be processed in a target scoring domain, where the score of the image to be processed in the target scoring domain is related to an image quality of the image to be processed.Type: GrantFiled: February 11, 2021Date of Patent: August 22, 2023Assignee: BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY CO., LTD.Inventors: Xiang Long, Ping Wang, Zhichao Zhou, Fu Li, Dongliang He, Hao Sun
-
Patent number: 11669990Abstract: An object area measurement method and an apparatus are provided, relating to the computer vision and deep learning technology. The method includes acquiring an original image with a spatial resolution, the original image including a target object; acquiring an object identification model including at least two sets of classification models; generating one or more original image blocks based on the original image; performing operations on each original image block: scaling each original image block at at least two scaling levels to obtain scaled image blocks with at least two sizes, the scaled image blocks respectively corresponding to the at least two sets of classification models, and inputting the scaled image blocks into the object identification model to obtain an identification result of the target object; and determining an area of the target object based on the respective identification results of the one or more original image blocks and the spatial resolution.Type: GrantFiled: August 26, 2021Date of Patent: June 6, 2023Assignee: BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY CO., LTD.Inventors: Yan Peng, Xiang Long, Shumin Han, Honghui Zheng, Zhuang Jia, Xiaodi Wang, Pengcheng Yuan, Yuan Feng, Bin Zhang, Ying Xin
-
Publication number: 20230153387Abstract: A training method for a human body attribute detection model includes: acquiring positive sample sub-images and negative sample sub-images respectively corresponding to a plurality of human body attribute categories; determining a plurality of first annotation attributes respectively corresponding to the plurality of positive sample sub-images; and a plurality of second annotation attributes respectively corresponding to the plurality of negative sample sub-images; and training an artificial intelligence model according to the plurality of positive sample sub-images, the plurality of negative sample sub-images, the plurality of first annotation attributes and the plurality of second annotation attributes to obtain the human body attribute detection model, so that the human body attribute detection model obtained by training can effectively model fine-grained attributes of the human body.Type: ApplicationFiled: January 6, 2023Publication date: May 18, 2023Applicant: BEIJING BAIDU NETCOM SCIENCE TECHNOLOGY CO., LTD.Inventors: Chao Li, Ying Xin, Yuan Feng, Bin Zhang, Yunhao Wang, Xiaodi Wang, Yi Gu, Xiang Long, Yan Peng, Honghui Zheng, Zhuang Jia, Shumin Han
-
Publication number: 20230154163Abstract: A method for recognizing a category of an image includes: acquiring a spectral image; training an image recognition model based on the spectral image, in which the image recognition model acquires a spectral semantic feature of each pixel, a minimum distance between each pixel and each category, and a spectral distance between a first spectrum of each pixel and a second spectrum of each category; splices them; and performs classification and recognition based on the spliced feature to output a recognition probability of each pixel under each category; determining a loss function of the image recognition model, adjusting the image recognition model based on the loss function, and returning to training the adjusted image recognition model based on the spectral image until training ends; recognizing a maximum recognition probability, output from a target image recognition model, and using a category corresponding to the maximum recognition probability as a target category.Type: ApplicationFiled: January 6, 2023Publication date: May 18, 2023Applicant: BEIJING BAIDU NETCOM SCIENCE TECHNOLOGY CO., LTD.Inventors: Zhuang Jia, Xiang Long, Yan Peng, Honghui Zheng, Bin Zhang, Yunhao Wang, Ying Xin, Chao Li, Xiaodi Wang, Song Xue, Yuan Feng, Shumin Han
-
Patent number: 11625433Abstract: Embodiments of the present disclosure disclose a method and apparatus for searching a video segment, a device and a medium, and relate to the field of video data search. The method includes: sampling video frames from a target video and videos to be searched in a video library, and extracting features from the sampled frames; matching the target video and the videos to be searched according to the extracted features to determine a candidate video to be searched that matches the target video; determining at least one candidate video segment from the determined candidate video, and calculating a degree of matching between the target video and each candidate video segment based on the extracted features of each sampled frame; and determining a video segment matching the target video in the videos to be searched according to the calculated degree of matching between the target video and each candidate video segment.Type: GrantFiled: February 23, 2021Date of Patent: April 11, 2023Assignee: Beijing Baidu Netcom Science and Technology Co., Ltd.Inventors: Xiang Long, Ping Wang, Fu Li, Dongliang He, Hao Sun, Shilei Wen
-
Patent number: 11615140Abstract: A method includes screening, by a video-clip screening module in a video description model, a plurality of video proposal clips acquired from a video to be analyzed, to acquire a plurality of video clips suitable for description. The plural video proposal clips acquired from the video to be analyzed may be screened by the video-clip screening module to acquire the plural video clips suitable for description; and then, each video clip is described by a video-clip describing module, thus avoiding description of all the video proposal clips, only describing the screened video clips which have strong correlation with the video and are suitable for description, removing the interference of the description of the video clips which are not suitable for description in the description of the video, guaranteeing the accuracy of the final descriptions of the video clips, and improving the quality of the descriptions of the video clips.Type: GrantFiled: January 8, 2021Date of Patent: March 28, 2023Assignee: BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY CO., LTD.Inventors: Xiang Long, Dongliang He, Fu Li, Xiang Zhao, Tianwei Lin, Hao Sun, Shilei Wen, Errui Ding
-
Publication number: 20230068025Abstract: A method for generating a road annotation, a device, and a storage medium are provided. The method may include: generating a road quantity and a road width in a tag picture; generating, for each road in the tag picture, a start point and an end point of the road; generating at least one point between the start point and the end point; drawing, for two adjacent points, a line segment from a previous point to a next point, where a width of the line segment is equal to the road width; and generating slanted box annotation information based on a coordinate of the previous point and a coordinate of the next point, where the slanted box annotation information includes an intersection point of diagonal lines, a width, a height and a slant angle of a slanted box.Type: ApplicationFiled: November 7, 2022Publication date: March 2, 2023Inventors: Yan PENG, Xiang LONG, Honghui ZHENG, Zhuang JIA, Bin ZHANG, Xiaodi WANG, Ying XIN, Yi GU, Yunhao WANG, Chao LI, Yuan FENG, Shumin HAN
-
Patent number: 11552326Abstract: The invention relates to a button lithium ion battery, a preparation method thereof, and a method of producing a lithium ion cell composite flat sheet, wherein the button lithium ion battery comprises a battery housing, a cell accommodated in the battery housing and an electrolyte filled in the battery housing; the cell is formed by winding a composite flat sheet in which a first separator, a positive piece, a second separator and a negative piece are sequentially stacked and hot-laminated to form an integrated structure. The cell of the button lithium ion battery is formed by winding a composite flat sheet, so that winding efficiency can be improved, and misalignment can be avoided; moreover, chances of hand contact can be reduced, the influence of dust and water vapor can be avoided, and the quality of the lithium battery can be improved to the maximum extent.Type: GrantFiled: June 28, 2020Date of Patent: January 10, 2023Assignees: BetterPower Battery Co., Ltd., Jiangxi BetterPower New Energy Co., Ltd.Inventors: Huijun Yuan, Guomin Zhang, Xiang Long, Haitao Dang, Aijun Jian, Xiaolin Wang, Yin Zhang
-
Publication number: 20220391587Abstract: A method of training an image-text retrieval model, a method of multimodal image retrieval, an electronic device and a storage medium, each relating to the technical field of artificial intelligence, and in particular, to fields of computer vision and deep learning technologies. Sample data including a sample text and a sample image is acquired. The sample text includes a sample text in a first language and a sample text in a second language. The sample text in the first language and the sample text in the second language are processed by using the text encoding sub-model to obtain a sample text feature of the sample data. The sample image is processed by using the image encoding sub-model to obtain a sample image feature of the sample data. The image-text retrieval model is trained according to the sample text feature and the sample image feature.Type: ApplicationFiled: August 16, 2022Publication date: December 8, 2022Applicant: BEIJING BAIDU NETCOM SCIENCE TECHNOLOGY CO., LTD.Inventors: Yuan Feng, Xiang Long, Honghui Zheng, Ying Xin, Bin Zhang, Chao Li, Xiaodi Wang, Yi Gu, Yunhao Wang, Yan Peng, Zhuang Jia, Shumin Han
-
Patent number: 11456479Abstract: A battery proofed against short circuiting, for better safety, includes a battery cell and a first set of electrode tabs. The battery cell includes a first electrode plate and a second electrode plate. The first set of electrode tabs is electrically connected to the first electrode plate. The first set of electrode tabs includes a first bending portion, an edge of the second electrode plate defines a first receiving groove, and the first receiving groove corresponds to the first bending portion.Type: GrantFiled: July 23, 2019Date of Patent: September 27, 2022Assignee: DONGGUAN POWERAMP TECHNOLOGY LIMITEDInventors: Xiang-Long Han, Tao Tao
-
Patent number: 11455765Abstract: A method and apparatus for generating a virtual avatar are provided. The method may include: acquiring a first avatar, and determining an expression parameter of the first avatar, where the expression parameter of the first avatar including an expression parameter of at least one of five sense organs; and determining, based on the expression parameter of at least one of the five sense organs, a target virtual avatar that is associated with an attribute of the first avatar and has an expression of the first avatar.Type: GrantFiled: February 23, 2021Date of Patent: September 27, 2022Assignee: Beijing Baidu Netcom Science and Technology Co., Ltd.Inventors: Xiang Long, Xin Li, Henan Zhang, Hao Sun
-
Publication number: 20220301131Abstract: A method for generating a sample image includes: obtaining an initial image size of an initial image; obtaining a plurality of reference images by processing the initial image based on different reference processing modes; obtaining an image to be processed by fusing the plurality of reference images; and determining a target sample image from images to be processed based on the initial image size.Type: ApplicationFiled: May 12, 2022Publication date: September 22, 2022Inventors: Jingwei LIU, Yi GU, Xuhui LIU, Xiaodi WANG, Shumin HAN, Yuan FENG, Ying XIN, Chao LI, Bin ZHANG, Honghui ZHENG, Xiang LONG, Yan PENG, Errui DING, Yunhao WANG
-
Patent number: 11430265Abstract: The present application discloses a video-based human behavior recognition method, apparatus, device and storage medium, and relates to the technical field of human recognitions. The specific implementation scheme lies in: acquiring a human rectangle of each video frame of the video to be recognized, where each human rectangle includes a plurality of human key points, and each of the human key points has a key point feature; constructing a feature matrix according to the human rectangle of the each video frame; convolving the feature matrix with respect to a video frame quantity dimension to obtain a first convolution result and convolving the feature matrix with respect to a key point quantity dimension to obtain a second convolution result; inputting the first convolution result and the second convolution result into a preset classification model to obtain a human behavior category of the video to be recognized.Type: GrantFiled: September 16, 2020Date of Patent: August 30, 2022Inventors: Zhizhen Chi, Fu Li, Hao Sun, Dongliang He, Xiang Long, Zhichao Zhou, Ping Wang, Shilei Wen, Errui Ding
-
Patent number: 11401186Abstract: The present disclosure provides an urban river channel direct purification device. The device includes a support wall panel arranged vertically, an upper tray and a lower tray arranged horizontally, an upper end of the support wall panel is connected with the upper tray, a lower end of the support wall panel is connected with the lower tray, the upper tray and the lower tray are respectively semi-circular, several filler biological walls are disposed between the upper tray and the lower tray, a top end of each filler biological wall is fixedly connected with the bottom of the upper tray, a bottom end of each filler biological wall is fixedly connected with the lower tray, and the filler biological wall is arranged along a radial direction of the upper tray/lower tray. The device can purify the water of the river channel through the adsorption material in the device.Type: GrantFiled: May 24, 2019Date of Patent: August 2, 2022Assignee: Shanghai Investigation, Design & Research Institute Co., Ltd.Inventors: Zhaohui Wang, Hao Lu, Xin Zhang, Shaobo Zhu, Xiang Long
-
Publication number: 20220147822Abstract: Provided are a training method and apparatus for a target detection model, a device and a storage medium. The training method is described below. A feature map of a sample image is processed through a classification network of an initial model and a heat map and a classification prediction result of the feature map are obtained, a classification loss value is determined according to the classification prediction result and classification supervision data of the sample image, and a category probability of pixels in the feature map is determined according to the heat map of the feature map and a probability distribution map of the feature map is obtained; the feature map is processed through a regression network of the initial model and a regression prediction result is obtained, and a regression loss value is determined.Type: ApplicationFiled: August 27, 2021Publication date: May 12, 2022Applicant: BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY CO., LTD.Inventors: Ying XIN, Yuan FENG, Guanzhong WANG, Pengcheng YUAN, Bin ZHANG, Xiaodi WANG, Xiang LONG, Yan PENG, Honghui ZHENG, Shumin HAN
-
Publication number: 20220148190Abstract: The disclosure provides a method for detecting a change of a building, an apparatus for detecting a change of a building, an electronic device, a storage medium and a computer program product. The method includes: obtaining a remote-sensing image sequence of a to-be-detected region; obtaining a building probability map corresponding to each remote-sensing image in the remote-sensing image sequence; determining a sub-region located by each building in the to-be-detected region based on the building probability map corresponding to each remote-sensing image; for each building, determining an existence probability of the building in each remote-sensing image based on the sub-region located by the building and the building probability map corresponding to each remote-sensing image; and determining a change condition of the building based on the existence probability of the building in each remote-sensing image.Type: ApplicationFiled: January 19, 2022Publication date: May 12, 2022Inventors: Xiang LONG, Yan PENG, Honghui ZHENG, Zhuang JIA, Bin ZHANG, Xiaodi WANG, Pengcheng YUAN, Ying XIN, Yuan FENG, Shumin HAN