95 results about "Search graph" patented technology

The invention provides a target tracking method and system based on a double-domain attention and wavelet enhancement module, and the method comprises the steps: carrying out the preprocessing of a template image and a search image, and inputting a parameter adjustment feature extraction network, respectively extracting features of the template image and the search image in a spatial domain and a channel domain through double-domain attention of a feature extraction network; splicing the template image sequence features and the search image sequence features along channel dimensions, adjusting a self-attention module and a wavelet enhancement module of a feature fusion network by using parameters after splicing, and performing interactive fusion and feature enhancement; and sending the fusion feature into a prediction head to obtain a tracking result. According to the method, the spatial domain features and the channel domain features of the input image sequence are extracted through the double-domain attention, so that the model not only can pay attention to the spatial position of a target, but also can model the importance of channel semantics, double-domain complementary modeling is realized, a target region is positioned more accurately, and target features and noise channels are effectively distinguished.

Disclosed is a network and method for creating and searching a graph in a massively parallel manner. The network includes a plurality of graph storage instances that collectively store a graph formed from a plurality of entities and comprising a vertex for each entity, edges connecting pairs of vertices, and adjacency relations. Each graph storage instance stores a subgraph of the graph and comprises a partition with a non-overlapping vertex set of all the vertices in the respective subgraph, an edge set of all the edges between vertices in the respective vertex set, and the adjacency relations for the edge set and to any edges outside the partition, to which the edge set connects. Each graph storage instance also includes an executor for executing one or more of the actions over the respective subgraph, and an action monitor for supplying actions to the respective executor.

1. The name of the design product: content search module of content display dynamic graphical user interface of electronic device. 2. The use of the design product: an electronic device. 3. The design points of the design product: the claimed part of the graphical user interface. 4. The picture or photo that best shows the design points: the front view. 5. The use of the graphical user interface: for displaying content; the use of the claimed part is to search for content. 6. The human-computer interaction mode of the graphical user interface: in the content search mode, in the order from the front view to the change state view 3, as the user taps, clicks or touches a certain area in the oval search bar at the top of the interface, the content window below the search bar gradually shrinks and blurs, and at the same time the search bar itself moves to the center of the interface and gradually enlarges. 7. Other circumstances that need to be explained: the part depicted by the solid line in the view is the claimed part of the design.

1. Name of the product in this design: Intelligent Question-Answering Search Graphical User Interface for Electronic Devices. 2. Intended use of this design: for use in an electronic device. 3. The key design feature of this product is its graphical user interface. 4. The picture or photo that best illustrates the key design points: Design 1 front view. 5. Design 1 is designated as the basic design. 6. Uses of the graphical user interface: for AI teaching assistant intelligent question answering and search interaction. 7. Description of the changing states of the graphical user interface: In the main view of Design 1, click on any covered area below "Referencing XX materials as references" in the middle of the interface to enter the changing state diagram of Design 1 and view the video content; the interaction method of Design 2 is the same as that of Design 1, so the description is omitted. 8. Other situations requiring explanation: Other explanation: The covered area is the content screen; X represents text content.

The large-scale image search method based on deep hash comprises the following steps: acquiring a query image uploaded by a user and preprocessing the query image to obtain a to-be-searched image; the to-be-searched image is input into a pre-trained image Hash coding model, the image Hash coding model comprises a feature extraction network and a Hash mapping network, and the feature extraction network is constructed based on Vision Transform and is used for carrying out feature extraction on the to-be-searched image to obtain image high-dimensional features; the Hash mapping network is used for performing Hash coding on the image high-dimensional features to obtain search Hash codes; calculating the similarity between the search hash code and the in-library hash code of the inventory image in the image library based on the Hamming distance; and screening the inventory images based on the similarity to obtain a target image and feeding back the target image to the user. The invention provides a deep hash-based large-scale image search method, an image recommendation method, a recommendation system and computer equipment, which have better search performance.

1. The name of the design product: the search for housing part of the house source graphical user interface of the electronic device. 2. The use of the design product: an electronic device. 3. The design points of the design product: in the local part of the graphical user interface. 4. The picture or photo that best indicates the design points: design 1 front view. 5. Design 1 is designated as the basic design. 6. The use of the graphical user interface: used as a house source search graphical user interface as a whole, and the search for housing part is used to search for house sources and display maps and house source related information. The user inputs the housing search information in the search box of design 1-design 4 front view, and the map and list below display the corresponding house source search results and related information according to the search information, such as displaying the search location, nearby communities and the corresponding number of house sources in the map. The user inputs the housing search information in the search box of design 5 front view, and the map and list below display the corresponding house source search results and related information according to the search information, such as displaying the search route and the corresponding number of house sources in the map. The housing search information input by the user in the search box can be a specific location, house source characteristics (such as business district, urban area, price), subway, etc. 7. The present design is a partial design, wherein the blue coated part is not claimed, and the map content displayed in design 1 to design 5 views does not belong to the claimed picture.

The application discloses a target tracking method and device, electronic equipment and storage medium, comprising: acquiring a to-be-detected video sequence and determining an example image and a search image; inputting the example image and the search image into a trained feature extraction network for processing to obtain a first feature map set and a second feature map set; inputting the first feature map set and the second feature map set into a trained twin mutual attention module for processing to obtain a reinforced second feature map set; obtaining regression features according to the first feature map set and the reinforced second feature map set; performing anchor frame regression according to the regression features to obtain the position of a to-be-detected target in the search image, and further determining the position of the to-be-detected target in the to-be-detected video sequence. The application strengthens the features through the twin mutual attention module, applies the information of the to-be-detected target to the extracted features, makes the adaptability of the reinforced second feature map set stronger, and realizes robust, efficient and accurate target tracking.

The system obtains emails sent to a user, an email among the emails, and a sender of the email and determines whether the sender provided an image representing the sender. Upon determining that the sender did not provide the image, the system obtains the image representing the sender. The system identifies a subset of emails, where each email in the subset of emails is from the sender. The system presents in an email interface the subset of emails along with the image representing the sender. The system obtains an indication from the user to change the image, and in response obtains images representing the sender by searching a database of images. The system presents the images to the user and obtains a selected image from the user. The system replaces in the email interface the image representing the sender with the selected image to obtain an updated email interface.

1. The name of the design product: search box of browser graphical user interface for electronic equipment. 2. The use of the design product: for an electronic equipment. 3. The design points of the design product: the interface content expressed by non-dotted line in the graphical user interface. 4. The picture or photo that best shows the design points: design 1 front view. 5. Design 1 is designated as the basic design. 6. The use of the graphical user interface: the whole of the graphical user interface of the design is used for browser, and the part claimed is used for information search. In each design, the user can select the search icon in the interface shown in the front view by clicking or other methods to open the search box. The interface after opening the search box is shown in the change state diagram. The user can input keywords in the search box to search information. The position of the search icon includes but is not limited to the layout shown in the view. 7. Other circumstances that need to be explained: "X" in the interface represents a text, number or symbol area. The design claimed does not include the interface content and interface border expressed by dotted line in each design.

1. The name of the design product: AI helper question and answer graphical user interface for electronic equipment. 2. The use of the design product: an electronic device. 3. The design points of the design product: the graphical user interface content displayed on the screen. 4. The picture or photo that best indicates the design points: front view. 5. No design points, omit rear view, left view, right view, top view, bottom view. 6. The use of the graphical user interface: the figure is used for the user to enter the management page of the AI helper question and answer; the front view displays the homepage of the management page of the main webpage; in the front view, click the search pattern on the right side of the "unified search" field to enter the interface change state figure 1; in the interface change state figure 1, enter any question in the search field and click search to enter the interface change state figure 2; in the interface change state figure 2, click the pattern of the AI helper on the right side of the search field to enter the interface change state figure 3; in the question field below the interface change state figure 3, enter any question and send it to enter the interface change state figure 4; in the interface change state figure 4, click the "history conversation" button on the right side to enter the interface change state figure 5.

A cybersecurity service (“service”) obtains alerts indicating security policy violations for assets in a computing environment and the corresponding issue category(ies) associated with each violation. For each alert, the service determines which asset in the computing environment to target for remediation of the associated violation by searching a graph representation of the computing environment based on the affected asset's type and / or the issue category. The service identifies a target asset and other assets related to the affected asset and the target asset as a result of searching the graph and generates a remediation plan indicating actions to take on the target asset to remediate the security policy violation for the affected asset based on the target asset type and the corresponding issue category. The service indicates the remediation plan, the related assets identified due to the graph traversal, and their corresponding security policy violations within the same issue category.

1. The name of the design product: electronic device operation and maintenance monitoring management graphical user interface. 2. The use of the design product: the design product is used for an electronic device. 3. The design points of the design product: the graphical user interface. 4. The picture or photo that best indicates the design points: design 1 front view. 5. The carrier of the design product is the usual design, and other views are omitted. 6. Design 1 is designated as the basic design. 7. The use of the graphical user interface: the interface is mainly used for the interactive interface of operation and maintenance monitoring management, and mainly presents the ping test relationship between services through horizontal and vertical coordinates. Clicking on a "ping test unit (rectangle)" in the middle of the design 1 front view interface, the interface changes to design 1 interface change state diagram 1. Clicking on a "details" function key in the pop-up window of design 1 interface change state diagram 1, the interface changes to design 1 interface change state diagram 2. Entering the same information in the search box in the middle of the design 2 front view interface and clicking the search icon to the right of the search box, the interface changes to design 2 interface change state diagram.

1. Name of the product in this design: Electronic device with graphical user interface for deploying smart campus map beacons. 2. Intended use of this design: for use in an electronic device. 3. The key design features of this product are its graphical user interface. 4. The image or photograph that best illustrates the design's key points: the front view. 5. Electronic devices are designed in a conventional way, so the rear view, left and right views and the top and bottom views are omitted. 6. Purpose of the graphical user interface: It is used by park managers to manage maps and bind beacons via mobile devices. 7. Human-computer interaction method of graphical user interface: The main view is the initial login interface. After selecting any item in the list in the main view, it jumps to the interface change state diagram 1; after selecting any building in the list in the interface change state diagram 1, it jumps to the interface change state diagram 2, which displays the floor map of that building. Different floor maps can be switched. The map can be zoomed in and out using gestures. The device icon is displayed on the map; after clicking the device icon (i.e., the teardrop icon) on the map in the interface change state diagram 2, it jumps to the interface change state diagram 3, where beacon information can be popped up and modified or deleted; after clicking the add beacon button "⊕", clicking on a map area will show a gray icon, as shown in the interface change state diagram 4. You can click on other map areas again, and the gray icon will follow until you confirm and the beacon position will be fixed, completing the addition; clicking the search icon in the lower right corner is shown in the interface change state diagram 5.

The application relates to a Siamese network video single-target tracking method based on feature fusion, and particularly relates to a Siamese network monitoring video single-target tracking method based on feature fusion. In order to solve the problems that the Siamese network single-target tracking algorithm has low tracking capability when facing complex environments and obvious background interference near a tracked target, cannot accurately track the target, and the output tracking area is not accurate when tracking some specific targets, a model is trained by using a template region image set and a search region image set, feature maps of the template image and the search image are respectively output, the model sequentially comprises a ResNet-50 network based on a mixed attention mechanism and a twin feature fusion network, the feature map of the template image and the feature map of the search image are input into an RPN network for similarity comparison, a prediction region with the highest similarity to the template image in the search image is output, and single-target tracking is realized. The application belongs to the field of target tracking.

This enables the automatic search for alternative products that are "similar in appearance" and "cheaper." [Solution] When the control unit receives a command to search for a substitute for the target object, it acquires information about the target object. The information about the target object includes an image of the target object and the price of the target object. Based on the information about the target object, the control unit searches for a substitute object whose image is similar to the image of the target object and whose price is less than or equal to the price of the target object. The control unit outputs the search results.

The invention provides a target tracking method and system based on multi-stage feature fusion and residual enhancement, and the method comprises the steps: extracting features of a template and a search image, and adding a position code, so as to obtain a template image feature and a search image feature; the search features are enhanced through a double-stage enhancement module, and a confidence score is generated; thirdly, utilizing a learnable sparse modulation and dynamic gating bottleneck module to carry out further screening and differential enhancement on the features; then, training the model by using a large-scale data set, and optimizing parameters through joint classification and IoU loss; and finally, splicing the enhanced search features with the template features, interacting through an encoder, and outputting a tracking result by a prediction head. According to the method, through multi-stage enhancement, residual fusion and a dynamic adjustment mechanism, difficult scenes such as target shielding, complex backgrounds, scale change and rapid motion can be effectively handled, and the robustness and accuracy of target tracking are improved.

Embodiments of the present application disclose a traffic monitoring service processing method and an electronic device. The method comprises: acquiring a target image and related identification information, wherein the related identification information comprises identification information of a target commodity and / or a first user; generating an information code according to the related identification information and adding the information code to the target image, so as to publish content in a content publishing system by using the image to which the information code is added; after receiving a search request initiated by a second user in a commodity information service system by means of image search, judging whether there is a valid information code in the input search image; if there is, adding a traffic source identification related to a content publisher recommendation to the current search behavior, so as to parse the related identification information according to the information code and provide traffic monitoring information for the first user. Through the embodiments of the present application, a service of monitoring an effect of a "talent recommendation" operation strategy can be provided for a merchant user.

This invention discloses a target tracking method and system based on a cross-correlation matching enhanced Siamese network, comprising: cropping a video sequence of the target to be tracked to obtain template images and search images for all frames; inputting the template images and search images into a constructed and trained cross-correlation matching enhanced Siamese network to extract template features and search features from the template images and search images; performing cross-correlation matching on the template features and search features to obtain cross-correlation features; encoding bounding box information in the template images to obtain bounding box encoded features; performing classification and regression calculations on the fused features of cross-correlation features and bounding box encoded features to obtain corresponding classification score maps and regression prediction maps; and obtaining the final position of the target on the video sequence frames based on the position with the largest response value in the classification score map and the offset of the regression prediction map. This invention has strong adaptability and high accuracy in tracking complex scene changes.

The invention provides a method and a device for constructing a distributed approximate neighbor search graph index. The method comprises the following steps of: initializing each process, dividing batches for a read-only vector data set, and distributing a message buffer area; if the value of the counter is an even number, unprocessed data set batches are taken out, an adjacency list of each point is calculated in parallel, and a tuple is generated; if the counter value is an odd number, determining the affected points in the graph index updating process, and performing parallel pruning again and updating; the adjacency list length information is written into an adjacency list length array in parallel in the process; copying the information to a message sending buffer area in parallel by utilizing a parallel prefix and a calculation offset; broadcasting a sending message buffer area of each process; deserializing a tuple from the received message buffer area by each process, and updating a graph index in the process; generating tuples for the adjacency table of the updated points; printing related results by one process and outputting a graph index. According to the method, the index construction time is greatly shortened; and higher query accuracy can be provided in a query stage.

1. Name of the product in this design: Operation area and display area of ​​an intelligent dialogue or search graphical user interface for electronic devices. 2. Purpose of this design: An electronic device. 3. The key design features of this product are the graphical user interface in the electronic device for which protection is sought. 4. The picture or photo that best illustrates the key design points: Design 1 change state diagram 4. 5. Design 1 is designated as the basic design. 6. Uses of graphical user interfaces: Graphical user interfaces are used for intelligent dialogue or search. The graphical user interface requests protection for a portion used for image recognition and to display relevant dialogue prompts and dialogue content. 7. Human-computer interaction method of graphical user interface: In response to the user touching or clicking the capture button in the main view of Design 1, the graphical user interface changes from the main view of Design 1 to Design 1 change state diagram 1, then to Design 1 change state diagram 2, and then to Design 1 change state diagram 3 to show the process of generating dialogue prompts; in response to the completion of dialogue prompt generation, the graphical user interface changes from Design 1 change state diagram 3 to Design 1 change state diagram 4 to show the result of dialogue prompt generation; in response to the user touching or clicking the prompt at the bottom of Design 1 change state diagram 4, the graphical user interface changes from Design 1 change state diagram 4 to Design 1 change state diagram 5 to show the dialogue result; in response to the user touching or clicking the "In-depth Explanation" button in Design 1 change state diagram 5, the graphical user interface changes from Design 1 change state diagram 5 to Design 1 change state diagram 6 to show more details. In response to a user touching or clicking the capture button on the main view of Design 2, the graphical user interface changes from the main view of Design 2 to Design 2 Change State Diagram 1, then to Design 2 Change State Diagram 2, and then to Design 2 Change State Diagram 3 to demonstrate the generation process of the dialogue prompt; in response to the completion of the dialogue prompt generation, the graphical user interface changes from Design 2 Change State Diagram 3 to Design 2 Change State Diagram 4 to demonstrate the result of the dialogue prompt generation; in response to a user touching or clicking the prompt at the bottom of Design 2 Change State Diagram 4, the graphical user interface changes from Design 2 Change State Diagram 4 to Design 2 Change State Diagram 5 to demonstrate the dialogue result. In response to a user touching or clicking the capture button on the main view of Design 3, the graphical user interface changes from the main view of Design 3 to Design 3 Change State Diagram 1, then to Design 3 Change State Diagram 2, and then to Design 3 Change State Diagram 3 to display the generated dialog prompt; in response to a user touching or clicking the prompt at the bottom of Design 3 Change State Diagram 3, the graphical user interface changes from Design 3 Change State Diagram 3 to Design 3 Change State Diagram 4 to display the dialog result. In response to a user touching or clicking the capture button in the main view of Design 4, the graphical user interface changes from the main view of Design 4 to Design 4 Change State Diagram 1, then to Design 4 Change State Diagram 2, and then to Design 4 Change State Diagram 3 to display the generated dialogue prompts. In response to a user touching or clicking the prompt at the bottom of Design 4 Change State Diagram 3, the graphical user interface changes from Design 4 Change State Diagram 3 to Design 4 Change State Diagram 4 to display the dialogue results. In response to a user touching or clicking the "In-Depth Explanation" button in Design 4 Change State Diagram 4, the graphical user interface changes from Design 4 Change State Diagram 4 to Design 4 Change State Diagram 5 to display more detailed content. In response to a user touching or clicking the capture button in the main view of Design 5, the graphical user interface changes from the main view of Design 5 to Design 5 Change State Diagram 1, and then to Design 5 Change State Diagram 2 to demonstrate the generation process of the dialogue prompt; in response to the completion of the dialogue prompt generation, the graphical user interface changes from Design 5 Change State Diagram 2 to Design 5 Change State Diagram 3 to demonstrate the result of the dialogue prompt generation; in response to a user touching or clicking the prompt at the bottom of Design 5 Change State Diagram 3, the graphical user interface changes from Design 5 Change State Diagram 3 to Design 5 Change State Diagram 4 to demonstrate the dialogue result; in response to a user touching or clicking the "In-Depth Explanation" button in Design 5 Change State Diagram 4, the graphical user interface changes from Design 5 Change State Diagram 4 to Design 5 Change State Diagram 5 to demonstrate more details. In response to a user touching or clicking the capture button in the main view of Design 6, the graphical user interface changes from the main view of Design 6 to Design 6 Change State Diagram 1, and then to Design 6 Change State Diagram 2 to display the generated dialog prompt. In response to a user touching or clicking the prompt at the bottom of Design 6 Change State Diagram 2, the graphical user interface changes from Design 6 Change State Diagram 2 to Design 6 Change State Diagram 3 to display the dialog result. In response to a user touching or clicking the "In-Depth Explanation" button in Design 6 Change State Diagram 3, the graphical user interface changes from Design 6 Change State Diagram 3 to Design 6 Change State Diagram 4 to display more details. In response to a user touching or clicking the capture button on the main view of Design 7, the graphical user interface changes from the main view of Design 7 to Design 7 Change State Diagram 1, and then to Design 7 Change State Diagram 2 to show the process of generating the dialogue prompt; in response to the completion of the dialogue prompt generation, the graphical user interface changes from Design 7 Change State Diagram 2 to Design 7 Change State Diagram 3 to show the result of the dialogue prompt generation; in response to a user touching or clicking the prompt at the bottom of Design 7 Change State Diagram 3, the graphical user interface changes from Design 7 Change State Diagram 3 to Design 7 Change State Diagram 4 to show the dialogue result. In response to a user touching or clicking the capture button on the main view of Design 8, the graphical user interface changes from the main view of Design 8 to Design 8 Change State Diagram 1, and then to Design 8 Change State Diagram 2 to display the generated dialog prompt; in response to a user touching or clicking the prompt at the bottom of Design 8 Change State Diagram 2, the graphical user interface changes from Design 8 Change State Diagram 2 to Design 8 Change State Diagram 3 to display the dialog result. 8. Other situations requiring explanation: The portions of the graphical user interface shown by the dashed lines in the views of Designs 1 to 8 do not constitute the portion protected by this design.

A computerized-method for operating intraday schedule optimization in real-time for a schedule having one or more time-intervals, in a contact-center. The computerized-method includes: (i) retrieving current-state data of the contact center for each time-interval in the schedule; (ii) generating a current-schedule-state node that includes the received current-state data of the contact center; (iii) generating a directed-graph of a plurality of updated-schedule-state nodes; (iv) applying a model to predict SLA-level for each updated-schedule-state node in the generated directed-graph; (v) applying a heuristic search graph algorithm on the generated directed-graph of the plurality of updated-schedule-state nodes based on the SLA level of each updated-schedule-state node in the generated directed-graph as a heuristic to yield a path in the directed-graph of updated-schedule-state nodes; (vi) updating the schedule in the contact center based on the change in agents activities of each edge in the yielded path in the updated-schedule-state nodes in the path.

Device (40) for managing dimensional information, which manages dimensional information about an embedded object (51) contained in a search image showing the presence or absence of an embedded (51) object in a measurement object (50) and generated by a device (10) for scanning embedded objects, which performs a scan along the measurement object (50), wherein the device (40) for managing dimensional information comprises: a detection unit (41) configured to detect search information comprising the search image from the device (10) for scanning embedded objects; and a search information storage unit (43) configured to store the search information acquired by the acquisition unit (41); characterized by an input unit (44) into which design information is entered, which includes position information about the embedded object (51) in the measured object (50); a matching unit (47) configured to compare the search information stored in the search information storage unit (43) with the design information entered into the input unit (44) and to determine whether a match exists or not; and a design drawing generation unit (48) which is configured to generate a design drawing with screw positions based on the search information and the corresponding design information, if, as a result of the matching performed by the matching unit (47), the search information matches the design information.

1. Name of the product in this design: Operation selection box for an artificial intelligence search graphical user interface of an electronic device. 2. Purpose of this design: An electronic device. 3. The key design features of this product are the parts of the graphical user interface that require protection. 4. The image or photograph that best illustrates the design's key features: the front view. 5. Purpose of the graphical user interface: The overall interface is an AI search graphical user interface, displaying a split-screen view; the parts of the interface are operation selection boxes for the search graphical user interface. In the left-hand interface, when a user clicks or taps an object or text, the area is automatically recognized and a selection box matching its size is displayed. At this time, a selection area consisting of a rounded rectangle and a highlighted outer border covers the entire image. Users can adjust the size of the selection area using the control points on the edge of the selection box, or they can change the position of the selection area by dragging it. Users can also click the long oval at the bottom of the selection box to perform related operations. 6. Other situations requiring explanation: The dotted lines in the diagram represent content for which protection is not sought. The grayscale tones in the view represent the visual effect of the actual color contrast presented in the interface.

The application provides a graph neural network architecture search method and device, and relates to the technical field of artificial intelligence and deep learning, and the method comprises the following steps: constructing a super network based on an application requirement and a graph neural network search space, the search space comprising a function space and an operation space; performing search on the function space to determine a function combination with the highest accuracy of the super network; fixing the function of each position on the super network according to the function combination with the highest accuracy; and performing search on the operation space to determine an optimal graph neural network architecture satisfying the hardware efficiency requirement and the accuracy requirement in the application requirement. The application divides the search space into the function space and the operation space, and organizes the search space in the form of the super network, so that the search time can be effectively reduced. In addition, the application combines a hardware perception device, so that the actual hardware efficiency of the searched graph neural network architecture on a target device can be effectively improved.

Detecting fine-grained similarity in image includes determining a core area of a search image by generating an image salient map from a plurality of layers of the search image and determining a connected area based on the image salient map. Feature descriptors are generated from the core area of the search image. A plurality of capsule vectors are generated from different ones of a plurality of keypoints of the feature descriptors. Capsule vectors of the search image are compared with capsule vectors of each image of the dataset to generate a top-K matrix. Similarity scores for the top-K matrix are calculated. One or more image of the dataset having fine-grained similarity with the search image are selected based a bundled similarity score for each image of the dataset. The bundled similarity score is a summation of the similarity scores of the image.

The present application belongs to the technical field of image processing, and particularly relates to a template matching method based on a twin network and accurate center point positioning. The method comprises the following steps: S1, obtaining a training data set, i.e. a template and a search image; S2, constructing a template matching network based on a twin network and accurate center point positioning, and inputting the training data set of S1 into the template matching network, wherein the template matching network is composed of three parts, i.e. a twin feature extraction network, a dynamic shrink cross-correlation network and a center point positioning network, which are sequentially cascaded; and S3, training the template matching network of S2 by using a loss function. The method can better solve the problem of differences between the template and the search image, effectively improve the positioning accuracy of the target center point and the robustness of the template matching.

1. The name of the design product: the display area and input area of the smart conversation or search graphical user interface of an electronic device. 2. The use of the design product: an electronic device. 3. The design points of the design product: the protected part of the graphical user interface in the electronic device. 4. The picture or photo that best shows the design points: design 1 front view. 5. Design 1 is designated as the basic design. 6. The use of the graphical user interface: the graphical user interface is used for smart conversation or search. The protected part of the graphical user interface is used for the display of the problem thinking process and the input of the user's question. 7. The human-computer interaction mode of the graphical user interface: in design 1, design 2 and design 4, the user can pause the thinking of the question by touching or clicking the pause button at the bottom of the graphical user interface. In design 3, the user can input the question or requirement through the input box at the bottom of the graphical user interface. In response to the completion of skill planning generation, the graphical user interface changes from design 5 front view to design 5 change state figure 1 to display the step execution process; in response to the completion of step execution, the graphical user interface changes from design 5 change state figure 1 to design 5 change state figure 2 to display the thinking result. In response to the user clicking the pause button in the input box at the bottom of design 6 front view, inputting a supplementary requirement, the graphical user interface changes from design 6 front view to design 6 change state figure 1 to display the thinking process for the supplementary requirement; in response to the completion of thinking for the supplementary requirement, the graphical user interface changes from design 6 change state figure 1 to design 6 change state figure 2 to display the re-planning process for the supplementary requirement. 8. Other circumstances that need to be explained: the part of the graphical user interface shown by the dashed line in each view of design 1 to design 6 does not constitute the part claimed in the present design.

The application provides a target tracking method and system based on multi-stage feature fusion and residual enhancement, which comprises the following steps: extracting the features of a template and a search image and adding position coding to obtain template image features and search image features; enhancing the search features through a two-stage enhancement module and generating a confidence score; then, using a learnable sparse modulation and a dynamic gating bottleneck module to further filter and differentially enhance the features; then, training the model using a large-scale dataset, optimizing the parameters through joint classification and IoU loss; finally, splicing the enhanced search features and the template features, interacting through an encoder, and outputting the tracking results by a prediction head. Through multi-stage enhancement, residual fusion and dynamic adjustment mechanism, the application can effectively deal with difficult scenes such as target occlusion, complex background, scale transformation and rapid motion, and improve the robustness and accuracy of target tracking.

The application discloses a visual target tracking method based on natural language and target state information, and comprises the following steps: step (1), constructing a training sample set; step (2), constructing a visual target tracking model based on natural language and target state information; step (3), adjusting parameters of an image-text encoder and loading pre-training weights to obtain features of text and a first template after fusion, features of a second template and features of a search image; step (4), fusing position information of a target in a sample set and boundary box information of the target into the features of the second template; step (5), obtaining features after joint modeling; step (6), obtaining tokens containing target position information after query; step (7), obtaining a predicted target boundary box regression result; and step (8), obtaining a final tracking result. The application effectively improves the tracking accuracy of a visual tracker based on natural language.

The invention relates to a method for recognizing an object (2) in a search image (1), comprising the following steps: a) providing a pattern vector (5) describing the object (2) by means of coordinates of characteristic pixels (7); b) moving the pattern vector (5) over different positions of the search image (1); c) determining a respective success value (15) at the different positions; and d) recognizing the object (2) at the positions depending on the success values (15); wherein a first direction (8) and a second direction (9) different from the first direction (8) are associated with each characteristic pixel (7), wherein a first total intensity value (10) of a first number (11) of one-dimensionally arranged pixels in the first direction (8) and a second total intensity value (12) of a second number (13) of one-dimensionally arranged pixels in the second direction (9) are determined, respectively, wherein a difference value (14) between the first total intensity value (10) and the second total intensity value (12) is determined, respectively, wherein the success value (15) is determined depending on the respective difference value (14).