Abstract: A bi-directional interaction network (BINet)-based person search method, system, and apparatus are provided. The method includes: obtaining, as an input image, a tth frame of image in an input video; and normalizing the input image, and obtaining a search result of a to-be-searched target person by using a pre-trained person search model, where the person search model is constructed based on a residual network, and a new classification layer is added to a classification and regression layer of the residual network to obtain an identity classification probability of the target person. The method improves the accuracy of the person search.

Abstract: A display device is disclosed. The display device includes an array substrate and at least two driving units. The array substrate includes a peripheral region and a display region, the array substrate further includes a peripheral grounding line and a test line, wherein the peripheral grounding line is located in the peripheral region, and the test line is located in the peripheral region. The at least two driving units are located on at least one side of the array substrate, the driving unit includes at least two grounding pins, a grounding pin of at least one of the driving units is connected to the peripheral grounding line, and each of at least one grounding pin of one of two adjacent driving units is electrically connected to a corresponding grounding pin of the other adjacent driving unit.

Abstract: A bi-directional interaction network (BINet)-based person search method, system, and apparatus are provided. The method includes: obtaining, as an input image, a tth frame of image in an input video; and normalizing the input image, and obtaining a search result of a to-be-searched target person by using a pre-trained person search model, where the person search model is constructed based on a residual network, and a new classification layer is added to a classification and regression layer of the residual network to obtain an identity classification probability of the target person. The method improves the accuracy of the person search.