Abstract: Provided are embodiments including a computer-implemented method for performing recognition. The computer-implemented method includes receiving video data, and performing, at a pre-attention prediction module, a pre-attention prediction for the video data to generate first prediction priors. The computer-implemented method also includes receiving, at a dual attention module, data including the video data and data from the pre-attention prediction to generate attention maps, wherein the attention maps indicate a region of interest of a frame of the video data, wherein the dual attention module generates enhanced feature representations, and performing, at a post-attention prediction module, a post-attention prediction from data from the dual attention module based at least in part on the enhanced feature representation. Also provided are embodiments for a system and a computer program produce for performing recognition.

Abstract: This application provides a target detection method and device based on a neural network and training method and device of a neural network for target detection. The target detection method comprises: acquiring a to-be-detected image that contains a target; acquiring first feature information of the to-be-detected image by use of a first neural network, acquiring second feature information of the to-be-detected image by use of a second neural network; combining the first feature information and the second feature information to acquire combined feature information; and acquiring a target detection result by use of the second neural network and based on the combined feature information, wherein the number of layers of the second neural network is larger than the number of layers of the first neural network, the first feature information is heatmap feature information, and the second feature information is picture feature information.

Abstract: This application provides a target detection method and device based on a neural network and training method and device of a neural network for target detection. The target detection method comprises: acquiring a to-be-detected image that contains a target;acquiring first feature information of the to-be-detected image by use of a first neural network, acquiring second feature information of the to-be-detected image by use of a second neural network;combining the first feature information and the second feature information to acquire combined feature information; and acquiring a target detection result by use of the second neural network and based on the combined feature information, wherein the number of layers of the second neural network is larger than the number of layers of the first neural network, the first feature information is heatmap feature information, and the second feature information is picture feature information.