Abstract: A high-strength stainless steel rotor and a method for preparing the same, are provided. The high-strength stainless steel rotor, including the following element components by mass percentage: C: 0.03-0.050%, Cr: 14.90-15.80%, Ni: 5.00-5.70%, Cu: 2.20-2.80%, (Nb+Ta): 0.35-0.44%, Mo: 0.45-0.54%, V: 0.06-0.10%, Si: 0.20-0.60%, Mn: 0.40-0.80%, P?0.010%, S?0.010%, O?0.003%, and the balance of iron and inevitable impurities.

Abstract: A hot extrusion die for a special-shaped square pipe includes a die cavity sleeve with a special-shaped cavity. A hot extrusion mandrel is arranged in the die cavity sleeve. An area between the die cavity sleeve and the hot extrusion mandrel forms a die cavity hole. A first extrusion diversion hole and a second extrusion diversion hole are arranged below the die cavity hole. An integral centroid of the die cavity hole is located at a circle center of a radial cross section of the die cavity sleeve. Further disclosed is a hot extrusion integral forming method for a special-shaped square pipe, including: heating and expanding a blank material; heating the blank material again after expanding; performing hot extrusion on the blank material; and cooling the formed special-shaped square pipe in air to a room temperature, and inspecting surface quality and mechanical properties of the special-shaped square pipe.

Abstract: A segmentation recognition method includes: an object detection step of detecting an object image in a target image by inputting bounding box information including a coordinate and category information of each bounding box defined in the target image to an object detection model that uses a machine learning approach; a filtering step of selecting effective training mask information from training mask information associated with foregrounds in the target image based on the bounding box information; a bounding box branch step of recognizing the object image using weight information of the object detection model as an initial value of weight information of an object recognition model that recognizes an object of the object image; and a mask branch step of generating mask information having a shape of the object image using the selected effective training mask information as training data and using weight information of the object recognition model as an initial value of weight information of a segmentation shape

Abstract: The present invention makes it possible to cause an action recognizer capable of recognizing actions with high accuracy and with a small quantity of learning data to learn. An input unit 101 receives input of a learning video and an action label indicating an action of an object, a detection unit 102 detects a plurality of objects included in each frame image included in the learning video, a direction calculation unit 103 calculates a direction of a reference object, which is an object to be used as a reference among the plurality of detected objects, a normalization unit 104 normalizes the learning video so that a positional relationship between the reference object and another object becomes a predetermined relationship, and an optimization unit 106 optimizes parameters of an action recognizer to estimate the action of the object in the inputted video based on the action estimated by inputting the normalized learning video to the action recognizer and the action indicated by the action label.

Abstract: A high-strength stainless steel rotor and a method for preparing the same, are provided. The high-strength stainless steel rotor, including the following element components by mass percentage: C: 0.03-0.050%, Cr: 14.90-15.80%, Ni: 5.00-5.70%, Cu: 2.20-2.80%, (Nb+Ta): 0.35-0.44%, Mo: 0.45-0.54%, V: 0.06-0.10%, Si: 0.20-0.60%, Mn: 0.40-0.80%, P?0.010%, S?0.010%, O?0.003%, and the balance of iron and inevitable impurities.

Abstract: An object is to accurately recognize an action of a subject. A direction alignment unit 24 is configured to perform at least one of rotation and inversion on an image based on an action direction of a desired subject in the image, so as to obtain an adjusted image. An action recognition device 26 is configured to recognize an action of the desired subject using the adjusted image as an input.

Abstract: The category and region of an object shown by an image can be accurately recognized. A first hierarchical feature map generation unit 23 Generates a hierarchical feature map constituted of feature maps hierarchized from a deep layer to a shallow layer, based on feature maps which are output by layers of the CNN. A second hierarchical feature map generation unit 24 generates a hierarchical feature map constituted of feature maps hierarchized from the shallow layer to the deep layer. As integration unit 25 generates a hierarchical feature map by integrating feature maps of corresponding layers. An object region detection unit 26 detects object candidate regions and an object recognition unit 27 recognizes, for each of the object candidate regions, the category and region of as object represented by the object candidate region.

Abstract: The present invention belongs to the technical field of metal materials for additive manufacturing, and relates to a Mn—Cu-based damping alloy powder for use in a selective laser melting (SLM) process and a preparation method thereof. The powder has chemical components in percent by weight as follows: C: ?0.15%, Ni: 4.9-5.2%, Si: ?0.15%, Fe: 1.8-5.0%, Cu: 20-23%, P: ?0.03%, S: ?0.06%, and the balance being Mn and inevitable impurities. The preparation method includes: preparation of master alloy, powdering by vacuum induction melting gas atomization (VIGA), mechanical vibrating and air classification screening under protection of an inert gas and collecting. Compared with the prior art, the powder of the present invention has a high sphericity, a high apparent density, a small angle of repose, a desired fluidity and a relatively high yield of fine powders having a size of 15-53 ?m.