Convolutional neural networkConvolutional neural network (CNN) is a regularized type of feed-forward neural network that learns feature engineering by itself via filters (or kernel) optimization. Vanishing gradients and exploding gradients, seen during backpropagation in earlier neural networks, are prevented by using regularized weights over fewer connections. For example, for each neuron in the fully-connected layer 10,000 weights would be required for processing an image sized 100 × 100 pixels.
Residual neural networkA Residual Neural Network (a.k.a. Residual Network, ResNet) is a deep learning model in which the weight layers learn residual functions with reference to the layer inputs. A Residual Network is a network with skip connections that perform identity mappings, merged with the layer outputs by addition. It behaves like a Highway Network whose gates are opened through strongly positive bias weights. This enables deep learning models with tens or hundreds of layers to train easily and approach better accuracy when going deeper.
AnimationAnimation is the method by which are manipulated to create moving images. In traditional animation, images are drawn or painted by hand on transparent celluloid sheets to be photographed and exhibited on film. Today, many animations are computer animations made with (CGI). Stop motion animation, in particular claymation, has continued to exist alongside these other forms. Animation is contrasted with live-action film, although the two do not exist in isolation. Many moviemakers have produced films that are a hybrid of the two.
Computer animationComputer animation is the process used for digitally generating animations. The more general term (CGI) encompasses both static scenes (s) and dynamic images (s), while computer animation refers to moving images. Modern computer animation usually uses 3D computer graphics to generate a three-dimensional picture. The target of the animation is sometimes the computer itself, while other times it is film. Computer animation is essentially a digital successor to stop motion techniques, but using 3D models, and traditional animation techniques using frame-by-frame animation of 2D illustrations.
Feature (computer vision)In computer vision and , a feature is a piece of information about the content of an image; typically about whether a certain region of the image has certain properties. Features may be specific structures in the image such as points, edges or objects. Features may also be the result of a general neighborhood operation or feature detection applied to the image. Other examples of features are related to motion in image sequences, or to shapes defined in terms of curves or boundaries between different image regions.
Animeis hand-drawn and computer-generated animation originating from Japan. Outside Japan and in English, anime refers specifically to animation produced in Japan. However, in Japan and in Japanese, anime (a term derived from a shortening of the English word animation) describes all animated works, regardless of style or origin. Animation produced outside Japan with similar style to Japanese animation is commonly referred to as anime-influenced animation. The earliest commercial Japanese animations date to 1917.
Natural language processingNatural language processing (NLP) is an interdisciplinary subfield of linguistics and computer science. It is primarily concerned with processing natural language datasets, such as text corpora or speech corpora, using either rule-based or probabilistic (i.e. statistical and, most recently, neural network-based) machine learning approaches. The goal is a computer capable of "understanding" the contents of documents, including the contextual nuances of the language within them.
Chinese animationChinese animation refers to animation made in China. In Chinese, donghua () describes all animated works, regardless of style or origin. However, outside of China and in English, donghua is colloquial for Chinese animation and refers specifically to animation produced in China. History of Chinese animation The history of animated moving pictures in China began in 1918 when an animation piece from the United States titled Out of the Inkwell landed in Shanghai. Cartoon clips were first used in advertisements for domestic products.
Flash animationAdobe Flash animation (formerly Macromedia Flash animation and FutureSplash animation) is an animation that is created with the Adobe Animate (formerly Flash Professional) platform or similar animation software and often distributed in the SWF file format. The term Adobe Flash animation refers to both the file format and the medium in which the animation is produced. Adobe Flash animation has enjoyed mainstream popularity since the mid-2000s, with many Adobe Flash-animated television series, television commercials, and award-winning online shorts being produced since then.
OSI modelThe Open Systems Interconnection model (OSI model) is a conceptual model from the International Organization for Standardization (ISO) that "provides a common basis for the coordination of standards development for the purpose of systems interconnection." In the OSI reference model, the communications between a computing system are split into seven different abstraction layers: Physical, Data Link, Network, Transport, Session, Presentation, and Application.
Homography (computer vision)In the field of computer vision, any two images of the same planar surface in space are related by a homography (assuming a pinhole camera model). This has many practical applications, such as , , or camera motion—rotation and translation—between two images. Once camera resectioning has been done from an estimated homography matrix, this information may be used for navigation, or to insert models of 3D objects into an image or video, so that they are rendered with the correct perspective and appear to have been part of the original scene (see Augmented reality).
Pose (computer vision)In the fields of computing and computer vision, pose (or spatial pose) represents the position and orientation of an object, usually in three dimensions. Poses are often stored internally as transformation matrices. The term “pose” is largely synonymous with the term “transform”, but a transform may often include scale, whereas pose does not. In computer vision, the pose of an object is often estimated from camera input by the process of pose estimation.
