Abstract: An activity classifier system and method that classifies human activities using 2D skeleton data. The system includes a skeleton preprocessor that transforms the 2D skeleton data into transformed skeleton data, the transformed skeleton data comprising scaled, relative joint positions and relative joint velocities. The system also includes a gesture classifier comprising a first recurrent neural network that receives the transformed skeleton data, and is trained to identify the most probable of a plurality of gestures. The system also has an action classifier comprising a second recurrent neural network that receives information from the first recurrent neural networks and is trained to identify the most probable of a plurality of actions.

Abstract: An activity classifier system and method that classifies human activities using 2D skeleton data. The system includes a skeleton preprocessor that transforms the 2D skeleton data into transformed skeleton data, the transformed skeleton data comprising scaled, relative joint positions and relative joint velocities. The system also includes a gesture classifier comprising a first recurrent neural network that receives the transformed skeleton data, and is trained to identify the most probable of a plurality of gestures. The system also has an action classifier comprising a second recurrent neural network that receives information from the first recurrent neural networks and is trained to identify the most probable of a plurality of actions.

Abstract: An activity classifier system and method that classifies human activities using 2D skeleton data. The system includes a skeleton preprocessor that transforms the 2D skeleton data into transformed skeleton data, the transformed skeleton data comprising scaled, relative joint positions and relative joint velocities. The system also includes a gesture classifier comprising a first recurrent neural network that receives the transformed skeleton data, and is trained to identify the most probable of a plurality of gestures. The system also has an action classifier comprising a second recurrent neural network that receives information from the first recurrent neural networks and is trained to identify the most probable of a plurality of actions.

Abstract: System and method for extracting human pose information from an image, comprising a feature extractor connected to a database, a convolutional neural network (CNN) with a plurality of CNN layers. Said system/method further comprising at least one of the following modules: a 2D body skeleton detector for determining 2D body skeleton information from the human-related image features; a body silhouette detector for determining body silhouette information from the human-related image features; a hand silhouette detector for determining hand silhouette detector from the human-related image features; a hand skeleton detector for determining hand skeleton from the human-related image features; a 3D body skeleton detector for determining 3D body skeleton from the human-related image features; and a facial keypoints detector for determining facial keypoints from the human-related image features.

Abstract: An activity classifier system and method that classifies human activities using 2D skeleton data. The system includes a skeleton preprocessor that transforms the 2D skeleton data into transformed skeleton data, the transformed skeleton data comprising scaled, relative joint positions and relative joint velocities. The system also includes a gesture classifier comprising a first recurrent neural network that receives the transformed skeleton data, and is trained to identify the most probable of a plurality of gestures. The system also has an action classifier comprising a second recurrent neural network that receives information from the first recurrent neural networks and is trained to identify the most probable of a plurality of actions.

Abstract: This disclosure is directed to an activity classifier system, for classifying human activities using 2D skeleton data. The system includes a skeleton preprocessor that transforms the 2D skeleton data into transformed skeleton data, the transformed skeleton data comprising scaled, relative joint positions and relative joint velocities. It also includes a gesture classifier comprising a first recurrent neural network that receives the transformed skeleton data, and is trained to identify the most probable of a plurality of gestures. There is also an action classifier comprising a second recurrent neural network that receives information from the first recurrent neural networks and is trained to identify the most probable of a plurality of actions.

Abstract: This disclosure is directed to an activity classifier system, for classifying human activities using 2D skeleton data. The system includes a skeleton preprocessor that transforms the 2D skeleton data into transformed skeleton data, the transformed skeleton data comprising scaled, relative joint positions and relative joint velocities. It also includes a gesture classifier comprising a first recurrent neural network that receives the transformed skeleton data, and is trained to identify the most probable of a plurality of gestures. There is also an action classifier comprising a second recurrent neural network that receives information from the first recurrent neural networks and is trained to identify the most probable of a plurality of actions.

Abstract: A method and system for providing a computer-simulated environment for displaying a selected mannequin wearing a combination of selected garments. In one aspect, three-dimensional scenes containing mannequin and garment objects are created within a three-dimensional modeling environment, and a simulation is performed using a cloth simulator within the modeling environment to model the construction, draping, and collision of the garment with the mannequin. Rendering frames corresponding to a variety of garments, mannequins, garment dimensions, garment styles, wearing patterns, viewing angles, and other parameters, are then generated from which images can be rendered and displayed in accordance with user requests.

Abstract: A method and system for providing a computer-simulated environment for displaying a selected mannequin wearing a combination of selected garments. In one aspect, three-dimensional scenes containing mannequin and garment objects are created within a three-dimensional modeling environment, and a simulation is performed using a cloth simulator within the modeling environment to model the construction, draping, and collision of the garment with the mannequin. Rendering frames corresponding to a variety of garments, mannequins, garment dimensions, garment styles, wearing patterns, viewing angles, and other parameters, are then generated from which images can be rendered and displayed in accordance with user requests.

Abstract: A method and system for providing a computer-simulated environment for displaying a selected mannequin wearing a combination of selected garments. In one aspect, three-dimensional scenes containing mannequin and garment objects are created within a three-dimensional modeling environment, and a simulation is performed using a cloth simulator within the modeling environment to model the construction, draping, and collision of the garment with the mannequin. Rendering frames corresponding to a variety of garments, mannequins, garment dimensions, garment styles, wearing patterns, viewing angles, and other parameters, are then generated from which images can be rendered and displayed in accordance with user requests.

Abstract: A method and system for providing a computer-simulated environment for displaying a selected mannequin wearing a combination of selected garments. In one aspect, three-dimensional scenes containing mannequin and garment objects are created within a three-dimensional modeling environment, and a simulation is performed using a cloth simulator within the modeling environment to model the construction, draping, and collision of the garment with the mannequin. Rendering frames corresponding to a variety of garments, mannequins, garment dimensions, garment styles, wearing patterns, viewing angles, and other parameters, are then generated from which images can be rendered and displayed in accordance with user requests.

Abstract: The method for on-screen animation includes providing a digital world including image object elements and defining autonomous image entities (AIE). Each AIE may represent a character or an object that is characterized by i) attributes defining the AIE relatively to the image objects elements of the digital world, and ii) behaviours for modifying some of the attributes. Each AIE is associated to animation clips allowing representing the AIE in movement in the digital world. Virtual sensors allow the AIE to gather data information about image object elements or other AIE within the digital world. Decision trees are used for processing the data information resulting in selecting and triggering one of the animation cycle or selecting a new behaviour. A system embodying the above method is also provided. The method and system for on-screen animation of digital entities according to the present invention can be used for creating animation for movies, for video games, and for simulation.