Abstract: A method includes receiving input from a client at least partially specifying one or more characteristics, wherein the initial input includes a seed image and a natural language statement describing a desired change to the seed image; predicting one or more attributes of the seed image by operation of a neural network on the seed image; and parsing the natural language statement to identify desired changes to the one or more attributes of the seed image. The method also includes generating an interim target image by changing the one or more attributes of the seed image, according to the parsed natural language statement; selecting a set of images from an image database for output to the client, each of said set of images being determined to at least partially satisfy the one or more changed attributes of the seed image; and displaying the set of images to the client.

Abstract: A method and system for auto-curating a media are provided. Media content is received over the network interface. A set of markers is identified for the media content, each marker corresponding to one of a plurality of visible and audible cues in the media content. Segments in the media content are identified based on the identified set of markers. An excitement score is computed for each segment based on the identified markers that fall within the segment. A highlight clip is generated by identifying segments having excitement scores greater than a threshold.

Abstract: Techniques regarding action detection based on motion in receptive fields of a neural network model are provided. For example, one or more embodiments described herein can comprise a system, which can comprise a memory that can store computer executable components. The system can also comprise a processor, operably coupled to the memory, and that can execute the computer executable components stored in the memory. The computer executable components can comprise a motion component that can extract a motion vector from a plurality of adaptive receptive fields in a deformable convolution layer of a neural network model. The computer executable components can also comprise an action detection component that can generate a spatio-temporal feature by concatenating the motion vector with a spatial feature extracted from the deformable convolution layer.

Abstract: A method includes receiving input from a client at least partially specifying one or more characteristics, wherein the initial input includes a seed image and a natural language statement describing a desired change to the seed image; predicting one or more attributes of the seed image by operation of a neural network on the seed image; and parsing the natural language statement to identify desired changes to the one or more attributes of the seed image. The method also includes generating an interim target image by changing the one or more attributes of the seed image, according to the parsed natural language statement; selecting a set of images from an image database for output to the client, each of said set of images being determined to at least partially satisfy the one or more changed attributes of the seed image; and displaying the set of images to the client.

Abstract: A method includes: receiving initial input from a client at least partially specifying one or more characteristics sought by the client; selecting a set of images from an image database for output to the client; and determining after each set of images whether an end condition has occurred. The method also includes, until the end condition has occurred: responsive to each set of images output to the client, receiving additional input from the client further specifying the one or more characteristics sought by the client; and responsive to each input received from the client, selecting another set of images for presentation to the client, said set of images being determined to at least partially satisfy the one or more characteristics specified by all input received from the client, said determination being based at least in part on side information for respective images for at least the set of images.

Abstract: A method includes: receiving initial input from a client at least partially specifying one or more characteristics sought by the client; selecting a set of images from an image database for output to the client; and determining after each set of images whether an end condition has occurred. The method also includes, until the end condition has occurred: responsive to each set of images output to the client, receiving additional input from the client further specifying the one or more characteristics sought by the client; and responsive to each input received from the client, selecting another set of images for presentation to the client, said set of images being determined to at least partially satisfy the one or more characteristics specified by all input received from the client, said determination being based at least in part on side information for respective images for at least the set of images.

Abstract: A method and system for auto-curating a media are provided. Media content is received over the network interface. A set of markers is identified for the media content, each marker corresponding to one of a plurality of visible and audible cues in the media content. Segments in the media content are identified based on the identified set of markers. An excitement score is computed for each segment based on the identified markers that fall within the segment. A highlight clip is generated by identifying segments having excitement scores greater than a threshold.

Abstract: A system and a method for tracking a plurality of objects, including obtaining input data, estimating a number of skipping frames of the input data based on information from the input data, predicting results based on the estimating of the number of skipping frames, and correcting the predicted results.

Abstract: A method and system for auto-curating a media are provided. Media content is received over the network interface. A set of markers is identified for the media content, each marker corresponding to one of a plurality of visible and audible cues in the media content. Segments in the media content are identified based on the identified set of markers. An excitement score is computed for each segment based on the identified markers that fall within the segment. A highlight clip is generated by identifying segments having excitement scores greater than a threshold.

Abstract: Techniques regarding action detection based on motion in receptive fields of a neural network model are provided. For example, one or more embodiments described herein can comprise a system, which can comprise a memory that can store computer executable components. The system can also comprise a processor, operably coupled to the memory, and that can execute the computer executable components stored in the memory. The computer executable components can comprise a motion component that can extract a motion vector from a plurality of adaptive receptive fields in a deformable convolution layer of a neural network model. The computer executable components can also comprise an action detection component that can generate a spatio-temporal feature by concatenating the motion vector with a spatial feature extracted from the deformable convolution layer.

Abstract: A method and system for auto-curating a media are provided. Media content is received over the network interface. A set of markers is identified for the media content, each marker corresponding to one of a plurality of visible and audible cues in the media content. Segments in the media content are identified based on the identified set of markers. An excitement score is computed for each segment based on the identified markers that fall within the segment. A highlight clip is generated by identifying segments having excitement scores greater than a threshold.

Abstract: A person detection system includes a face detector configured to detect a face in an input video sequence, the face detector outputting a face keyframe to be stored if a face is detected; and a person detector configured to detect a person in the input video sequence if the face detector fails to detect a face, the person detector outputting a person keyframe to be stored, if a person is detected in the input video sequence.

Abstract: An occlusion detection system and method include a decomposer configured to decompose an image into a set of hierarchical parts. A hierarchy of classifiers is employed to detect features in the image and the hierarchical parts. A logical operation is configured to logically combine a classification result from at least two of the classifiers to detect an occlusion state of the image.

Abstract: A person detection system includes a face detector configured to detect a face in an input video sequence, the face detector outputting a face keyframe to be stored if a face is detected; and a person detector configured to detect a person in the input video sequence if the face detector fails to detect a face, the person detector outputting a person keyframe to be stored, if a person is detected in the input video sequence.

Abstract: A method generates a stylized image of a scene including an object. A set of n input images are acquired of the scene with a camera. Each one of the n input images is illuminated by one of a set of n light sources mounted on a body of the camera at different positions from a center of projection of a lens of the camera. Ambient lighting can be used to illuminate one image. Features in the set of n input images are detected. The features include depth edges, intensity edges, and texture edges to determine qualitative depth relationships between the depth edges, the intensity edges and the texture edges. The set of n input images are then combined in an output image to enhance the detected features according to the qualitative relationships.

Abstract: An occlusion detection system and method include a decomposer configured to decompose an image into a set of hierarchical parts. A hierarchy of classifiers is employed to detect features in the image and the hierarchical parts. A logical operation is configured to logically combine a classification result from at least two of the classifiers to detect an occlusion state of the image.