Abstract: Systems and methods of the present disclosure are directed to computer-implemented method for contextual processing via inter-model between pre-trained machine-learned models. The method includes obtaining, by a computing system comprising one or more computing devices, input data. The method includes processing, by the computing system, the input data with two or more pre-trained models to generate output data, wherein processing the input comprises executing a structured inter-model communication schema for inter-model communication between the two or more pre-trained models over a communications channel. The method includes providing, by the computing system, the output data as an output.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing videos and text using co-tokenization.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for determining one or more neural network architectures of a neural network for performing a video processing neural network task. In one aspect, a method comprises: at each of a plurality of iterations: selecting a parent neural network architecture from a set of neural network architectures; training a neural network having the parent neural network architecture to perform the video processing neural network task, comprising determining trained values of connection weight parameters of the parent neural network architecture; generating a new neural network architecture based at least in part on the trained values of the connection weight parameters of the parent neural network architecture; and adding the new neural network architecture to the set of neural network architectures.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for determining one or more neural network architectures of a neural network for performing a video processing neural network task. In one aspect, a method comprises: at each of a plurality of iterations: selecting a parent neural network architecture from a set of neural network architectures; training a neural network having the parent neural network architecture to perform the video processing neural network task, comprising determining trained values of connection weight parameters of the parent neural network architecture; generating a new neural network architecture based at least in part on the trained values of the connection weight parameters of the parent neural network architecture; and adding the new neural network architecture to the set of neural network architectures.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for controlling an agent interacting with an environment. In one aspect, a method comprises: receiving a natural language text sequence that characterizes a task to be performed by the agent in the environment; generating an encoded representation of the natural language text sequence; and at each of a plurality of time steps: obtaining an observation image characterizing a state of the environment at the time step; processing the observation image to generate an encoded representation of the observation image; generating a sequence of input tokens; processing the sequence of input tokens to generate a policy output that defines an action to be performed by the agent in response to the observation image; selecting an action to be performed by the agent using the policy output; and causing the agent to perform the selected action.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing a network input using a computer vision neural network with learned tokenization.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for processing a network input using a neural network to generate a network output.

Abstract: Generally, the present disclosure is directed to a neural architecture search process for finding small and fast video processing networks for understanding of video data. The neural architecture search process can automatically design networks that provide comparable video processing performance at a fraction of the computational and storage cost of larger existing models, thereby conserving computing resources such as memory and processor usage.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for determining one or more neural network architectures of a neural network for performing a video processing neural network task. In one aspect, a method comprises: at each of a plurality of iterations: selecting a parent neural network architecture from a set of neural network architectures; training a neural network having the parent neural network architecture to perform the video processing neural network task, comprising determining trained values of connection weight parameters of the parent neural network architecture; generating a new neural network architecture based at least in part on the trained values of the connection weight parameters of the parent neural network architecture; and adding the new neural network architecture to the set of neural network architectures.

Abstract: Disclosed are an apparatus and a method for analyzing a video. The video analyzing apparatus includes a route analyzing unit configured to analyze a subject of a first-person view video and an object represented in the first-person view video based on the first-person view video and generate route information of the subject and the object; and an event analyzing unit configured to classify the first-person view video as a semantic event using the route information.

Abstract: Disclosed are a method and an apparatus for generating training videos and recognizing situations, using composed videos. The method for generating training videos using composed videos according to an exemplary embodiment of the present invention includes generating composed videos based on configuration information of an original video; selecting the composed videos satisfying structural constraints of situations among the generated composed videos; and configuring the training videos including the selected composed videos.