Abstract: The present teaching relates to content categorization. Supervised training data and unlabeled data clusters are used to generate augmented training data. Each unlabeled data cluster includes data samples with varying features. Weakly labeled training data is created based on supervised training data and the unlabeled data clusters with data samples therein with cluster labels via consistent self-training so that a labeled data sample in the supervised training data and a data sample in the weakly labeled training data with the same label have varying characteristics. Augmented training data is created from the supervised and the weakly labeled training data and is used to train a robust content categorization model via machine learning.

Abstract: The present teaching relates to content categorization. Supervised training data and unlabeled data clusters are used to generate augmented training data. Each unlabeled data cluster includes data samples with varying features. Weakly labeled training data is created with new data samples generated via generative augmentation based on supervised training data and the unlabeled data clusters. Each new data sample is assigned a label from a corresponding data sample from the supervised training data with generated varying characteristics. Augmented training data is created from the supervised and the weakly labeled training data and is used to train a robust content categorization model via machine learning.

Abstract: A multi-image sensor system includes data, clock, and control buses, an application processor connected to the data bus and the clock bus, and image sensors connected in a daisy chain using the control bus. A first one of the image sensors configured as a master outputs image data to the data bus, outputs a first clock signal to the clock bus, and sends a control signal to a second one of the image sensors in the daisy chain through the control bus. The control signal has a first logic state when output of the first image data starts and a second other logic state when output of the first image data ends. The second image sensor connects itself to the data bus and the master disconnects itself from the data bus according to a state of the first control signal.

Abstract: A multi-image sensor system includes data, clock, and control buses, an application processor connected to the data bus and the clock bus, and image sensors connected in a daisy chain using the control bus. A first one of the image sensors configured as a master outputs image data to the data bus, outputs a first clock signal to the clock bus, and sends a control signal to a second one of the image sensors in the daisy chain through the control bus. The control signal has a first logic state when output of the first image data starts and a second other logic state when output of the first image data ends. The second image sensor connects itself to the data bus and the master disconnects itself from the data bus according to a state of the first control signal.

Abstract: A method performed with an image sensor having a pixel array. At least one frame of a scene may be obtained using the pixel array. At least one region of interest (ROI) is identified within the frame. Subsequent frames of the scene are obtained, which involves controlling the pixel array to perform high resolution imaging with respect to the at least one ROI and low resolution imaging using analog binning with respect to remaining regions of the frames.

Abstract: A method performed with an image sensor having a pixel array. At least one frame of a scene may be obtained using the pixel array. At least one region of interest (ROI) is identified within the frame. Subsequent frames of the scene are obtained, which involves controlling the pixel array to perform high resolution imaging with respect to the at least one ROI and low resolution imaging using analog binning with respect to remaining regions of the frames.