Abstract: A method is provided, that initiates with providing a video over a network to a plurality of client devices, wherein each client device is configured to render the video and track movements of a pointer during the rendering of the video. Movement data that is indicative of the tracked movements of the pointer is received over the network from each client device. The movement data from the plurality of client devices is processed to determine aggregate pointer movement versus elapsed time of the video. The aggregate pointer movement is analyzed to identify a region of interest of the video. A preview of the video is generated based on the identified region of interest.

Abstract: A method is provided, that initiates with providing a video over a network to a plurality of client devices, wherein each client device is configured to render the video and track movements of a pointer during the rendering of the video. Movement data that is indicative of the tracked movements of the pointer is received over the network from each client device. The movement data from the plurality of client devices is processed to determine aggregate pointer movement versus elapsed time of the video. The aggregate pointer movement is analyzed to identify a region of interest of the video. A preview of the video is generated based on the identified region of interest.

Abstract: A system and method enable generating a specific object detector for a category of interest. The method includes identifying seed objects in frames of a video sequence with a pre-trained generic detector for the category. An appearance model is iteratively learned for each of the seed objects using other frames in which the seed object is identified. The appearance models are learned jointly to optimize a loss function which accounts for the loss of incorrectly labeling sub-images and a regularization term which measures a distance between the appearance models. The loss of incorrectly labeling sub-images is determined using a motion model which predicts the location of the seed object in the subsequent frames so that sub-images outside the location that the current appearance model contribute to the loss. The specific object detector is then generated by aggregating the optimized appearance models.

Abstract: A system and method enable generating a specific object detector for a category of interest. The method includes identifying seed objects in frames of a video sequence with a pre-trained generic detector for the category. An appearance model is iteratively learned for each of the seed objects using other frames in which the seed object is identified. The appearance models are learned jointly to optimize a loss function which accounts for the loss of incorrectly labeling sub-images and a regularization term which measures a distance between the appearance models. The loss of incorrectly labeling sub-images is determined using a motion model which predicts the location of the seed object in the subsequent frames so that sub-images outside the location that the current appearance model contribute to the loss. The specific object detector is then generated by aggregating the optimized appearance models.