Abstract: An example system includes a processor to receive an image containing an object to be detected. The processor is to detect the object in the image via a binary object detector trained via a self-supervised training on raw and unlabeled videos.

Abstract: An example system includes a processor to receive an image containing an object to be detected. The processor is to detect the object in the image via a binary object detector trained via a self-supervised training on raw and unlabeled videos.

Abstract: An example system includes a processor to receive raw and unlabeled videos. The processor is to extract speech from the raw and unlabeled videos. The processor is to extract positive frames and negative frames from the raw and unlabeled videos based on the extracted speech for each object to be detected. The processor is to extract region proposals from the positive frames and negative frames. The processor is to extract features based on the extracted region proposals. The processor is to cluster the region proposals and assign a potential score to each cluster. The processor is to train a binary object detector to detect objects based on positive samples randomly selected based on the potential score.

Abstract: An example system includes a processor to receive input data comprising noisy positive data and clean negative data. The processor is to cluster the input data. The processor is to compute a potential score for each cluster of the clustered input data. The processor is to iteratively refine cluster quality of the clusters using the potential scores of the clusters as weights. The processor is to train a classifier by sampling the negative dataset uniformly and the positive set in a non-uniform manner based on the potential score.

Abstract: Automated detection and approximation of objects in a video, including: (a) sampling a provided digital video, to obtain a set of sampled frames; (b) applying an object detection algorithm to the sampled frames, to detect objects appearing in the sampled frames; (c) based on the detections in the sampled frames, applying an object approximation algorithm to each sequence of frames that lie between the sampled frames, to approximately detect objects appearing in each of the sequences; (d) applying a trained regression model to each of the sequences, to estimate a quality of the approximate detection of objects in the respective sequence; (e) applying the object detection algorithm to one or more frames in those of the sequences whose quality of the approximate detection is below a threshold, to detect objects appearing in those frames.

Abstract: Automated detection and approximation of objects in a video, including: (a) sampling a provided digital video, to obtain a set of sampled frames; (b) applying an object detection algorithm to the sampled frames, to detect objects appearing in the sampled frames; (c) based on the detections in the sampled frames, applying an object approximation algorithm to each sequence of frames that lie between the sampled frames, to approximately detect objects appearing in each of the sequences; (d) applying a trained regression model to each of the sequences, to estimate a quality of the approximate detection of objects in the respective sequence; (e) applying the object detection algorithm to one or more frames in those of the sequences whose quality of the approximate detection is below a threshold, to detect objects appearing in those frames.

Abstract: A system comprising at least one hardware processor; and a non-transitory computer-readable storage medium having stored thereon program instructions, the program instructions executable by the at least one hardware processor to: receive, as input, video data, perform a first tracking, using a tracking algorithm, of an identified target in a sequence of frames of said video data, wherein said first tracking is performed forward in time, perform a second tracking, using said tracking algorithm, of said target in said sequence, wherein said second tracking is performed backward in time, and calculate a confidence score for a tracked location of said target in a frame of said sequence, based, at least in part, on a comparison between said first tracking and said second tracking.

Abstract: An example system includes a processor to receive input data comprising noisy positive data and clean negative data. The processor is to cluster the input data. The processor is to compute a potential score for each cluster of the clustered input data. The processor is to iteratively refine cluster quality of the clusters using the potential scores of the clusters as weights. The processor is to train a classifier by sampling the negative dataset uniformly and the positive set in a non-uniform manner based on the potential score.

Abstract: An example system includes a processor to receive raw and unlabeled videos. The processor is to extract speech from the raw and unlabeled videos. The processor is to extract positive frames and negative frames from the raw and unlabeled videos based on the extracted speech for each object to be detected. The processor is to extract region proposals from the positive frames and negative frames. The processor is to extract features based on the extracted region proposals. The processor is to cluster the region proposals and assign a potential score to each cluster. The processor is to train a binary object detector to detect objects based on positive samples randomly selected based on the potential score.

Abstract: An example system includes a processor to receive detections or recognitions with confidence scores for an object in a medium from a plurality of trained detection or recognition models. The processor is to generate a probability of correctness for each of the detections or recognitions based on the confidence scores via correctness mappings generated for each of the trained detection or recognition models. The processor is to also select a detection or recognition with a higher probability of correctness from the detections or recognitions. The processor is to perform a detection or recognition task based on the selected detection or recognition.

Abstract: A system comprising at least one hardware processor; and a non-transitory computer-readable storage medium having stored thereon program instructions, the program instructions executable by the at least one hardware processor to: receive, as input, video data, perform a first tracking, using a tracking algorithm, of an identified target in a sequence of frames of said video data, wherein said first tracking is performed forward in time, perform a second tracking, using said tracking algorithm, of said target in said sequence, wherein said second tracking is performed backward in time, and calculate a confidence score for a tracked location of said target in a frame of said sequence, based, at least in part, on a comparison between said first tracking and said second tracking.

Abstract: An example system includes a processor to receive detections or recognitions with confidence scores for an object in a medium from a plurality of trained detection or recognition models. The processor is to generate a probability of correctness for each of the detections or recognitions based on the confidence scores via correctness mappings generated for each of the trained detection or recognition models. The processor is to also select a detection or recognition with a higher probability of correctness from the detections or recognitions. The processor is to perform a detection or recognition task based on the selected detection or recognition.

Abstract: A system comprising a non-transient computer-readable storage medium having stored thereon instructions and at least one hardware processor configured to execute the instructions, to receive a video sequence; divide the video sequence into one or more scenes based on scene boundaries, wherein each scene comprises a plurality of temporally-contiguous image frames, and wherein said scene boundaries are being determined based on a similarity metric between two temporally-contiguous image frames meeting a dissimilarity threshold; and, for each scene of the one or more scenes, (i) generate a plurality of preliminary classifications of an object appearing in at least some of said image frames in the scene, wherein each of said plurality of preliminary classifications has a confidence score, and (ii) calculate a combined classification of the object based on said plurality of preliminary classifications, wherein each of said preliminary classifications is weighted in accordance with its confidence score.

Abstract: A system comprising a non-transient computer-readable storage medium having stored thereon instructions and at least one hardware processor configured to execute the instructions, to receive a video sequence; divide the video sequence into one or more scenes based on scene boundaries, wherein each scene comprises a plurality of temporally-contiguous image frames, and wherein said scene boundaries are being determined based on a similarity metric between two temporally-contiguous image frames meeting a dissimilarity threshold; and, for each scene of the one or more scenes, (i) generate a plurality of preliminary classifications of an object appearing in at least some of said image frames in the scene, wherein each of said plurality of preliminary classifications has a confidence score, and (ii) calculate a combined classification of the object based on said plurality of preliminary classifications, wherein each of said preliminary classifications is weighted in accordance with its confidence score.