Large margin high-order deep learning with auxiliary tasks for video-based anomaly detection

1. A computer-implemented method for video-based anomaly detection, comprising:

forming, by a processor, a Deep High-Order Convolutional Neural Network (DHOCNN)-based model having a one-class Support Vector Machine (SVM) as a loss layer of the DHOCNN-based model, an objective of the SVM being configured to perform the video-based anomaly detection;

generating, by the processor, one or more predictions of an impending anomaly based on the high-order deep learning based model applied to an input image; and

initiating, by the processor, an action to a hardware device to mitigate expected harm to at least one item selected from the group consisting of the hardware device, another hardware device related to the hardware device, and a person related to the hardware device;

wherein the DHOCNN-based model uses a plurality of high-order kernels to capture high-order feature interactions relating to the input image on which the video-based anomaly detection is performed.

2. The computer-implemented method of claim 1 , further comprising pre-training the DHOCNN-based model using a plurality of auxiliary tasks relating to potential dangerous conditions which generate supervision labels and guide parameter learning for the DHOCNN-based model.

3. The computer-implemented method of claim 2 , wherein pre-training the DHOCNN-based model uses back-propagation with the plurality of auxiliary tasks.

4. The computer-implemented method of claim 1 , further comprising fine-tuning model parameters of the DHOCNN-based model using back-propagation.

5. The computer-implemented method of claim 1 , wherein the SVM is employed in a final layer of the DHOCNN-based model.

6. The computer-implemented method of claim 1 , wherein the video-based anomaly detection is supervised video-based anomaly detection.

7. The computer-implemented method of claim 1 , further comprising reducing a computational complexity of the DHOCNN-based model using a matrix factorization technique.

8. The computer-implemented method of claim 7 , wherein the matrix factorization technique involves a plurality of rank-one matrices.

9. The computer-implemented method of claim 1 , wherein the SVM is configured to separate data examples from an origin in a feature space and maximize a distance from a hyperplane of the feature space to the origin.

10. The computer-implemented method of claim 1 , wherein the SVM is configured to produce a binary function that captures regions in a feature space where a probability density is greatest.

11. A computer-implemented method for video-based anomaly detection, comprising:

forming, by a processor, a Deep High-Order Convolutional Neural Network (DHOCNN)-based model having a one-class Support Vector Machine (SVM) as a loss layer of the DHOCNN-based model, an objective of the SVM being configured to perform the video-based anomaly detection;

generating, by the processor, one or more predictions of an impending anomaly based on the high-order deep learning based model applied to an input image; and

initiating, by the processor, an action to a hardware device to mitigate expected harm to at least one item selected from the group consisting of the hardware device, another hardware device related to the hardware device, and a person related to the hardware device;

further comprising reducing a computational complexity of the DHOCNN-based model using a matrix factorization technique;

wherein the matrix factorization technique involves a plurality of rank-one matrices;

wherein the plurality of rank-one matrices are configured to explicitly model different orders of interaction among features extracted the input image.

12. A computer program product for video-based anomaly detection, the computer program product comprising a non-transitory computer readable storage medium having program instructions embodied therewith, the program instructions executable by a computer to cause the computer to perform a method comprising:

forming, by a processor, a Deep High-Order Convolutional Neural Network (DHOCNN)-based model having a one-class Support Vector Machine (SVM) as a loss layer of the DHOCNN-based model, an objective of the SVM being configured to perform the video-based anomaly detection;

generating, by the processor, one or more predictions of an impending anomaly based on the high-order deep learning based model applied to an input image; and

initiating, by the processor, an action to a hardware device to mitigate expected harm to at least one item selected from the group consisting of the hardware device, another hardware device related to the hardware device, and a person related to the hardware device;

wherein the method further comprises reducing a computational complexity of the DHOCNN-based model using a matrix factorization technique that involves a plurality of rank-one matrices, and wherein the plurality of rank-one matrices are configured to explicitly model different orders of interaction among features extracted the input image.

13. The computer program product of claim 12 , wherein the method further comprises pre-training the DHOCNN-based model using a plurality of auxiliary tasks relating to potential dangerous conditions which generate supervision labels and guide parameter learning for the DHOCNN-based model.

14. The computer program product of claim 12 , wherein the method further comprises fine-tuning model parameters of the DHOCNN-based model using back-propagation.

15. The computer program product of claim 12 , wherein the SVM is employed in a final layer of the DHOCNN-based model.

16. The computer program product of claim 12 , wherein the SVM is configured to separate data examples from an origin in a feature space and maximize a distance from a hyperplane of the feature space to the origin.

17. The computer program product of claim 12 , wherein the SVM is configured to produce a binary function that captures regions in a feature space where a probability density is greatest.