Learning activity progression in LSTMs for activity detection and early detection
Files
Published version
Date
2016
Authors
Ma, Shugao
Sigal, Leonid
Sclaroff, Stan
Version
Published version
OA Version
Citation
S Ma, L Sigal, S Sclaroff. 2016. "Learning Activity Progression in LSTMs for Activity Detection and Early Detection." Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR).
Abstract
In this work we improve training of temporal deep models to better learn activity progression for activity detection and early detection tasks. Conventionally, when training a Recurrent Neural Network, specifically a Long Short Term Memory (LSTM) model, the training loss only considers classification error. However, we argue that the detection score of the correct activity category, or the detection score margin between the correct and incorrect categories, should be monotonically non-decreasing as the model observes more of the activity. We design novel ranking losses that directly penalize the model on violation of such monotonicities, which are used together with classification loss in training of LSTM models. Evaluation on ActivityNet shows significant benefits of the proposed ranking losses in both activity detection and early detection tasks.
Description
License
This CVPR paper is the Open Access version, provided by the Computer Vision Foundation. Except for this watermark on the paper, it is identical to the version available on IEEE Xplore.