边距(机器学习)
排名(信息检索)
计算机科学
人工智能
放射性检测
机器学习
深度学习
人工神经网络
循环神经网络
培训(气象学)
短时记忆
模式识别(心理学)
物理
气象学
作者
Shugao Ma,Leonid Sigal,Stan Sclaroff
标识
DOI:10.1109/cvpr.2016.214
摘要
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.
科研通智能强力驱动
Strongly Powered by AbleSci AI