Learning Activity Progression in LSTMs for Activity Detection and Early Detection

Citations Over TimeTop 1% of 2016 papers

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.

Related Papers

• → Artificial Intelligence for Sport Actions and Performance Analysis using Recurrent Neural Network (RNN) with Long Short-Term Memory (LSTM)(2018)10 cited
• → Understanding LSTM -- a tutorial into Long Short-Term Memory Recurrent\n Neural Networks(2019)497 cited
• → Understanding LSTM -- a tutorial into Long Short-Term Memory Recurrent Neural Networks(2019)152 cited
• → Accident Detection System Based on RNN Exploiting Keypoints and LSTM(2023)
• → Hoax Identification On Social Media Using Recurrent Neural Network (RNN) And Long Short-term Memory (LSTM) Methods(2023)