Temporal Performance Prediction for Deep Convolutional Long Short-Term Memory Networks

2023-11-13 · Laura Fieback, Bidya Dash, Jakob Spiegelberg, Hanno Gottschalk

Quantifying predictive uncertainty of deep semantic segmentation networks is essential in safety-critical tasks. In applications like autonomous driving, where video data is available, convolutional long short-term memory networks are capable of not only providing semantic segmentations but also predicting the segmentations of the next timesteps. These models use cell states to broadcast information from previous data by taking a time series of inputs to predict one or even further steps into the future. We present a temporal postprocessing method which estimates the prediction performance of convolutional long short-term memory networks by either predicting the intersection over union of predicted and ground truth segments or classifying between intersection over union being equal to zero or greater than zero. To this end, we create temporal cell state-based input metrics per segment and investigate different models for the estimation of the predictive quality based on these metrics. We further study the influence of the number of considered cell states for the proposed metrics.

📄 PDF Abstract BibTeX arXiv:2311.07477

Code (0)

등록된 구현이 없습니다.

Tasks

Autonomous Driving Semantic SegmentationTime Series

Short-Term Power Prediction for Renewable Energy Using Hybrid Graph Convolutional Network and Long Short-Term Memory Approach

2021-11-15 · Wenlong Liao, Birgitte Bak-Jensen, Jayakrishnan Radhakrishna Pillai, Zhe Yang 외

Accurate short-term solar and wind power predictions play an important role in the planning and operation of power systems. However, the short-term power prediction of renewable energy has always been considered a comple…

Graph Neural Network

Anomaly detection using prediction error with Spatio-Temporal Convolutional LSTM

2022-05-18 · Hanh Thi Minh Tran, David Hogg

In this paper, we propose a novel method for video anomaly detection motivated by an existing architecture for sequence-to-sequence prediction and reconstruction using a spatio-temporal convolutional Long Short-Term Memo…

Anomaly Detection Prediction Video Anomaly Detection

Spatiotemporal Recurrent Convolutional Networks for Traffic Prediction in Transportation Networks

2017-05-07 · Haiyang Yu, Zhihai Wu, Shuqin Wang, Yunpeng Wang 외

Predicting large-scale transportation network traffic has become an important and challenging topic in recent decades. Inspired by the domain knowledge of motion prediction, in which the future motion of an object can be…

motion prediction Traffic Prediction

Short-Term Forecasting of Passenger Demand under On-Demand Ride Services: A Spatio-Temporal Deep Learning Approach

2017-06-20 · Jintao Ke, Hongyu Zheng, Hai Yang, Xiqun 외

Short-term passenger demand forecasting is of great importance to the on-demand ride service platform, which can incentivize vacant cars moving from over-supply regions to over-demand regions. The spatial dependences, te…

Demand Forecasting feature selection Time Series Analysis Time Series Prediction

Convolutional Sequence to Sequence Model for Human Dynamics

2018-05-02 · CVPR 2018 6 · Chen Li, Zhen Zhang, Wee Sun Lee, Gim Hee Lee

Human motion modeling is a classic problem in computer vision and graphics. Challenges in modeling human motion include high dimensional prediction as well as extremely complicated dynamics.We present a novel approach to…

Decoder Human Dynamics Human Pose Forecasting model