Spatiotemporal Tile-based Attention-guided LSTMs for Traffic Video Prediction

10/24/2019
by   Tu Nguyen, et al.
0

This extended abstract describes our solution for the Traffic4Cast Challenge 2019. The key problem we addressed is to properly model both low-level (pixel based) and high-level spatial information while still preserve the temporal relations among the frames. Our approach is inspired by the recent adoption of convolutional features into a recurrent neural networks such as LSTM to jointly capture the spatio-temporal dependency. While this approach has been proven to surpass the traditional stacked CNNs (using 2D or 3D kernels) in action recognition, we observe suboptimal performance in traffic prediction setting. Therefore, we apply a number of adaptations in the frame encoder-decoder layers and in sampling procedure to better capture the high-resolution trajectories, and to increase the training efficiency.

READ FULL TEXT
research
11/19/2015

Delving Deeper into Convolutional Networks for Learning Video Representations

We propose an approach to learn spatio-temporal features in videos from ...
research
08/25/2017

Learning Spatio-Temporal Features with 3D Residual Networks for Action Recognition

Convolutional neural networks with spatio-temporal 3D kernels (3D CNNs) ...
research
12/21/2018

3DSRnet: Video Super-resolution using 3D Convolutional Neural Networks

In video super-resolution, the spatio-temporal coherence between, and am...
research
11/22/2017

Multi-Level Recurrent Residual Networks for Action Recognition

Most existing Convolutional Neural Networks(CNNs) used for action recogn...
research
08/29/2016

Temporal Convolutional Networks: A Unified Approach to Action Segmentation

The dominant paradigm for video-based action segmentation is composed of...
research
02/27/2022

Meta-path Analysis on Spatio-Temporal Graphs for Pedestrian Trajectory Prediction

Spatio-temporal graphs (ST-graphs) have been used to model time series t...
research
11/25/2020

Temporal Autoencoder with U-Net Style Skip-Connections for Frame Prediction

Finding sustainable and novel solutions to predict city-wide mobility be...

Please sign up or login with your details

Forgot password? Click here to reset