Cores Costa, DanielBrea Sánchez, Víctor ManuelMucientes Molina, Manuel2021-11-162021-11-162021Image and Vision Computing. Volume 110, June 2021, 104179http://hdl.handle.net/10347/27098We present a new network architecture able to take advantage of spatio-temporal information available in videos to boost object detection precision. First, box features are associated and aggregated by linking proposals that come from the same anchor box in the nearby frames. Then, we design a new attention module that aggregates short-term enhanced box features to exploit long-term spatio-temporal information. This module takes advantage of geometrical features in the long-term for the first time in the video object detection domain. Finally, a spatio-temporal double head is fed with both spatial information from the reference frame and the aggregated information that takes into account the short- and long-term temporal context. We have tested our proposal in five video object detection datasets with very different characteristics, in order to prove its robustness in a wide number of scenarios. Non-parametric statistical tests show that our approach outperforms the state-of-the-art. Our code is available at https://github.com/daniel-cores/SLTneteng© 2021 The Authors. Published by Elsevier B.V. This work is licenced under a CC Attribution-NonCommercial-NoDerivatives 4.0 International licence (CC BY-NC-ND 4.0)http://creativecommons.org/licenses/by-nc-nd/4.0/Video object detectionSpatio-temporal featuresConvolutional neural networksjournal article10.1016/j.imavis.2021.1041790262-8856open access