# Video Object Detection with an Aligned Spatial-Temporal Memory Source: [Video Object Detection with an Aligned Spatial-Temporal Memory]() Collection index: [llms.txt]() Data updated: 2025-10-25T21:08:59.042Z Authors: Fanyi Xiao, Yong Jae Lee Published: 2017-12-18T10:02:23.000Z ## Abstract We introduce Spatial-Temporal Memory Networks for video object detection. At its core, a novel Spatial-Temporal Memory module (STMM) serves as the recurrent computation unit to model long-term temporal appearance and motion dynamics. The STMM's design enables full integration of pretrained backbone CNN weights, which we find to be critical for accurate detection. Furthermore, in order to tackle object motion in videos, we propose a novel MatchTrans module to align the spatial-temporal memory from frame to frame. Our method produces state-of-the-art results on the benchmark ImageNet VID dataset, and our ablative studies clearly demonstrate the contribution of our different design choices. We release our code and models at http://fanyix.cs.ucdavis.edu/project/stmn/project.html. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Video Object Detection on ImageNet VID (val)](): Video Object Detection; ImageNet VID (val); mAP (%): 80.5. ## Original sources and implementation [Original paper]() [PDF]()