Video Object Detection with an Aligned Spatial-Temporal Memory
COMPUTER VISION - ECCV 2018, PT VIII(2018)
摘要
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.
更多查看译文
关键词
Aligned spatial-temporal memory, Video object detection
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络