T-CNN: Tubelets with Convolutional Neural Networks for Object Detection from Videos
Abstract
The state-of-the-art performance for object detection has been significantly improved over the past two years. Besides the introduction of powerful deep neural networks such as GoogleNet and VGG, novel object detection frameworks such as R-CNN and its successors, Fast R-CNN and Faster R-CNN, play an essential role in improving the state-of-the-art. Despite their effectiveness on still images, those frameworks are not specifically designed for object detection from videos. Temporal and contextual information of videos are not fully investigated and utilized. In this work, we propose a deep learning framework that incorporates temporal and contextual information from tubelets obtained in videos, which dramatically improves the baseline performance of existing still-image detection frameworks when they are applied to videos. It is called T-CNN, i.e. tubelets with convolutional neueral networks. The proposed framework won the recently introduced object-detection-from-video (VID) task with provided data in the ImageNet Large-Scale Visual Recognition Challenge 2015 (ILSVRC2015).
Keywords
Cite
@article{arxiv.1604.02532,
title = {T-CNN: Tubelets with Convolutional Neural Networks for Object Detection from Videos},
author = {Kai Kang and Hongsheng Li and Junjie Yan and Xingyu Zeng and Bin Yang and Tong Xiao and Cong Zhang and Zhe Wang and Ruohui Wang and Xiaogang Wang and Wanli Ouyang},
journal= {arXiv preprint arXiv:1604.02532},
year = {2018}
}
Comments
ImageNet 2015 VID challenge tech report. The first two authors share co-first authorship. Accepted as a Transaction paper by T-CSVT Special Issue on Large Scale and Nonlinear Similarity Learning for Intelligent Video Analysis