papers AI Learner
The Github is limit! Click to go to the new site.

Object Detection from Video Tubelets with Convolutional Neural Networks

2016-04-14
Kai Kang, Wanli Ouyang, Hongsheng Li, Xiaogang Wang

Abstract

Deep Convolution Neural Networks (CNNs) have shown impressive performance in various vision tasks such as image classification, object detection and semantic segmentation. For object detection, particularly in still images, the performance has been significantly increased last year thanks to powerful deep networks (e.g. GoogleNet) and detection frameworks (e.g. Regions with CNN features (R-CNN)). The lately introduced ImageNet task on object detection from video (VID) brings the object detection task into the video domain, in which objects’ locations at each frame are required to be annotated with bounding boxes. In this work, we introduce a complete framework for the VID task based on still-image object detection and general object tracking. Their relations and contributions in the VID task are thoroughly studied and evaluated. In addition, a temporal convolution network is proposed to incorporate temporal information to regularize the detection results and shows its effectiveness for the task.

Abstract (translated by Google)
URL

https://arxiv.org/abs/1604.04053

PDF

https://arxiv.org/pdf/1604.04053


Similar Posts

Comments