Object detection, as of one the most fundamental and challenging problems in computer
vision, has received great attention in recent years. Over the past two decades, we have …

Object detection that focuses on locating objects of interest and categorizing them has long
played a critical role in the development of remote sensing imagery. Following significant …

Abstract We present Open Images V4, a dataset of 9.2 M images with unified annotations for
image classification, object detection and visual relationship detection. The images have a …

Image captioning models have achieved impressive results on datasets containing limited
visual concepts and large amounts of paired image-caption training data. However, if these …

Manually annotating object bounding boxes is central to building computer vision datasets,
and it is very time consuming (annotating ILSVRC [53] took 35s for one high-quality box …

For many applications the collection of labeled data is expensive laborious. Exploitation of
unlabeled data during training is thus a long pursued objective of machine learning. Self …

Despite significant efforts made so far for Weakly Supervised Object Detection (WSOD),
proposal generation and proposal selection are still two major challenges. In this paper, we …

Object detection methods like Single Shot Multibox Detector (SSD) provide highly accurate
object detection that run in real-time. However, these approaches require a large number of …

Weakly supervised learning has attracted growing research attention due to the significant
saving in annotation cost for tasks that require intra-image annotations, such as object …

The great success that deep models have achieved in the past is mainly owed to large
amounts of labeled training data. However, the acquisition of labeled data for new tasks …