The past decade has witnessed significant progress on detecting objects in aerial images
that are often distributed with large-scale variations and arbitrary orientations. However …

Complicated underwater environments bring new challenges to object detection, such as
unbalanced light conditions, low contrast, occlusion, and mimicry of aquatic organisms …

We develop a probabilistic interpretation of two-stage object detection. We show that this
probabilistic interpretation motivates a number of common empirical training practices. It …

Although two-stage object detectors have continuously advanced the state-of-the-art
performance in recent years, the training process itself is far from crystal. In this work, we first …

DETR is a recently proposed Transformer-based method which views object detection as a
set prediction problem and achieves state-of-the-art performance but demands extra-long …

We present FoveaBox, an accurate, flexible, and completely anchor-free framework for
object detection. While almost all state-of-the-art object detectors utilize predefined anchors …

As a prerequisite for autonomous driving, scene understanding has attracted extensive
research. With the rise of the convolutional neural network (CNN)-based deep learning …

Object detection is a fundamental yet challenging task in computer vision. Despite the great
strides made over recent years, modern detectors may still produce unsatisfactory …

Deep learning-based dense object detectors have achieved great success in the past few
years and have been applied to numerous multimedia applications such as video …

Recently, salient object detection in optical remote sensing images (RSI-SOD) has attracted
great attention. Benefiting from the success of deep learning and the inspiration of natural …