Abstract Deep Neural Networks (DNNs) learn representation from data with an impressive
capability, and brought important breakthroughs for processing images, time-series, natural …

Detecting objects remains one of computer vision and image understanding applications'
most fundamental and challenging aspects. Significant advances in object detection have …

We show that the YOLOv4 object detection neural network based on the CSP approach,
scales both up and down and is applicable to small and large networks while maintaining …

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 …

Abstract Localization Quality Estimation (LQE) is crucial and popular in the recent
advancement of dense object detectors since it can provide accurate ranking scores that …

Recent advances in detecting arbitrary objects in the real world are trained and evaluated
on object detection datasets with a relatively restricted vocabulary. To facilitate the …

Instance segmentation has witnessed a remarkable progress on class-balanced
benchmarks. However, they fail to perform as accurately in real-world scenarios, where the …

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

Object detection is a fundamental computer vision task that simultaneously predicts the
category and localization of the targets of interest. Recently one-stage (also termed “dense”) …

Temporal action localization (TAL) in videos is a challenging task, especially due to the
large variation in action temporal scales. Short actions usually occupy a major proportion in …