In this paper, we study the problem of end-to-end multi-person pose estimation. State-of-the-
art solutions adopt the DETR-like framework, and mainly develop the complex decoder, eg …

Contemporary deep-learning object detection methods for autonomous driving usually
presume fixed categories of common traffic participants, such as pedestrians and cars. Most …

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 …

Existing object detection methods are bounded in a fixed-set vocabulary by costly labeled
data. When dealing with novel categories, the model has to be retrained with more bounding …

Feature pyramids have been proven powerful in image understanding tasks that require
multi-scale features. Stateof-the-art methods for multi-scale feature learning focus on …

Since Transformer has found widespread use in NLP, the potential of Transformer in CV has
been realized and has inspired many new approaches. However, the computation required …

Coconut (Cocos nucifera L.) is one of the world's most economically important tree species,
and coconut palm plantations dominate many islands and tropical coastlines. However, the …

The recent advances in camera-based bird's eye view (BEV) representation exhibit great
potential for in-vehicle 3D perception. Despite the substantial progress achieved on …

This study adheres to a set of guidelines for performing an SLR. The mission of the SLR is to
find publications, publishers, deep learning types, improved and amended deep learning …

This paper investigates a phenomenon where query-based object detectors mispredict at
the last decoding stage while predicting correctly at an intermediate stage. We review the …