Dynamic attention mechanism and global modeling ability make Transformer show strong
feature learning ability. In recent years, Transformer has become comparable to CNNs …

Recent transformer-based models, especially patch-based methods, have shown huge
potentiality in vision tasks. However, the split fixed-size patches divide the input features into …

In this work, we present a novel multi-scale feature fusion network (M-FFN) for image
captioning task to incorporate discriminative features and scene contextual information of an …

Pedestrian detection is an important but challenging problem in computer vision, especially
in human-centric tasks. Over the past decade, significant improvement has been witnessed …

The application of convolutional neural network (CNN) has greatly promoted the scope and
scenario of intelligent fault diagnosis and brought about a significant improvement of …

For object detection, how to address the contradictory requirement between feature map
resolution and receptive field on high-resolution inputs still remains an open question. In this …

The task of object detection and tracking is one of the most complex and challenging
problems in artificial intelligence (AI) systems that model perception. Object tracking has …

Object detection traditionally requires sliding-window classifier in modern deep learning
based approaches. However, both of these approaches requires tedious configurations in …

Semantic segmentation is a critical method in the field of autonomous driving. When
performing semantic image segmentation, a wider field of view (FoV) helps to obtain more …

Pedestrian detection in images is a topic that has been studied extensively, but existing
detectors designed for perspective images do not perform as successfully on images taken …