Previous work generally believes that improving the spatial invariance of convolutional
networks is the key to object counting. However, after verifying several mainstream counting …

The mainstream crowd counting methods usually utilize the convolution neural network
(CNN) to regress a density map, requiring point-level annotations. However, annotating …

This paper investigates crowd counting in the frequency domain, which is a novel direction
compared to the traditional view in the spatial domain. By transforming the density map into …

Crowd localization, predicting head positions, is a more practical and high-level task than
simply counting. Existing methods employ pseudo-bounding boxes or pre-designed …

Accurately estimating the number of objects in a single image is a challenging yet
meaningful task and has been applied in many applications such as urban planning and …

Supervised crowd counting relies heavily on costly manual labeling, which is difficult and
expensive, especially in dense scenes. To alleviate the problem, we propose a novel …

In this paper, we focus on the crowd localization task, a crucial topic of crowd analysis. Most
regression-based methods utilize convolution neural networks (CNN) to regress a density …

Recently, most handwritten mathematical expression recognition (HMER) methods adopt
the encoder-decoder networks, which directly predict the markup sequences from formula …

Recently, indiscernible scene understanding has attracted a lot of attention in the vision
community. We further advance the frontier of this field by systematically studying a new …

Crowd counting is a fundamental problem in crowd analysis which is typically accomplished
by estimating a crowd density map and summing over the density values. However this …