In this paper, we propose a novel SpatioTemporal convolutional Dense Network (STDNet) to address the video-based crowd counting problem, which contains the decomposition of 3D …
Deep neural networks (DNNs) have proven their capabilities in the past years and play a significant role in environment perception for the challenging application of automated …
K Tian, C Zhang, Y Wang, S Xiang - Neural Networks, 2023 - Elsevier
The development of deep learning techniques has greatly benefited CNN-based object detectors, leading to unprecedented progress in recent years. However, the distribution …
Class-agnostic counting is usually phrased as a matching problem between a user-defined exemplar patch and a query image. The count is derived based on the number of objects …
Hand segmentation is a crucial task in first-person vision. Since first-person images exhibit strong bias in appearance among different environments, adapting a pre-trained …
Modifying facial attributes without the paired dataset proves to be a challenging task. Previously, approaches either required supervision from a ground-truth transformed image …
F Huang, Z Yao, W Zhou - ECAI, 2023 - ebooks.iospress.nl
Due to the poor illumination and the difficulty in annotating, nighttime conditions pose a significant challenge for autonomous vehicle perception systems. Unsupervised domain …
Self-driving cars leverage on semantic segmentation to understand an urban scene. However, it is costly to collect segmentation labels, thus, synthetic datasets are used to train …
YM Hu, JJ Xie, HH Shuai, CC Huang… - 2023 IEEE …, 2023 - ieeexplore.ieee.org
Feature fusion is a key process of integrating multiple features in deep neural networks (DNN). The mainstream method in the literature is based on the Feature Pyramid Network …