no code implementations • 4 Feb 2024 • Jianming Lv, Sijun Xia, Depin Liang, Wei Chen
Traditional model-free feature selection methods treat each feature independently while disregarding the interrelationships among features, which leads to relatively poor performance compared with the model-aware methods.
no code implementations • 4 Feb 2024 • Jianming Lv, Depin Liang, Zequan Liang, Yaobin Zhang, Sijun Xia
Compared with gradient based artificial neural networks, biological neural networks usually show a more powerful generalization ability to quickly adapt to unknown environments without using any gradient back-propagation procedure.
no code implementations • CVPR 2021 • Sucheng Ren, Yong Du, Jianming Lv, Guoqiang Han, Shengfeng He
To these ends, we introduce a trainable "master" network which ingests both audio signals and silent lip videos instead of a pretrained teacher.
1 code implementation • 16 Mar 2020 • Jianming Lv, Qinzhe Xiao, Jiajie Zhong
To address this problem, we propose an attention based model, namely AVR, to achieve salient visual relationships based on both local and global context of the relationships.
1 code implementation • 14 Jan 2019 • Zhenguo Yang, Zehang Lin, Peipei Kang, Jianming Lv, Qing Li, Wenyin Liu
In this paper, we propose to learn shared semantic space with correlation alignment (${S}^{3}CA$) for multimodal data representations, which aligns nonlinear correlations of multimodal data distributions in deep neural networks designed for heterogeneous data.
no code implementations • 11 Jun 2018 • Jianming Lv, Xintong Wang
Meanwhile, SimPGAN uses the similarity consistency loss, which is measured by a siamese deep convolutional neural network, to preserve the similarity of the transformed images of the same person.
1 code implementation • CVPR 2018 • Jianming Lv, Weihang Chen, Qing Li, Can Yang
Most of the proposed person re-identification algorithms conduct supervised training and testing on single labeled datasets with small size, so directly deploying these trained models to a large-scale real-world camera network may lead to poor performance due to underfitting.
no code implementations • 23 Nov 2016 • Jianming Lv, Qing Li, Xintong Wang
Precise destination prediction of taxi trajectories can benefit many intelligent location based services such as accurate ad for passengers.