no code implementations • 11 Apr 2024 • Zhenzhe Gao, Zhenjun Tang, Zhaoxia Yin, Baoyuan Wu, Yue Lu
Neural networks have increasingly influenced people's lives.
1 code implementation • 19 Dec 2023 • Lingjun Zhang, Xinyuan Chen, Yaohui Wang, Yue Lu, Yu Qiao
To tackle this problem, we propose Diff-Text, which is a training-free scene text generation framework for any language.
no code implementations • 28 Oct 2023 • Pourya Shamsolmoali, Jocelyn Chanussot, Huiyu Zhou, Yue Lu
To address the aforementioned challenges, we propose Attention-based Feature Distillation (AFD), a new KD approach that distills both local and global information from the teacher detector.
no code implementations • 25 Oct 2023 • Yuejun Jiao, Song Qiu, Mingsong Chen, Dingding Han, Qingli Li, Yue Lu
Finally, the nodes and similarity adjacency matrices are fed into graph networks to extract more discriminative features for vehicle Re-ID.
1 code implementation • 15 Oct 2023 • Xinting Li, Shiguang Zhang, Yue Lu, Kerry Dang, Lingyan Ran
This method combines target detection information with the relative semantic similarity between the target and the navigation target, and constructs a brand new state representation based on similarity ranking, this state representation does not include target feature or environment feature, effectively decoupling the agent's navigation ability from target features.
no code implementations • 11 Oct 2023 • Pourya Shamsolmoali, Masoumeh Zareapoor, Huiyu Zhou, Xuelong Li, Yue Lu
The challenge of image generation has been effectively modeled as a problem of structure priors or transformation.
no code implementations • 22 Aug 2023 • Zhenzhe Gao, Zhaoxia Yin, Hongjian Zhan, Heng Yin, Yue Lu
Fragile watermarking is a technique used to identify tampering in AI models.
no code implementations • 25 Jun 2023 • Yangchen Xie, Xinyuan Chen, Hongjian Zhan, Palaiahankote Shivakum, Bing Yin, Cong Liu, Yue Lu
A large number of annotated training images is crucial for training successful scene text recognition models.
no code implementations • CVPR 2023 • Congqi Cao, Yue Lu, Peng Wang, Yanning Zhang
At present, it is the largest semi-supervised VAD dataset with the largest number of scenes and classes of anomalies, the longest duration, and the only one considering the scene-dependent anomaly.
no code implementations • 8 May 2023 • Jiajun Wei, Hongjian Zhan, Xiao Tu, Yue Lu, Umapada Pal
Inspired by ITC, the SITM network combines the visual features and the text features of all candidates to identify the candidate with the minimum distance in the feature space.
no code implementations • 3 Apr 2023 • WenBo Hu, Hongjian Zhan, Xinchen Ma, Cong Liu, Bing Yin, Yue Lu
In the field of historical manuscript research, scholars frequently encounter novel symbols in ancient texts, investing considerable effort in their identification and documentation.
no code implementations • 15 Mar 2023 • Congqi Cao, Yizhe WANG, Yue Lu, Xin Zhang, Yanning Zhang
Existing works in this field mainly suffer from two weaknesses: (1) They often neglect the multi-label case and only focus on temporal modeling.
1 code implementation • 30 Dec 2022 • Xinyuan Chen, Yangchen Xie, Li Sun, Yue Lu
Moreover, we introduce contrastive self-supervised learning to learn a robust style representation for fonts by understanding the similarity and dissimilarities of fonts.
1 code implementation • 7 Sep 2022 • Congqi Cao, Yue Lu, Yanning Zhang
For the context recovery stream, we propose a spatiotemporal U-Net which can fully utilize the motion information to predict the future frame.
Ranked #1 on Anomaly Detection on Corridor
1 code implementation • 23 Jul 2022 • Zhiheng Wu, Yue Lu, Xingyu Chen, Zhengxing Wu, Liwen Kang, Junzhi Yu
In this work, we propose a novel OWOD problem called Unknown-Classified Open World Object Detection (UC-OWOD).
no code implementations • 21 Jul 2022 • Dajian Zhong, Shujing Lyu, Palaiahnakote Shivakumara, Bing Yin, Jiajia Wu, Umapada Pal, Yue Lu
For target images (scene text images), the Semantic Generator Module generates simple semantic features that share the same feature distribution with support images (clear text images).
no code implementations • 9 Apr 2022 • Yue Lu, Gang Mei, Francesco Piccialli
To address the above problem, in this paper, we propose a deep learning method using physics-informed neural networks (PINN) to predict the excess pore water pressure of two-dimensional soil consolidation.
no code implementations • 15 Nov 2021 • Yue Lu, Congqi Cao, Yanning Zhang
In this paper, we propose a novel distance-based VAD method to take advantage of all the available normal data efficiently and flexibly.
no code implementations • 29 Sep 2021 • Ze Wang, Yue Lu, Qiang Qiu
We introduce Meta-OLE, a new geometry-regularized method for fast adaptation to novel tasks in few-shot image classification.
1 code implementation • CVPR 2021 • Yangchen Xie, Xinyuan Chen, Li Sun, Yue Lu
Font generation is a challenging problem especially for some writing systems that consist of a large number of characters and has attracted a lot of attention in recent years.
no code implementations • 20 Mar 2021 • Congqi Cao, Yue Lu, Yifan Zhang, Dongmei Jiang, Yanning Zhang
Inspired from 2D criss-cross attention used in segmentation task, we propose a recurrent 3D criss-cross attention (RCCA-3D) module to model the dense long-range spatiotemporal contextual information in video for action recognition.
no code implementations • 31 Dec 2020 • Hongjian Wang, Qi Li, Lanbo Zhang, Yue Lu, Steven Yoo, Srinivas Vadrevu, Zhenhui Li
Historical features are important in ads click-through rate (CTR) prediction, because they account for past engagements between users and ads.
no code implementations • 4 Mar 2020 • Xingyu Chen, Yue Lu, Zhengxing Wu, Junzhi Yu, Li Wen
According to our analysis, five key discoveries are reported: 1) Domain quality has an ignorable effect on within-domain convolutional representation and detection accuracy; 2) low-quality domain leads to higher generalization ability in cross-domain detection; 3) low-quality domain can hardly be well learned in a domain-mixed learning process; 4) degrading recall efficiency, restoration cannot improve within-domain detection accuracy; 5) visual restoration is beneficial to detection in the wild by reducing the domain shift between training data and real-world scenes.
no code implementations • 18 Oct 2019 • Jie Zhang, Yuping Duan, Yue Lu, Michael K. Ng, Huibin Chang
In this paper, we propose new operator-splitting algorithms for the total variation regularized infimal convolution (TV-IC) model [4] in order to remove mixed Poisson-Gaussian(MPG) noise.
no code implementations • 20 Apr 2019 • Qingqing Wang, Wenjing Jia, Xiangjian He, Yue Lu, Michael Blumenstein, Ye Huang
Scene text recognition has recently been widely treated as a sequence-to-sequence prediction problem, where traditional fully-connected-LSTM (FC-LSTM) has played a critical role.
no code implementations • 16 Oct 2018 • Yue Lu, Yun Zhou, Zhuqing Jiang, Xiaoqiang Guo, Zixuan Yang
Convolutional neural networks (CNNs) have demonstrated superior performance in super-resolution (SR).
no code implementations • 9 Oct 2017 • Hongjian Zhan, Qingqing Wang, Yue Lu
Recurrent neural network (RNN) and connectionist temporal classification (CTC) have showed successes in many sequence labeling tasks with the strong ability of dealing with the problems where the alignment between the inputs and the target labels is unknown.