no code implementations • 20 Mar 2024 • Xinyi He, Jiaru Zou, Yun Lin, Mengyu Zhou, Shi Han, Zejian yuan, Dongmei Zhang
Large Language Models (LLMs) have revolutionized code generation ability by converting natural language descriptions into executable code.
no code implementations • 11 Jan 2024 • Bin Dou, Tianyu Zhang, Yongjia Ma, Zhaohui Wang, Zejian yuan
We propose Compact and Swift Segmenting 3D Gaussians(CoSSegGaussians), a method for compact 3D-consistent scene segmentation at fast rendering speed with only RGB images input.
no code implementations • 21 Dec 2023 • Xinyi He, Mengyu Zhou, Xinrun Xu, Xiaojun Ma, Rui Ding, Lun Du, Yan Gao, Ran Jia, Xu Chen, Shi Han, Zejian yuan, Dongmei Zhang
We evaluate five state-of-the-art models using three different metrics and the results show that our benchmark presents introduces considerable challenge in the field of tabular data analysis, paving the way for more advanced research opportunities.
no code implementations • 15 Sep 2023 • Zhupeng Ye, Yinqi Li, Zejian yuan
This paper proposes a novel wide-range Pseudo-3D Vehicle Detection method based on images from a single camera and incorporates efficient learning methods.
no code implementations • 29 Aug 2023 • Ruijin Liu, Ning Lu, Dapeng Chen, Cheng Li, Zejian yuan, Wei Peng
We present PBFormer, an efficient yet powerful scene text detector that unifies the transformer with a novel text shape representation Polynomial Band (PB).
1 code implementation • 23 Aug 2023 • Lei Wang, Zejian yuan, Yao Lu, Badong Chen
We also propose a self-supervised learning approach to enhance the prediction ability of the tail-prefer feature representation branch by constraining tail-prefer predicate features.
no code implementations • 2 Sep 2022 • Xinyi He, Mengyu Zhou, Mingjie Zhou, Jialiang Xu, Xiao Lv, Tianle Li, Yijia Shao, Shi Han, Zejian yuan, Dongmei Zhang
Tabular data analysis is performed every day across various domains.
1 code implementation • 31 Dec 2021 • Ruijin Liu, Dapeng Chen, Tie Liu, Zhiliang Xiong, Zejian yuan
In this task, the correct camera pose is the key to generating accurate lanes, which can transform an image from perspective-view to the top-view.
Ranked #6 on 3D Lane Detection on Apollo Synthetic 3D Lane
no code implementations • 15 Nov 2020 • Zidong Guo, Zejian yuan, Chong Zhang, Wanchao Chi, Yonggen Ling, Shenghao Zhang
In domain adaption, we design an embedding representation with prediction consistency to ensure that the linear relationship between gaze directions in different domains remains consistent on gaze space and embedding space.
2 code implementations • 9 Nov 2020 • Ruijin Liu, Zejian yuan, Tie Liu, Zhiliang Xiong
To tackle these issues, we propose an end-to-end method that directly outputs parameters of a lane shape model, using a network built with a transformer to learn richer structures and context.
Ranked #20 on Lane Detection on TuSimple
no code implementations • 16 Jul 2020 • Ziyang Song, Zejian yuan, Chong Zhang, Wanchao Chi, Yonggen Ling, Shenghao Zhang
In recognition-based action interaction, robots' responses to human actions are often pre-designed according to recognized categories and thus stiff.
no code implementations • 2 Jul 2020 • Ziyang Song, Ziyi Yin, Zejian yuan, Chong Zhang, Wanchao Chi, Yonggen Ling, Shenghao Zhang
Despite the notable progress made in action recognition tasks, not much work has been done in action recognition specifically for human-robot interaction.
no code implementations • 24 May 2019 • Badong Chen, Yuqing Xie, Xin Wang, Zejian yuan, Pengju Ren, Jing Qin
In a recent work, the concept of mixture correntropy (MC) was proposed to improve the learning performance, where the kernel function is a mixture Gaussian kernel, namely a linear combination of several zero-mean Gaussian kernels with different widths.
no code implementations • 26 Oct 2018 • Zhihao Zhu, Zhan Xue, Zejian yuan
Recent progress on deep learning has made it possible to automatically transform the screenshot of Graphic User Interface (GUI) into code by using the encoder-decoder framework.
no code implementations • 23 Oct 2018 • Yuanliu Liu, Ang Li, Zejian yuan, Badong Chen, Nanning Zheng
We propose a Consistency-aware Selective Fusion (CSF) to integrate the pairwise orders into a globally consistent order.
no code implementations • 23 Oct 2018 • Yuanliu Liu, Zejian yuan
In this paper we propose an efficient way of user interaction that users need only to annotate the color composition of the image.
no code implementations • ECCV 2018 • Dapeng Chen, Hongsheng Li, Xihui Liu, Yantao Shen, Zejian yuan, Xiaogang Wang
Person re-identification is an important task that requires learning discriminative visual features for distinguishing different person identities.
Ranked #22 on Text based Person Retrieval on CUHK-PEDES
1 code implementation • 10 Jul 2018 • Zhihao Zhu, Zhan Xue, Zejian yuan
Attention mechanisms have attracted considerable interest in image captioning because of its powerful performance.
no code implementations • 3 Jul 2018 • Ang Li, Zejian yuan
Detecting the occlusion from stereo images or video frames is important to many computer vision applications.
no code implementations • 8 Jan 2018 • Jie Lyu, Zejian yuan, Dapeng Chen
For real-world driver drowsiness detection from videos, the variation of head pose is so large that the existing methods on global face is not capable of extracting effective features, such as looking aside and lowering head.
no code implementations • 19 Dec 2017 • Jie Lyu, Zejian yuan, Dapeng Chen
The network can learn to extract a sequence of local observations with detailed appearance and rough context, instead of sliding windows or convolutions on the entire image.
no code implementations • CVPR 2016 • Dapeng Chen, Zejian yuan, Badong Chen, Nanning Zheng
We therefore learn a novel similarity function, which consists of multiple sub-similarity measurements with each taking in charge of a subregion.
no code implementations • CVPR 2016 • Ang Li, Dapeng Chen, Yuanliu liu, Zejian yuan
While great progress has been made in stereo computation over the last decades, large textureless regions remain challenging.
no code implementations • ICCV 2015 • Yuanliu liu, Zejian yuan, Badong Chen, Jianru Xue, Nanning Zheng
In this paper we address the problem of inferring the color composition of the intrinsic reflectance of objects, where the shadows and highlights may change the observed color dramatically.
no code implementations • CVPR 2015 • Dapeng Chen, Zejian yuan, Gang Hua, Nanning Zheng, Jingdong Wang
We follow the learning-to-rank methodology and learn a similarity function to maximize the difference between the similarity scores of matched and unmatched images for a same person.
no code implementations • CVPR 2015 • Yuanliu Liu, Zejian yuan, Nanning Zheng, Yang Wu
Specular reflection generally decreases the saturation of surface colors, which will be possibly confused with other colors that have the same hue but lower saturation.
no code implementations • CVPR 2013 • Huaizu Jiang, Zejian yuan, Ming-Ming Cheng, Yihong Gong, Nanning Zheng, Jingdong Wang
Our method, which is based on multi-level image segmentation, utilizes the supervised learning approach to map the regional feature vector to a saliency score.