Search

Your search keyword '"Tang, Wenjian"' showing total 218 results
Start Over Author "Tang, Wenjian"
218 results on '"Tang, Wenjian"'

1. CLRNet: Cross Layer Refinement Network for Lane Detection

Author

Zheng, Tu, Huang, Yifei, Liu, Yang, Tang, Wenjian, Yang, Zheng, Cai, Deng, and He, Xiaofei

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

Lane is critical in the vision navigation system of the intelligent vehicle. Naturally, lane is a traffic sign with high-level semantics, whereas it owns the specific local pattern which needs detailed low-level features to localize accurately. Using different feature levels is of great importance for accurate lane detection, but it is still under-explored. In this work, we present Cross Layer Refinement Network (CLRNet) aiming at fully utilizing both high-level and low-level features in lane detection. In particular, it first detects lanes with high-level semantic features then performs refinement based on low-level features. In this way, we can exploit more contextual information to detect lanes while leveraging local detailed lane features to improve localization accuracy. We present ROIGather to gather global context, which further enhances the feature representation of lanes. In addition to our novel network design, we introduce Line IoU loss which regresses the lane line as a whole unit to improve the localization accuracy. Experiments demonstrate that the proposed method greatly outperforms the state-of-the-art lane detection approaches., Comment: CVPR2022 Acceptance

Published
2022

4. A Risk Evaluation Method of Unstable Slopes Using Multipoint Tilting Sensors

Author

Fukuhara, Makoto, Wang, Lin, Tao, Shangning, Tang, Zhijun, Tang, Wenjian, Dong, Linyao, Fan, Zhongjie, Alcántara-Ayala, Irasema, editor, Arbanas, Željko, editor, Cuomo, Sabatino, editor, Huntley, David, editor, Konagai, Kazuo, editor, Mihalić Arbanas, Snježana, editor, Mikoš, Matjaž, editor, Sassa, Kyoji, editor, Sassa, Shinji, editor, Tang, Huiming, editor, and Tiwari, Binod, editor

Published
2023
Full Text
View/download PDF

5. RESA: Recurrent Feature-Shift Aggregator for Lane Detection

Author

Zheng, Tu, Fang, Hao, Zhang, Yi, Tang, Wenjian, Yang, Zheng, Liu, Haifeng, and Cai, Deng

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

Lane detection is one of the most important tasks in self-driving. Due to various complex scenarios (e.g., severe occlusion, ambiguous lanes, etc.) and the sparse supervisory signals inherent in lane annotations, lane detection task is still challenging. Thus, it is difficult for the ordinary convolutional neural network (CNN) to train in general scenes to catch subtle lane feature from the raw image. In this paper, we present a novel module named REcurrent Feature-Shift Aggregator (RESA) to enrich lane feature after preliminary feature extraction with an ordinary CNN. RESA takes advantage of strong shape priors of lanes and captures spatial relationships of pixels across rows and columns. It shifts sliced feature map recurrently in vertical and horizontal directions and enables each pixel to gather global information. RESA can conjecture lanes accurately in challenging scenarios with weak appearance clues by aggregating sliced feature map. Moreover, we propose a Bilateral Up-Sampling Decoder that combines coarse-grained and fine-detailed features in the up-sampling stage. It can recover the low-resolution feature map into pixel-wise prediction meticulously. Our method achieves state-of-the-art results on two popular lane detection benchmarks (CULane and Tusimple). Code has been made available at: https://github.com/ZJULearning/resa.

Published
2020

22. Dual-Responsive Near-Infrared BODIPY-Based Fluorescent Probe for the Detection of F–and HClO in Organisms

Author

Mei, Yuan, Hai, Zijuan, Li, Ziyun, Rong, Kuanrong, Tang, Wenjian, and Song, Qin-Hua

Abstract

Fluoride anions (F–) play a crucial role in human physiological processes. However, excessive intake of F–would affect oxygen metabolism and promote the generation of oxygen-free radicals. Hence, it is essential to develop a precise and efficient fluorescent probe for visualizing F–-induced oxidative stress. In this work, we developed the first bifunctional BODIPY-based fluorescent probe dfBDP with p-tert-butyldimethylsilanolate benzyl thioether as the sensing site for the detection of F–and HClO via two distinct reactions, the self-immolative removal and the thioether oxidation, which generate the sensing products with two nonoverlap fluorescence bands: 800–1200 and 500–750 nm, respectively. The probe dfBDP displays rapid response, high specificity, and sensitivity for the detection of F–(LOD, 316.2 nM) and HClO (LOD, 33.9 nM) in vitro. Cellular imaging reveals a correlation between F–-induced oxidative stress and the upregulation of HClO. Finally, probe dfBDP was employed to detect F–and HClO in mice under the stimulation of F–. The experimental results display that the level of HClO elevates in the liver of mice.

Published
2024
Full Text
View/download PDF

23. Microtiter plate-based chemistry and in situ screening: SuFEx-enabled lead discovery of selective AChE inhibitors.

Author

Tang, Kun, Li, Huan-Huan, Wu, Chengyao, Zhang, Shi-Long, Yang, Jian-Guo, Tang, Wenjian, and Qin, Hua-Li

Subjects
SECONDARY amines, SULFONAMIDES, LEAD compounds, TROPANES, COGNITION disorders, SULFUR
Abstract

Sulphur fluoride exchange (SuFEx) is a category of click chemistry that enables covalent linking of modular units through sulphur connective hubs. Here, we reported an efficient synthesis and in situ screening method for building a library of sulphonamides on the picomolar scale by SuFEx reaction between a sulphonyl fluoride (RSO2F) core and primary or secondary amines. This biocompatible SuFEx reaction would allow us to rapidly synthesise sulphonamide molecules, and evaluate their ChE inhibitory activity. Compound T14-A24 was identified as a reversible, competitive, and selective AChE inhibitor (Ki = 22 nM). The drug-like evaluation showed that T14-A24 had benign BBB penetration, remarkable neuroprotective effect, and safe toxicological profile. In vivo behavioural study showed that T14-A24 treatment improved the Aβ1 − 42-induced cognitive impairment, significantly prevented the effects of Aβ1 − 42 toxicity. Therefore, this SuFEx click reaction can accelerate the discovery of lead compounds. [ABSTRACT FROM AUTHOR]

Published
2023
Full Text
View/download PDF

24. A BODIPY-based fluorescent probe for simultaneous detection of H2O2 and viscosity during the pyroptosis process.

Author

Mei, Yuan, Li, Ziyun, Rong, Kuanrong, Hai, Zijuan, Tang, Wenjian, and Song, Qin-Hua

Subjects
FLUORESCENT probes, PYROPTOSIS, VISCOSITY, PALMITIC acid, INTRAMOLECULAR proton transfer reactions, STAINS & staining (Microscopy), BLOOD substitutes
Abstract

A dual functional BODIPY fluorescent probe was developed for simultaneous detection of H2O2 and viscosity, by collecting fluorescence from 800–1100 nm and 550–750 nm, respectively. Bioimaging based on the probe shows that H2O2 accumulates and cytoplasmic viscosity increases during the palmitic acid (PA)-induced pyroptosis process. [ABSTRACT FROM AUTHOR]

Published
2023
Full Text
View/download PDF

29. ZJUNlict: RoboCup 2014 Small Size League Champion

Author

Li, Chuan, Xiong, Rong, Ren, Zeyu, Tang, Wenjian, Zhao, Yue, Goebel, Randy, Series editor, Tanaka, Yuzuru, Series editor, Wahlster, Wolfgang, Series editor, Bianchi, Reinaldo A. C., editor, Akin, H. Levent, editor, Ramamoorthy, Subramanian, editor, and Sugiura, Komei, editor

Published
2015
Full Text
View/download PDF

40. RESA: Recurrent Feature-Shift Aggregator for Lane Detection

Author

Zheng, Tu, Fang, Hao, Zhang, Yi, Tang, Wenjian, Yang, Zheng, Liu, Haifeng, and Cai, Deng

Subjects
FOS: Computer and information sciences, Computer Vision and Pattern Recognition (cs.CV), Computer Science - Computer Vision and Pattern Recognition, ComputerApplications_COMPUTERSINOTHERSYSTEMS, General Medicine
Abstract

Lane detection is one of the most important tasks in self-driving. Due to various complex scenarios (e.g., severe occlusion, ambiguous lanes, etc.) and the sparse supervisory signals inherent in lane annotations, lane detection task is still challenging. Thus, it is difficult for the ordinary convolutional neural network (CNN) to train in general scenes to catch subtle lane feature from the raw image. In this paper, we present a novel module named REcurrent Feature-Shift Aggregator (RESA) to enrich lane feature after preliminary feature extraction with an ordinary CNN. RESA takes advantage of strong shape priors of lanes and captures spatial relationships of pixels across rows and columns. It shifts sliced feature map recurrently in vertical and horizontal directions and enables each pixel to gather global information. RESA can conjecture lanes accurately in challenging scenarios with weak appearance clues by aggregating sliced feature map. Moreover, we propose a Bilateral Up-Sampling Decoder that combines coarse-grained and fine-detailed features in the up-sampling stage. It can recover the low-resolution feature map into pixel-wise prediction meticulously. Our method achieves state-of-the-art results on two popular lane detection benchmarks (CULane and Tusimple). Code has been made available at: https://github.com/ZJULearning/resa.

Published
2021

Catalog

Books, media, physical & digital resources
See catalog results