Search

Your search keyword '"Li, Shengjie"' showing total 1,292 results
Start Over Author "Li, Shengjie"
1,292 results on '"Li, Shengjie"'

3. The Behavior of Error Bounds via Moreau Envelopes

Author

Wang, Yu, Li, Shengjie, Hu, Yaohua, Li, Minghua, and Li, Xiaobing

Subjects
Mathematics - Optimization and Control
Abstract

In this paper, we first establish the equivalence of three types of error bounds: uniformized Kurdyka-{\L}ojasiewicz (u-KL) property, uniformized level-set subdifferential error bound (u-LSEB) and uniformized H\"{o}lder error bound (u-HEB) for prox-regular functions. Then we study the behavior of the level-set subdifferential error bound (LSEB) and the local H\"{o}lder error bound (LHEB) which is expressed respectively by Moreau envelopes, under suitable assumptions. Finally, in order to illustrate our main results and to compare them with those of recent references, some examples are also given., Comment: 12 pages

Published
2023

5. Multimodal Propaganda Processing

Author

Ng, Vincent and Li, Shengjie

Subjects
Computer Science - Computation and Language, Computer Science - Computer Vision and Pattern Recognition
Abstract

Propaganda campaigns have long been used to influence public opinion via disseminating biased and/or misleading information. Despite the increasing prevalence of propaganda content on the Internet, few attempts have been made by AI researchers to analyze such content. We introduce the task of multimodal propaganda processing, where the goal is to automatically analyze propaganda content. We believe that this task presents a long-term challenge to AI researchers and that successful processing of propaganda could bring machine understanding one important step closer to human understanding. We discuss the technical challenges associated with this task and outline the steps that need to be taken to address it., Comment: Accepted in AAAI 2023

Published
2023

7. End-to-End Neural Discourse Deixis Resolution in Dialogue

Author

Li, Shengjie and Ng, Vincent

Subjects
Computer Science - Computation and Language
Abstract

We adapt Lee et al.'s (2018) span-based entity coreference model to the task of end-to-end discourse deixis resolution in dialogue, specifically by proposing extensions to their model that exploit task-specific characteristics. The resulting model, dd-utt, achieves state-of-the-art results on the four datasets in the CODI-CRAC 2021 shared task., Comment: Accepted as a long paper to EMNLP 2022

Published
2022

11. Proximity-enabled covalent binding of IL-2 to IL-2Rα selectively activates regulatory T cells and suppresses autoimmunity

Author

Zhang, Bo, Sun, Jiaqi, Yuan, Yeshuang, Ji, Dezhong, Sun, Yeting, Liu, Yudong, Li, Shengjie, Zhu, Xingxing, Wu, Xunyao, Hu, Jin, Xie, Qiu, Wu, Ling, Liu, Lulu, Cheng, Boyang, Zhang, Yuanjie, Jiang, Lingjuan, Zhao, Lidan, Yu, Fei, Song, Wei, Wang, Min, Xu, Yue, Ma, Shiliang, Fei, Yunyun, Zhang, Lihe, Zhou, Demin, and Zhang, Xuan

Published
2023
Full Text
View/download PDF

27. Application of Plasma Spray Reactor to Inactivate the Osmotolerant Yeast Zygosaccharomyces rouxii in Apple Juice

Author

ZHANG Shaojun, ZHANG Wenle, ZHOU Jiajia, LI Shengjie, YUE Tianli, WANG Ying

Subjects
plasma spray reactor, osmotolerant yeast, apple juice, inactivation, Food processing and manufacture, TP368-456
Abstract

The inactivation effect of plasma spray reactor on Zygosaccharomyces rouxii in apple juice was studied as a function of plasma discharge voltages, gas flow rate and liquid flow rate, and the morphological changes of the cells and the effect of this treatment on apple juice quality were evaluated. In this study, a plasma spray reactor was used to treat 0.5 L of apple juice for 30 min at a discharge voltage of 21 kV, a gas flow rate of 150 L/h, and a liquid flow rate of 9.0 L/h. The number of osmotolerant yeast cells in apple juice decreased significantly. Plasma spray reactor treatment caused cell rupture, thus resulting in the inactivation of yeast cells. Under the optimal parameters, this treatment increased the pH of apple juice slightly, but did not cause any significant changes in the titratable acid or reducing sugar concentration (P > 0.05) and resulted in no significant changes in the major major volatile compounds in apple juice. This study may provide a reference for the application of plasma spray reactor in apple juice processing.

Published
2023
Full Text
View/download PDF

36. Segmenting Epipolar Line

Author

Li, Shengjie, Cai, Qi, and Wu, Yuanxin

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

Identifying feature correspondence between two images is a fundamental procedure in three-dimensional computer vision. Usually the feature search space is confined by the epipolar line. Using the cheirality constraint, this paper finds that the feature search space can be restrained to one of two or three segments of the epipolar line that are defined by the epipole and a so-called virtual infinity point., Comment: 5 pages, 6 figures

Published
2020

37. Clue: Cross-modal Coherence Modeling for Caption Generation

Author

Alikhani, Malihe, Sharma, Piyush, Li, Shengjie, Soricut, Radu, and Stone, Matthew

Subjects
Computer Science - Computation and Language, Computer Science - Computer Vision and Pattern Recognition
Abstract

We use coherence relations inspired by computational models of discourse to study the information needs and goals of image captioning. Using an annotation protocol specifically devised for capturing image--caption coherence relations, we annotate 10,000 instances from publicly-available image--caption pairs. We introduce a new task for learning inferences in imagery and text, coherence relation prediction, and show that these coherence annotations can be exploited to learn relation classifiers as an intermediary step, and also train coherence-aware, controllable image captioning models. The results show a dramatic improvement in the consistency and quality of the generated captions with respect to information needs specified via coherence relations., Comment: Accepted as a long paper to ACL 2020

Published
2020
Full Text
View/download PDF

38. SDOD:Real-time Segmenting and Detecting 3D Object by Depth

Author

Li, Shengjie, Xu, Caiyi, Xing, Jianping, Ning, Yafei, and Chen, Yonghong

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

Most existing instance segmentation methods only focus on improving performance and are not suitable for real-time scenes such as autonomous driving. This paper proposes a real-time framework that segmenting and detecting 3D objects by depth. The framework is composed of two parallel branches: one for instance segmentation and another for object detection. We discretize the objects' depth into depth categories and transform the instance segmentation task into a pixel-level classification task. The Mask branch predicts pixel-level depth categories, and the 3D branch indicates instance-level depth categories. We produce an instance mask by assigning pixels which have the same depth categories to each instance. In addition, to solve the imbalance between mask labels and 3D labels in the KITTI dataset, we introduce a coarse mask generated by the auto-annotation model to increase samples. Experiments on the challenging KITTI dataset show that our approach outperforms LklNet about 1.8 times on the speed of segmentation and 3D detection.

Published
2020

Catalog

Books, media, physical & digital resources
See catalog results