publications
- journal:
- ming-liang zhang, xu-yao zhang, chuang wang, cheng-lin liu, towards prior gap and representation gap for long-tailed recognition, pattern recognition, 133: 109312, 2023.
- chang liu, chun yang, hai-bo qin, xiaobin zhu, cheng-lin liu, xu-cheng yin, towards open-set text recognition via label-to-prototype learning, pattern recognition, 134: 109109, 2023.
- zhen cheng, fei zhu, xu-yao zhang, cheng-lin liu, adversarial training with distribution normalization and margin balance, pattern recognition, 136: 109182, 2023.
- xu-yao zhang, guo-sen xie, xiuli li, tao mei, cheng-lin liu, a survey on learning to reject, proceedings of the ieee, 111(2): 185-215, 2023.
- rui-qi wang, fei zhu, xu-yao zhang, cheng-lin liu, training with scaled logits to alleviate class-level over-fitting in few-shot learning, neurocomputing, 522: 142-151, 2023.
- yu-ting yang, yan-ming zhang, xiao-long yun, fei yin, cheng-lin liu, dygat: dynamic stroke classification of online handwritten documents and sketches, pattern recognition, 141: 109564, 2023.
- mengbiao zhao, wei feng, fei yin, cheng-lin liu, texts as points: scene text detection with point supervision, pattern recognition letters, 170: 1-8, 2023.
- fei zhu, zhen cheng, xu-yao zhang, cheng-lin liu, imitating the oracle: towards calibrated model for class incremental learning, neural networks, 164: 38-48, 2023.
- lintai wu, yong xu, junhui hou, c.l. philip chen, cheng-lin liu, a two-level rectification attention network for scene text recognition, ieee trans. multimedia, 25(6): 2404-2414, 2023.
- fei zhu, xu-yao zhang, rui-qi wang, cheng-lin liu, learning by seeing more classes, ieee trans. pattern analysis and machine intelligence, 45(6): 7477-7493, 2023.
- zhuo chen, fei yin, qing yang, cheng-lin liu, cross-lingual text image recognition via multi-hierarchy cross-modal mimic, ieee trans. multimedia, 25: 4830-4841, 2022.
- p. shivakumara, ayan banerjee, umapada pal, lokesh nandanwar, tong lu, cheng-lin liu, a new language-independent deep cnn for scene text detection and style transfer in social media images, ieee trans. image processing, 32: 3552-3566, 2023.
- jiao zhang, chuang wang, xu-yao zhang, cheng-lin liu, deep representation learning for domain generalization with information bottleneck principle, pattern recognition, 143: 109737, 2023.
- xiu-chuan li, xiaobo xia, fei zhu, tongliang liu, xu-yao zhang, cheng-lin liu, dynamics-aware loss for learning with label noise, pattern recognition, 144: 109835, 2023.
- ruisong zhang, chuang wang, cheng-lin liu, cycle-consistent weakly supervised visual grounding with individual and contextual representations, ieee trans. image processing, 32: 5167-5180, august 2023.
- kunal biswas, p. shivakumara, umapada pal, cheng-lin liu, yue lu, vqapt: a new visual question answering model for personality traits in social media images, pattern recognition letters, 175: 66-73, 2023.
- p. shivakumara, ayush roy, lokesh nandanwar, umapada pal, yue lu, cheng-lin liu, a new lightweight script independent scene text style transfer network, int. j. pattern recognition and artificial intelligence, 37(13): 235303, 2023.
- jianhui chen, zuoren wang, cheng-lin liu, lateral interaction by laplacian-based graph smoothing for deep neural networks, caai trans. intelligence technology, 8(4): 1590-1607, 2023.
- guo-sen xie, xu-yao zhang, tian-zhu xiang, fang zhao, zheng zhang, ling shao, xuelong li. leveraging balanced semantic embedding for generative zero-shot learning. ieee trans. neural networks and learning systems, 34(11): 9575-9582, november 2023.
- guo-feng luo, da-han wang, xia du, hua-yi yin, xu-yao zhang, shunzhi zhu. self-information of radicals: a new clue for zero-shot chinese character recognition. pattern recognition, 140: 109598, august 2023.
- 朱飞、张煦尧、刘成林，类别增量学习研究进展和性能评价，自动化学报，49(3): 635-660, 2023. fei zhu, xu-yao zhang, cheng-lin liu. class incremental learning: a review and performance evaluation. acta automatica sinica, 2023, 49(3): 635−660.
- 杨春、刘畅、方治屿、韩铮、刘成林、殷绪成，开放集文字识别技术，中国图象图形学报，28(6): 1767-1791, 2023. yang chun， liu chang， fang zhiyu， han zheng， liu chenglin， yin xucheng. 2023. open set text recognition technology. journal of image and graphics, 28(06): 1767-1791, 2023.
- 刘成林、金连文、白翔、李晓辉、殷飞，文档智能分析与识别前沿：回顾与展望，中国图象图形学报，28(08): 2223-2252, 2023. liu chenglin, jin lianwen, bai xiang, li xiaohui, yin fei, frontiers of intelligent document analysis and recognition: review and prospects, chinese journal of image and graphics, 28(08): 2223-2252, 2023.
- 刘成林，“面向开放环境的自适应感知研究进展”专辑序言，模式识别与人工智能，36 (12): i-iv, 2023.
- 袁晓彤, 张煦尧, 刘希, 程真, 刘成林，面向开放环境的机器学习理论研究进展，模式识别与人工智能，36 (12): 1059-1071, 2023.
- 张煦尧, 袁晓彤, 刘成林，变化环境自适应感知与学习研究进展，模式识别与人工智能，36 (12): 1072-1086, 2023.
- 张知诚, 杨巨峰, 程明明, 林巍峣, 汤进, 李成龙, 刘成林，属性知识引导的自适应视觉感知与结构理解研究进展，模式识别与人工智能，36 (12): 1104-1126，2023.
- conferences:
- yunfei guo, fei yin, wei feng, xudong yan, tao xue, shuqi mei, cheng-lin liu, social relation reasoning based on triangular constraints, the thirty-seventh aaai conference on artificial intelligence (aaai-23), february 7-14, 2023, washington dc, usa, pp.737-745.
- jing-yu liu, yan-ming zhang, fei yin, cheng-lin liu, streaming stroke classification of online handwriting, icassp 2023, rhodes island, june 4-10, 2023.
- fei zhu, zhen cheng, xu-yao zhang, cheng-lin liu, openmix: exploring outlier samples for misclassification detection, the ieee/cvf conference on computer vision and pattern recognition 2023 (cvpr 2023), vancouver, canada, june 18-22, 2022, pp.12074-12083.
- xin-jian wu, xiang ao, rui-song zhang, cheng-lin liu, structural recognition of handwritten chinese characters using a modified part capsule auto-encoder, caai international conference on artificial intelligence (cicai), fuzhou, july 22-23, 2023, springer, lnai 14473, pp.478-490, 2024.
- yi chen, heng zhang, cheng-lin liu, improved learning for online handwritten chinese text recognition with convolutional prototype network, 17th icdar, san jose, ca, august 21-26, 2023, lncs 14190, pp.38-53.
- yi-ming chen, xiang-ting hou, dong-fang lou, zhi-lin liao, cheng-lin liu, damgcn: entity linking in visually rich documents with dependency-aware multimodal graph, 17th icdar, san jose, ca, august 21-26, 2023, lncs 14189, pp.33-47.
- zhenru pan, zhilong ji, xiao liu, jinfeng bai, cheng-lin liu, visa: visual and semantic alignment for robust scene text recognition, 17th icdar, san jose, ca, august 21-26, 2023, lncs 14188, pp.223-242.
- wenwen yu, chengquan zhang, haoyu cao, wei hua, bohan li, huang chen, mingyu liu, mingrui chen, jianfeng kuang, mengjun cheng, yuning du, shikun feng, xiaoguang hu, pengyuan lyu, kun yao, yuechen yu, yuliang liu, wanxiang che, errui ding, cheng-lin liu, jiebo luo, shuicheng yan, min zhang, dimosthenis karatzas, xing sun, jingdong wang and xiang bai, icdar 2023 competition on structured text extraction from visually-rich document images, 17th icdar, san jose, ca, august 21-26, 2023, lncs 14188, pp.536-552.
- chenyang gao, yuliang liu, shiyu yao, jinfeng bai, xiang bai, lianwen jin and cheng-lin liu, icdar 2023 competition on recognition of multi-line handwritten mathematical expressions, 17th icdar, san jose, ca, august 21-26, 2023, lncs 14188, pp.566-576.
- zhibo yang, xiaoge song, sibo song, tong lu, xiang bai, cheng-lin liu, fei huang, cong yao, icdar 2023 competition on born digital video text question answering, 17th icdar, san jose, ca, august 21-26, 2023, lncs 14188, pp.508-521.
- ming-liang zhang, fei yin, cheng-lin liu, a multi-modal neural geometric solver with textual clauses parsed from diagram, proceedings of the thirty-second international joint conference on artificial intelligence (ijcai-23), macau, china, august 19-25, pp.3374-3382.
- jiaqi zhang, cheng-lin liu and xiaoyi jiang, quadratic kernel learning for interpolation kernel machine based graph classification, 13th iapr-tc15 international workshop on graph-based representations in pattern recognition (gbr 2023), salerno, italy, sep 6-8, 2023, gbrpr 2023, lncs 14121, pp.3-14.
- jiaqi zhang, cheng-lin liu and xiaoyi jiang, interpolation kernel machines: reducing multiclass to binary, the 20th international conference on computer analysis of images and patterns (caip 2023), limassol, cyprus, sep. 25-28, 2023, caip 2023, lncs 14184, pp.174-184.
- yunfei guo, fei yin, xiao-hui li, xudong yan, tao xue, shuqi mei, cheng-lin liu, visual traffic knowledge graph generation from scene images, ieee/cvf international conference on computer vision (iccv 2023), paris, france, oct. 2-6, 2023, pp.21604-21613.
- min-si ren, yan-ming zhang, qiu-feng wang, fei yin, cheng-lin liu, diff-writer: a diffusion model based stylized online handwritten chinese character generator, proc. iconip 2023, changsha, nov. 20-23, 2023, ccis 1964, springer, pp.86-100.
- mengbiao zhao, fei yin, cheng-lin liu, scene text detection with box supervision and level set evolution, proc. 7th acpr, kitakyushu, japan, nov. 5-8, 2023, lncs 14406, p.179-203.
- shibo gao, jinmeng gong, peipei yang, chao liang, linlin huang. a stable long-term tracking method for group-housed pigs. international conference on image and graphics (icig), nanjing, china, sep. 22-24, 2023, pp. 238-249.
- ayush roy, p. shivakumara, umapada pal, shivanand s. gornale cheng-lin liu, a new lightweight attention-based model for emotion recognition on distorted social media face images, 7th acpr, kitakyushu, japan, nov. 5-8, 2023, lncs 14407, pp.243-257.
- runxi li, fei yin, lin-lin huang, dewarping document image in complex scene by geometric control points, 7th acpr, kitakyushu, japan, nov. 5-8, 2023, lncs 14407, pp.265-278.
- arxiv reports:
- ming-liang zhang, fei yin, cheng-lin liu, a multi-modal neural geometric solver with textual clauses parsed from diagram, arxiv:2302.11097v1, 22 feb 2023.
- zhen cheng, fei zhu, xu-yao zhang, cheng-lin liu, average of pruning: improving performance and stability of out-of-distribution detection, arxiv:2303.01201v1, 2 mar 2023.
- fei zhu, zhen cheng, xu-yao zhang, cheng-lin liu, openmix: exploring outlier samples for misclassification detection, arxiv:2303.17093v1, 30 mar 2023.
- zhen cheng, xu-yao zhang, cheng-lin liu, unified classification and rejection: a one-versus-all framework, arxiv:2311.12255, 22 nov 2023.