publications
- journal:
- jing-yu liu, yan-ming zhang, fei yin, cheng-lin liu, transformer-based stroke relation encoding for online handwriting and sketches, pattern recognition, 148: 110131, 2024.
- ayan banerjee, p. shivakumara, s. bhattacharya, umapada pal, cheng-lin liu, an end-to-end model for multi-view scene text recognition, pattern recognition, 149: 110206, 2024.
- yuqi wang, xu-yao zhang, cheng-lin liu, tieniu tan, zhaoxiang zhang, emergence of machine language: towards symbolic intelligence with neural networks, national science review, 11: nwa317, 2024.
- yue xu, xu-yao zhang, zhaoxiang zhang, cheng-lin liu, large-scale continual learning for ancient chinese character recognition, pattern recognition, 150: 110283, 2024.
- ke xiao, anna zhu, brian kenji iwata, cheng-lin liu, scene text recognition via dual character counting-aware visual and semantic modeling network, science china information sciences, 67(3): 139101, 2024.
- ming-ming yu, heng zhang, cheng-lin liu, an approach for handwritten chinese text recognition unifying character segmentation and recognition, pattern recognition, 15: 110373, 2024.
- yunfei guo, wei feng, fei yin, cheng-lin liu, signparser: an end-to-end framework for traffic sign understanding, international journal of computer vision, 135: 805-821, 2024.
- fei zhu, xu-yao zhang, zhen cheng, cheng-lin liu, revisiting confidence estimation: towards reliable failure prediction, ieee trans. pattern analysis and machine intelligence, 46(5): 3370-3387, 2024.
- jun-bo zhang, wei feng, meng-biao zhao, fei yin, xu-yao zhang, cheng-lin liu, video text detection with robust feature representation, ieee trans. circuits and systems for video technology, 34(6): 4407-4420, 2024.
- zhen cheng, xu-yao zhang, cheng-lin liu, unifying classification and rejection: a one-versus-all framework, machine intelligence research, accepted, 2024.
- hao-ru tan, chuang wang, sitong wu, xu-yao zhang, fei yin, cheng-lin liu, ensemble quadratic assignment network for graph matching, int. j. computer vision, accepted, feb. 2024.
- jia-man tang, hong-yu guo, jin-wen wu, fei yin, lin-lin huang, offline handwritten mathematical expression recognition with graph encoder and transformer decoder, pattern recognition, 148: 110155, 2024.
- lenghuan meng, chuang wang, training dynamics of nonlinear contrastive learning model in the high dimensional limit, ieee signal processing letters, 2024, doi: 10.1109/lsp.2024.3434392
- conferences:
- jun-bo zhang, meng-biao zhao, fei yin, cheng-lin liu, sequential transformer for end-to-end video text detection, ieee/cvf winter conference on applications of computer vision (wacv 2024), waikoloa, hawaii, usa, jan 4-8, 2024, pp.6520-6530.
- xiang ao, xio-hui li, xu-yao zhang, cheng-lin liu, prototype calibration with synthesized samples for zero-shot chinese character recognition, proc. icassp 2024, seoul, korea, april 14-19, 2024, pp.6295-6299.
- zhengqing gao, xu-yao zhang, cheng-lin liu, unified entropy optimization for open-set test-time adaptation, ieee/cvf computer vision and pattern recognition conference (cvpr 2024), seattle, usa, june 17-21, 2024.
- fei zhu, xu-yao zhang, cheng-lin liu, zhaoxiang zhang, rcl: reliable continual learning for unified failure detection, ieee/cvf computer vision and pattern recognition conference (cvpr 2024), seattle, usa, june 17-21, 2024.
- shijie ma, xu-yao zhang, cheng-lin liu, active generalized category discovery, ieee/cvf computer vision and pattern recognition conference (cvpr 2024), seattle, usa, june 17-21, 2024.
- he-sen dai, xiao-hui li, fei yin, xu-dong yang, shu-qi mei, cheng-lin liu, graphmllm: a graph-based multi-level layout language-independent model for document understanding, 18th icdar, athens, greece, august 30-september 4, 2024.
- yangyang liu, yi chen, fei yin, cheng-lin liu, context-aware confidence estimation for rejection in handwritten chinese text recognition, 18th icdar, athens, greece, august 30-september 4, 2024.
- lu-rong ling, heng zhang, fei yin, cheng-lin liu, deep metric learning with cross-writer attention for offline signature verification, 18th icdar, athens, greece, august 30-september 4, 2024.
- chun-bo xu, yi-ming chen, cheng-lin liu, entitylayout: entity-level pre-training language model for semantic entity recognition and relation extraction, 18th icdar, athens, greece, august 30-september 4, 2024.
- arnab hadler, shivakumara palaiahnakote, umapada pal, michael blumenstein, cheng-lin liu, a new unsupervised approach text localization in shaky and non-shaky scene video, 18th icdar, athens, greece, august 30-september 4, 2024.
- tianzhuo li, heng zhang, xiaohui li, fei yin, adaptive scaling and refined pyramid feature fusion network for scene text segmentation, 18th icdar, athens, greece, august 30-september 4, 2024.
- xin yang, fei yin, yan ming zhang, xudong yan, and tao xue. document specular highlight removal with coarse to fine strategy, 18th icdar, athens, greece, august 30-september 4, 2024.
- zhong-zhi, li, ming-liang zhang, fei yin, cheng-lin liu, lans: a layout-aware neural solver for plane geometry problem, findings of acl, 2024.
- jiaxin zhang, zhong-zhi li, ming-liang zhang, fei yin, cheng-lin liu, yashar moshfeghi, findings of acl, 2024.
- xin-jian wu, ruisong zhang, jie qin, shijie ma, cheng-lin liu, wps-sam: towards weakly-supervised part segmentation with foundation models, eccv 2024, milano, italy, september 29-october 4, 2024.
- haiyang guo, fei zhu, wenzhuo liu, xu-yao zhang, cheng-lin liu, pilora: prototype guided incremental lora for federated class-incremental learning, eccv 2024, milano, italy, september 29-october 4, 2024.
- zhengqing gao, xiang ao, xu-yao zhang, cheng-lin liu, adapting vision-language models to open classes via test-time prompt tuning, the 7th chinese conference on pattern recognition and computer vision (prcv 2024), urumqi, china, october 18-20, 2024.