default search action
BibTeX records: Dong Liang 0008
@article{DBLP:journals/pr/KangWLDD26,
author = {Bin Kang and
Zongyu Wang and
Dong Liang and
Tianyu Ding and
Songlin Du},
title = {Robust unsupervised visual tracking via image-to-video identity knowledge
transferring},
journal = {Pattern Recognit.},
volume = {171},
pages = {112109},
year = {2026}
}
@article{DBLP:journals/jvcir/JiangLLD25,
author = {Qimin Jiang and
Xiaoyong Lu and
Dong Liang and
Songlin Du},
title = {SemMatcher: Semantic-aware feature matching with neighborhood consensus},
journal = {J. Vis. Commun. Image Represent.},
volume = {113},
pages = {104611},
year = {2025}
}
@article{DBLP:journals/pami/LiangGLXHC25,
author = {Dong Liang and
Yuanhang Gao and
Ling Li and
Zhengyan Xu and
Sheng{-}Jun Huang and
Songcan Chen},
title = {Aesthetics-Guided Low-Light Enhancement},
journal = {{IEEE} Trans. Pattern Anal. Mach. Intell.},
volume = {47},
number = {7},
pages = {5866--5883},
year = {2025}
}
@article{DBLP:journals/pami/ZhouLCH25,
author = {Yuyan Zhou and
Dong Liang and
Songcan Chen and
Sheng{-}Jun Huang},
title = {Image Lens Flare Removal Using Adversarial Curve Learning},
journal = {{IEEE} Trans. Pattern Anal. Mach. Intell.},
volume = {47},
number = {9},
pages = {7396--7409},
year = {2025}
}
@article{DBLP:journals/spl/ZhuQL25,
author = {Xinjia Zhu and
Xinyuan Qian and
Dong Liang},
title = {{SSDQ:} Target Speaker Extraction via Semantic and Spatial Dual Querying},
journal = {{IEEE} Signal Process. Lett.},
volume = {32},
pages = {3167--3171},
year = {2025}
}
@article{DBLP:journals/tgrs/SunLLCH25,
author = {Yue Sun and
Dong Liang and
Shao{-}Yuan Li and
Songcan Chen and
Sheng{-}Jun Huang},
title = {Handling Noisy Annotation for Remote Sensing Semantic Segmentation
via Boundary-Aware Knowledge Distillation},
journal = {{IEEE} Trans. Geosci. Remote. Sens.},
volume = {63},
pages = {1--20},
year = {2025}
}
@article{DBLP:journals/tgrs/WangYLH25,
author = {Qianqian Wang and
Haibo Ye and
Dong Liang and
Sheng{-}Jun Huang},
title = {Diffusion-Noise-Based Augmentation for Long-Tailed Remote Sensing
Image Classification},
journal = {{IEEE} Trans. Geosci. Remote. Sens.},
volume = {63},
pages = {1--14},
year = {2025}
}
@article{DBLP:journals/tmm/LiangZWWZ25,
author = {Dong Liang and
Dong Zhang and
Qiong Wang and
Zongqi Wei and
Liyan Zhang},
title = {CrossNet: Cross-Scene Background Subtraction Network via 3D Optical
Flow},
journal = {{IEEE} Trans. Multim.},
volume = {27},
pages = {693--706},
year = {2025}
}
@inproceedings{DBLP:conf/aaai/LiLDH25,
author = {Yachao Li and
Dong Liang and
Tianyu Ding and
Sheng{-}Jun Huang},
title = {StructSR: Refuse Spurious Details in Real-World Image Super-Resolution},
booktitle = {{AAAI}},
pages = {5022--5030},
publisher = {{AAAI} Press},
year = {2025}
}
@inproceedings{DBLP:conf/icassp/LaiQ0Q25,
author = {Yantao Lai and
Rong Quan and
Dong Liang and
Jie Qin},
title = {CLIPGaze: Zero-Shot Goal-Directed Scanpath Prediction Using {CLIP}},
booktitle = {{ICASSP}},
pages = {1--5},
publisher = {{IEEE}},
year = {2025}
}
@inproceedings{DBLP:conf/ijcai/GengLWLCY25,
author = {Chuanxing Geng and
Qifei Li and
Xinrui Wang and
Dong Liang and
Songcan Chen and
Pong C. Yuen},
title = {LoD: Loss-difference {OOD} Detection by Intentionally Label-Noisifying
Unlabeled Wild Data},
booktitle = {{IJCAI}},
pages = {5217--5225},
publisher = {ijcai.org},
year = {2025}
}
@article{DBLP:journals/corr/abs-2501-05777,
author = {Yachao Li and
Dong Liang and
Tianyu Ding and
Sheng{-}Jun Huang},
title = {StructSR: Refuse Spurious Details in Real-World Image Super-Resolution},
journal = {CoRR},
volume = {abs/2501.05777},
year = {2025}
}
@article{DBLP:journals/corr/abs-2505-12952,
author = {Chuanxing Geng and
Qifei Li and
Xinrui Wang and
Dong Liang and
Songcan Chen and
Pong C. Yuen},
title = {LoD: Loss-difference {OOD} Detection by Intentionally Label-Noisifying
Unlabeled Wild Data},
journal = {CoRR},
volume = {abs/2505.12952},
year = {2025}
}
@article{DBLP:journals/corr/abs-2508-07022,
author = {Shengtao Wen and
Haodong Chen and
Yadong Wang and
Zhongying Pan and
Xiang Chen and
Yu Tian and
Bo Qian and
Dong Liang and
Sheng{-}Jun Huang},
title = {MultiMedEdit: {A} Scenario-Aware Benchmark for Evaluating Knowledge
Editing in Medical {VQA}},
journal = {CoRR},
volume = {abs/2508.07022},
year = {2025}
}
@article{DBLP:journals/chinaf/LiangSDCH24,
author = {Dong Liang and
Yue Sun and
Yun Du and
Songcan Chen and
Sheng{-}Jun Huang},
title = {Relative difficulty distillation for semantic segmentation},
journal = {Sci. China Inf. Sci.},
volume = {67},
number = {9},
year = {2024}
}
@article{DBLP:journals/cviu/WuHSLL24,
author = {Pingfan Wu and
Hengyi Huang and
Han Sun and
Dong Liang and
Ningzhong Liu},
title = {{CPRNC:} Channels pruning via reverse neuron crowding for model compression},
journal = {Comput. Vis. Image Underst.},
volume = {240},
pages = {103942},
year = {2024}
}
@article{DBLP:journals/ijcv/LiangXLWC24,
author = {Dong Liang and
Zhengyan Xu and
Ling Li and
Mingqiang Wei and
Songcan Chen},
title = {{PIE:} Physics-Inspired Low-Light Enhancement},
journal = {Int. J. Comput. Vis.},
volume = {132},
number = {9},
pages = {3911--3932},
year = {2024}
}
@article{DBLP:journals/jei/ZhouWLP24,
author = {Wenjun Zhou and
Nan Wang and
Dong Liang and
Bo Peng},
title = {Precision in visual object tracking: a dual-branch approach},
journal = {J. Electronic Imaging},
volume = {33},
number = {2},
year = {2024}
}
@article{DBLP:journals/pr/KangDLWL24,
author = {Bin Kang and
Songlin Du and
Dong Liang and
Fan Wu and
Xin Li},
title = {Fine-grained recognition via submodular optimization regulated progressive
training},
journal = {Pattern Recognit.},
volume = {156},
pages = {110849},
year = {2024}
}
@article{DBLP:journals/sensors/GuoGHQL24,
author = {Yi Guo and
Yuanhang Gao and
Bingliang Hu and
Xueming Qian and
Dong Liang},
title = {{CMID:} Crossmodal Image Denoising via Pixel-Wise Deep Reinforcement
Learning},
journal = {Sensors},
volume = {24},
number = {1},
pages = {42},
year = {2024}
}
@article{DBLP:journals/sivp/ZhouLWLP24,
author = {Wenjun Zhou and
Yao Liu and
Nan Wang and
Dong Liang and
Bo Peng},
title = {Efficient Siamese model for visual object tracking with attention-based
fusion modules},
journal = {Signal Image Video Process.},
volume = {18},
number = {11},
pages = {7801--7810},
year = {2024}
}
@article{DBLP:journals/tim/FanWLCXWLW24,
author = {Yihua Fan and
Yongzhen Wang and
Dong Liang and
Yiping Chen and
Haoran Xie and
Fu Lee Wang and
Jonathan Li and
Mingqiang Wei},
title = {Low-FaceNet: Face Recognition-Driven Low-Light Image Enhancement},
journal = {{IEEE} Trans. Instrum. Meas.},
volume = {73},
pages = {1--13},
year = {2024}
}
@article{DBLP:journals/tits/SheLWLCXW24,
author = {Yutong She and
Peng Li and
Mingqiang Wei and
Dong Liang and
Yiping Chen and
Haoran Xie and
Fu Lee Wang},
title = {eViTBins: Edge-Enhanced Vision-Transformer Bins for Monocular Depth
Estimation on Edge Devices},
journal = {{IEEE} Trans. Intell. Transp. Syst.},
volume = {25},
number = {12},
pages = {20320--20334},
year = {2024}
}
@article{DBLP:journals/vc/ZhaoLCWHL24,
author = {Xinyue Zhao and
Quanzhi Li and
Yue Chao and
Quanyou Wang and
Zaixing He and
Dong Liang},
title = {RT-less: a multi-scene {RGB} dataset for 6D pose estimation of reflective
texture-less objects},
journal = {Vis. Comput.},
volume = {40},
number = {8},
pages = {5187--5200},
year = {2024}
}
@inproceedings{DBLP:conf/eccv/QuanLQL24,
author = {Rong Quan and
Yantao Lai and
Mengyu Qiu and
Dong Liang},
title = {Pathformer3D: {A} 3D Scanpath Transformer for {\textdollar}360{\^{}}\{{\textbackslash}circ
\}{\textdollar} Images},
booktitle = {{ECCV} {(35)}},
series = {Lecture Notes in Computer Science},
volume = {15093},
pages = {73--90},
publisher = {Springer},
year = {2024}
}
@inproceedings{DBLP:conf/icic/GaoZFL24,
author = {Yuanhang Gao and
Qi Zhu and
Yutian Fu and
Dong Liang},
title = {Aesthetics-Driven Active Reinforcement Learning for Color Enhancement},
booktitle = {{ICIC} {(11)}},
series = {Lecture Notes in Computer Science},
volume = {14872},
pages = {289--300},
publisher = {Springer},
year = {2024}
}
@inproceedings{DBLP:conf/icic/XuLDL24,
author = {Zhengyan Xu and
Yachao Li and
Feng Dong and
Dong Liang},
title = {Beyond the Limits: Tackling Extreme Overexposure with Diffusion Model},
booktitle = {{ICIC} {(11)}},
series = {Lecture Notes in Computer Science},
volume = {14872},
pages = {301--312},
publisher = {Springer},
year = {2024}
}
@article{DBLP:journals/corr/abs-2404-04586,
author = {Dong Liang and
Zhengyan Xu and
Ling Li and
Mingqiang Wei and
Songcan Chen},
title = {{PIE:} Physics-inspired Low-light Enhancement},
journal = {CoRR},
volume = {abs/2404.04586},
year = {2024}
}
@article{DBLP:journals/corr/abs-2407-03719,
author = {Dong Liang and
Yue Sun and
Yun Du and
Songcan Chen and
Sheng{-}Jun Huang},
title = {Relative Difficulty Distillation for Semantic Segmentation},
journal = {CoRR},
volume = {abs/2407.03719},
year = {2024}
}
@article{DBLP:journals/corr/abs-2407-10563,
author = {Rong Quan and
Yantao Lai and
Mengyu Qiu and
Dong Liang},
title = {Pathformer3D: {A} 3D Scanpath Transformer for 360{\textdegree} Images},
journal = {CoRR},
volume = {abs/2407.10563},
year = {2024}
}
@article{DBLP:journals/ijon/YiLLZLL23,
author = {Zexiang Yi and
Jing Lian and
Qidong Liu and
Hegui Zhu and
Dong Liang and
Jizhao Liu},
title = {Learning rules in spiking neural networks: {A} survey},
journal = {Neurocomputing},
volume = {531},
pages = {163--179},
year = {2023}
}
@article{DBLP:journals/sensors/QuanXL23,
author = {Rong Quan and
Biaoyi Xu and
Dong Liang},
title = {Discriminatively Unsupervised Learning Person Re-Identification via
Considering Complicated Images},
journal = {Sensors},
volume = {23},
number = {6},
pages = {3259},
year = {2023}
}
@article{DBLP:journals/tgrs/LiangZTH23,
author = {Dong Liang and
Jing{-}Wei Zhang and
Ying{-}Peng Tang and
Sheng{-}Jun Huang},
title = {{MUS-CDB:} Mixed Uncertainty Sampling With Class Distribution Balancing
for Active Annotation in Aerial Object Detection},
journal = {{IEEE} Trans. Geosci. Remote. Sens.},
volume = {61},
pages = {1--13},
year = {2023}
}
@article{DBLP:journals/tifs/ZhuXFLZZZ23,
author = {Qi Zhu and
Guangnan Xin and
Lunke Fei and
Dong Liang and
Zheng Zhang and
Daoqiang Zhang and
David Zhang},
title = {Contactless Palmprint Image Recognition Across Smartphones With Self-Paced
CycleGAN},
journal = {{IEEE} Trans. Inf. Forensics Secur.},
volume = {18},
pages = {4944--4954},
year = {2023}
}
@article{DBLP:journals/tnn/KangLMTZZ23,
author = {Bin Kang and
Dong Liang and
Junxi Mei and
Xiaoyang Tan and
Quan Zhou and
Dengyin Zhang},
title = {Robust {RGB-T} Tracking via Graph Attention-Based Bilinear Pooling},
journal = {{IEEE} Trans. Neural Networks Learn. Syst.},
volume = {34},
number = {12},
pages = {9900--9911},
year = {2023}
}
@article{DBLP:journals/vc/ZhaoWHLZT23,
author = {Xinyue Zhao and
Guangli Wang and
Zaixing He and
Dong Liang and
Shuyou Zhang and
Jianrong Tan},
title = {Unsupervised inner-point-pairs model for unseen-scene and online moving
object detection},
journal = {Vis. Comput.},
volume = {39},
number = {4},
pages = {1391--1407},
year = {2023}
}
@inproceedings{DBLP:conf/icassp/LiYLD23,
author = {Dongyue Li and
Yaping Yan and
Dong Liang and
Songlin Du},
title = {{MSFORMER:} Multi-Scale Transformer with Neighborhood Consensus for
Feature Matching},
booktitle = {{ICASSP}},
pages = {1--5},
publisher = {{IEEE}},
year = {2023}
}
@inproceedings{DBLP:conf/iccv/ZhouLCHYL23,
author = {Yuyan Zhou and
Dong Liang and
Songcan Chen and
Sheng{-}Jun Huang and
Shuo Yang and
Chongyi Li},
title = {Improving Lens Flare Removal with General-Purpose Pipeline and Multiple
Light Sources Recovery},
booktitle = {{ICCV}},
pages = {12923--12933},
publisher = {{IEEE}},
year = {2023}
}
@inproceedings{DBLP:conf/ijcai/LiLGHC23,
author = {Ling Li and
Dong Liang and
Yuanhang Gao and
Sheng{-}Jun Huang and
Songcan Chen},
title = {{ALL-E:} Aesthetics-guided Low-light Image Enhancement},
booktitle = {{IJCAI}},
pages = {1062--1070},
publisher = {ijcai.org},
year = {2023}
}
@inproceedings{DBLP:conf/ismar/QiuRLT23,
author = {Mengyu Qiu and
Quan Rong and
Dong Liang and
Huawei Tu},
title = {Visual ScanPath Transformer: Guiding Computers to See the World},
booktitle = {{ISMAR}},
pages = {223--232},
publisher = {{IEEE}},
year = {2023}
}
@inproceedings{DBLP:conf/smc/ZhouWLP23,
author = {Wenjun Zhou and
Nan Wang and
Dong Liang and
Bo Peng},
title = {Visual Tracking Based on Efficient Dual-Branch Siamese Network},
booktitle = {{SMC}},
pages = {3677--3682},
publisher = {{IEEE}},
year = {2023}
}
@article{DBLP:journals/corr/abs-2303-14075,
author = {Mingqiang Wei and
Qian Sun and
Haoran Xie and
Dong Liang and
Fu Lee Wang},
title = {Search By Image: Deeply Exploring Beneficial Features for Beauty Product
Retrieval},
journal = {CoRR},
volume = {abs/2303.14075},
year = {2023}
}
@article{DBLP:journals/corr/abs-2304-14610,
author = {Ling Li and
Dong Liang and
Yuanhang Gao and
Sheng{-}Jun Huang and
Songcan Chen},
title = {{ALL-E:} Aesthetics-guided Low-light Image Enhancement},
journal = {CoRR},
volume = {abs/2304.14610},
year = {2023}
}
@article{DBLP:journals/corr/abs-2308-16460,
author = {Yuyan Zhou and
Dong Liang and
Songcan Chen and
Sheng{-}Jun Huang and
Shuo Yang and
Chongyi Li},
title = {Improving Lens Flare Removal with General Purpose Pipeline and Multiple
Light Sources Recovery},
journal = {CoRR},
volume = {abs/2308.16460},
year = {2023}
}
@article{DBLP:journals/corr/abs-2309-14764,
author = {Fan Li and
Dong Liang and
Jing Lian and
Qidong Liu and
Hegui Zhu and
Jizhao Liu},
title = {InvKA: Gait Recognition via Invertible Koopman Autoencoder},
journal = {CoRR},
volume = {abs/2309.14764},
year = {2023}
}
@article{DBLP:journals/cgf/ZhengSYLWYGX22,
author = {Chengyu Zheng and
Ding Shi and
Xuefeng Yan and
Dong Liang and
Mingqiang Wei and
Xin Yang and
Yanwen Guo and
Haoran Xie},
title = {GlassNet: Label Decoupling-based Three-stream Neural Network for Robust
Image Glass Detection},
journal = {Comput. Graph. Forum},
volume = {41},
number = {1},
pages = {377--388},
year = {2022}
}
@article{DBLP:journals/mta/LiangGSZK22,
author = {Dong Liang and
Qixiang Geng and
Han Sun and
Huiyu Zhou and
Shun'ichi Kaneko},
title = {Inferred box harmonization and aggregation for degraded face detection
in crowds},
journal = {Multim. Tools Appl.},
volume = {81},
number = {24},
pages = {35411--35430},
year = {2022}
}
@article{DBLP:journals/staeors/WeiLZZGWZ22,
author = {Zongqi Wei and
Dong Liang and
Dong Zhang and
Liyan Zhang and
Qixiang Geng and
Mingqiang Wei and
Huiyu Zhou},
title = {Learning Calibrated-Guidance for Object Detection in Aerial Images},
journal = {{IEEE} J. Sel. Top. Appl. Earth Obs. Remote. Sens.},
volume = {15},
pages = {2721--2733},
year = {2022}
}
@article{DBLP:journals/tgrs/LiangGWVKWZ22,
author = {Dong Liang and
Qixiang Geng and
Zongqi Wei and
Dmitry A. Vorontsov and
Ekaterina L. Kim and
Mingqiang Wei and
Huiyu Zhou},
title = {Anchor Retouching via Model Interaction for Robust Object Detection
in Aerial Images},
journal = {{IEEE} Trans. Geosci. Remote. Sens.},
volume = {60},
pages = {1--13},
year = {2022}
}
@inproceedings{DBLP:conf/aaai/0008LWYZYD022,
author = {Dong Liang and
Ling Li and
Mingqiang Wei and
Shuo Yang and
Liyan Zhang and
Wenhan Yang and
Yun Du and
Huiyu Zhou},
title = {Semantically Contrastive Learning for Low-Light Image Enhancement},
booktitle = {{AAAI}},
pages = {1555--1563},
publisher = {{AAAI} Press},
year = {2022}
}
@inproceedings{DBLP:conf/aaai/ZhuL0YLCWQ22,
author = {Hongwei Zhu and
Peng Li and
Haoran Xie and
Xuefeng Yan and
Dong Liang and
Dapeng Chen and
Mingqiang Wei and
Jing Qin},
title = {I Can Find You! Boundary-Guided Separated Attention Network for Camouflaged
Object Detection},
booktitle = {{AAAI}},
pages = {3608--3616},
publisher = {{AAAI} Press},
year = {2022}
}
@inproceedings{DBLP:conf/icassp/ShenFWLQXW22,
author = {Yiyang Shen and
Yidan Feng and
Weiming Wang and
Dong Liang and
Jing Qin and
Haoran Xie and
Mingqiang Wei},
title = {MBA-RainGAN: {A} Multi-Branch Attention Generative Adversarial Network
for Mixture of Rain Removal},
booktitle = {{ICASSP}},
pages = {3418--3422},
publisher = {{IEEE}},
year = {2022}
}
@inproceedings{DBLP:conf/pricai/Du0QDY22,
author = {Yun Du and
Dong Liang and
Rong Quan and
Songlin Du and
Yaping Yan},
title = {More Than Accuracy: An Empirical Study of Consistency Between Performance
and Interpretability},
booktitle = {{PRICAI} {(3)}},
series = {Lecture Notes in Computer Science},
volume = {13631},
pages = {579--590},
publisher = {Springer},
year = {2022}
}
@article{DBLP:journals/corr/abs-2210-15950,
author = {Huajian Si and
Zeyong Wei and
Zhe Zhu and
Honghua Chen and
Dong Liang and
Weiming Wang and
Mingqiang Wei},
title = {{LBF:} Learnable Bilateral Filter For Point Cloud Denoising},
journal = {CoRR},
volume = {abs/2210.15950},
year = {2022}
}
@article{DBLP:journals/corr/abs-2212-02804,
author = {Dong Liang and
Jing{-}Wei Zhang and
Ying{-}Peng Tang and
Sheng{-}Jun Huang},
title = {{MUS-CDB:} Mixed Uncertainty Sampling with Class Distribution Balancing
for Active Annotation in Aerial Object Detection},
journal = {CoRR},
volume = {abs/2212.02804},
year = {2022}
}
@article{DBLP:journals/iet-ipr/SunCL0021,
author = {Han Sun and
Jun Cen and
Ningzhong Liu and
Dong Liang and
Huiyu Zhou},
title = {{MPI:} Multi-receptive and parallel integration for salient object
detection},
journal = {{IET} Image Process.},
volume = {15},
number = {13},
pages = {3281--3291},
year = {2021}
}
@article{DBLP:journals/pr/LiangKLGTK21,
author = {Dong Liang and
Bin Kang and
Xinyu Liu and
Pan Gao and
Xiaoyang Tan and
Shun'ichi Kaneko},
title = {Cross-scene foreground segmentation with supervised and unsupervised
model communication},
journal = {Pattern Recognit.},
volume = {117},
pages = {107995},
year = {2021}
}
@inproceedings{DBLP:conf/ccbr/GengL21,
author = {Qixiang Geng and
Dong Liang},
title = {Holistic Co-occurrence Prior for High-Density Face Detection},
booktitle = {{CCBR}},
series = {Lecture Notes in Computer Science},
volume = {12878},
pages = {307--315},
publisher = {Springer},
year = {2021}
}
@inproceedings{DBLP:conf/fgr/GengLZZSL21,
author = {Qixiang Geng and
Dong Liang and
Huiyu Zhou and
Liyan Zhang and
Han Sun and
Ningzhong Liu},
title = {Dense Face Detection via High-level Context Mining},
booktitle = {{FG}},
pages = {1--8},
publisher = {{IEEE}},
year = {2021}
}
@inproceedings{DBLP:conf/icassp/LiangKLSZL21,
author = {Dong Liang and
Bin Kang and
Xinyu Liu and
Han Sun and
Liyan Zhang and
Ningzhong Liu},
title = {Cross Scene Video Foreground Segmentation Via Co-Occurrence Probability
Oriented Supervised and Unsupervised Model Interaction},
booktitle = {{ICASSP}},
pages = {1795--1799},
publisher = {{IEEE}},
year = {2021}
}
@inproceedings{DBLP:conf/icassp/LiangDSZLW21,
author = {Dong Liang and
Yun Du and
Han Sun and
Liyan Zhang and
Ningzhong Liu and
Mingqiang Wei},
title = {Nlkd: Using Coarse Annotations For Semantic Segmentation Based on
Knowledge Distillation},
booktitle = {{ICASSP}},
pages = {2335--2339},
publisher = {{IEEE}},
year = {2021}
}
@inproceedings{DBLP:conf/icassp/DengZP0K21,
author = {Yuheng Deng and
Wenjun Zhou and
Bo Peng and
Dong Liang and
Shun'ichi Kaneko},
title = {Robust Spatial-Temporal Correlation Model for Background Initialization
in Severe Scene},
booktitle = {{ICASSP}},
pages = {2415--2419},
publisher = {{IEEE}},
year = {2021}
}
@inproceedings{DBLP:conf/icmcs/0008WS021,
author = {Dong Liang and
Zongqi Wei and
Han Sun and
Huiyu Zhou},
title = {Robust Cross-Scene Foreground Segmentation in Surveillance Video},
booktitle = {{ICME}},
pages = {1--6},
publisher = {{IEEE}},
year = {2021}
}
@article{DBLP:journals/corr/abs-2103-11399,
author = {Dong Liang and
Zongqi Wei and
Dong Zhang and
Qixiang Geng and
Liyan Zhang and
Huiyu Zhou and
Mingqiang Wei},
title = {Learning Calibrated-Guidance for Object Detection in Aerial Images},
journal = {CoRR},
volume = {abs/2103.11399},
year = {2021}
}
@article{DBLP:journals/corr/abs-2108-03618,
author = {Han Sun and
Jun Cen and
Ningzhong Liu and
Dong Liang and
Huiyu Zhou},
title = {{MPI:} Multi-receptive and Parallel Integration for Salient Object
Detection},
journal = {CoRR},
volume = {abs/2108.03618},
year = {2021}
}
@article{DBLP:journals/corr/abs-2108-11117,
author = {Chengyu Zheng and
Ding Shi and
Xuefeng Yan and
Dong Liang and
Mingqiang Wei and
Xin Yang and
Yanwen Guo and
Haoran Xie},
title = {GlassNet: Label Decoupling-based Three-stream Neural Network for Robust
Image Glass Detection},
journal = {CoRR},
volume = {abs/2108.11117},
year = {2021}
}
@article{DBLP:journals/corr/abs-2112-06451,
author = {Dong Liang and
Ling Li and
Mingqiang Wei and
Shuo Yang and
Liyan Zhang and
Wenhan Yang and
Yun Du and
Huiyu Zhou},
title = {Semantically Contrastive Learning for Low-light Image Enhancement},
journal = {CoRR},
volume = {abs/2112.06451},
year = {2021}
}
@article{DBLP:journals/corr/abs-2112-06701,
author = {Dong Liang and
Qixiang Geng and
Zongqi Wei and
Dmitry A. Vorontsov and
Ekaterina L. Kim and
Mingqiang Wei and
Huiyu Zhou},
title = {Anchor Retouching via Model Interaction for Robust Object Detection
in Aerial Images},
journal = {CoRR},
volume = {abs/2112.06701},
year = {2021}
}
@article{DBLP:journals/access/SunFSLLZ20,
author = {Han Sun and
Yejia Fan and
Jiaquan Shen and
Ningzhong Liu and
Dong Liang and
Huiyu Zhou},
title = {A Novel Semantics-Preserving Hashing for Fine-Grained Image Retrieval},
journal = {{IEEE} Access},
volume = {8},
pages = {26199--26209},
year = {2020}
}
@article{DBLP:journals/access/SunYSLLZ20,
author = {Han Sun and
Jian Yang and
Jiaquan Shen and
Dong Liang and
Ningzhong Liu and
Huiyu Zhou},
title = {TIB-Net: Drone Detection Network With Tiny Iterative Backbone},
journal = {{IEEE} Access},
volume = {8},
pages = {130697--130707},
year = {2020}
}
@article{DBLP:journals/access/CenSCLL020,
author = {Jun Cen and
Han Sun and
Xinyi Chen and
Ningzhong Liu and
Dong Liang and
Huiyu Zhou},
title = {WFNet: {A} Wider and Finer Network for Salient Object Detection},
journal = {{IEEE} Access},
volume = {8},
pages = {210418--210428},
year = {2020}
}
@article{DBLP:journals/iet-ipr/XiangLKA20,
author = {Sheng Xiang and
Dong Liang and
Shun'ichi Kaneko and
Hirokazu Asano},
title = {Robust defect detection in 2D images printed on 3D micro-textured
surfaces by multiple paired pixel consistency in orientation codes},
journal = {{IET} Image Process.},
volume = {14},
number = {14},
pages = {3373--3384},
year = {2020}
}
@article{DBLP:journals/itiis/SunGSL0Z20,
author = {Han Sun and
Wen Geng and
Jiaquan Shen and
Ningzhong Liu and
Dong Liang and
Huiyu Zhou},
title = {Deeper {SSD:} Simultaneous Up-sampling and Down-sampling for Drone
Detection},
journal = {{KSII} Trans. Internet Inf. Syst.},
volume = {14},
number = {12},
pages = {4795--4815},
year = {2020}
}
@article{DBLP:journals/sensors/SunCWLLZ20,
author = {Han Sun and
Xinyi Chen and
Ling Wang and
Dong Liang and
Ningzhong Liu and
Huiyu Zhou},
title = {{C2DAN:} An Improved Deep Adaptation Network with Domain Confusion
and Classifier Adaptation},
journal = {Sensors},
volume = {20},
number = {12},
pages = {3606},
year = {2020}
}
@article{DBLP:journals/tip/KangLDZZ20,
author = {Bin Kang and
Dong Liang and
Wan Ding and
Huiyu Zhou and
Wei{-}Ping Zhu},
title = {Grayscale-Thermal Tracking via Inverse Sparse Representation-Based
Collaborative Encoding},
journal = {{IEEE} Trans. Image Process.},
volume = {29},
pages = {3401--3415},
year = {2020}
}
@inproceedings{DBLP:conf/icpr/LiangL20,
author = {Dong Liang and
Xinyu Liu},
title = {Coarse-to-fine Foreground Segmentation based on Co-occurrence Pixel-Block
and Spatio-Temporal Attention Model},
booktitle = {{ICPR}},
pages = {3807--3813},
publisher = {{IEEE}},
year = {2020}
}
@inproceedings{DBLP:conf/visapp/XiangKL20,
author = {Sheng Xiang and
Shun'ichi Kaneko and
Dong Liang},
title = {Robust Method for Detecting Defect in Images Printed on 3D Micro-textured
Surfaces: Modified Multiple Paired Pixel Consistency},
booktitle = {{VISIGRAPP} {(5:} {VISAPP)}},
pages = {260--267},
publisher = {{SCITEPRESS}},
year = {2020}
}
@article{DBLP:journals/corr/abs-2003-12931,
author = {Wenjun Zhou and
Yuheng Deng and
Bo Peng and
Dong Liang and
Shun'ichi Kaneko},
title = {Co-occurrence Background Model with Superpixels for Robust Background
Initialization},
journal = {CoRR},
volume = {abs/2003.12931},
year = {2020}
}
@article{DBLP:journals/corr/abs-2005-10582,
author = {Yiyang Shen and
Yidan Feng and
Sen Deng and
Dong Liang and
Jing Qin and
Haoran Xie and
Mingqiang Wei},
title = {MBA-RainGAN: Multi-branch Attention Generative Adversarial Network
for Mixture of Rain Removal from Single Images},
journal = {CoRR},
volume = {abs/2005.10582},
year = {2020}
}
@article{DBLP:journals/pr/KangZLC19,
author = {Bin Kang and
Wei{-}Ping Zhu and
Dong Liang and
Mingkai Chen},
title = {Robust visual tracking via nonlocal regularized multi-view sparse
representation},
journal = {Pattern Recognit.},
volume = {88},
pages = {75--89},
year = {2019}
}
@article{DBLP:journals/sensors/LiangPSZ19,
author = {Dong Liang and
Jiaxing Pan and
Han Sun and
Huiyu Zhou},
title = {Spatio-Temporal Attention Model for Foreground Detection in Cross-Scene
Surveillance Videos},
journal = {Sensors},
volume = {19},
number = {23},
pages = {5142},
year = {2019}
}
@article{DBLP:journals/sigpro/ZhouKHSL19,
author = {Wenjun Zhou and
Shun'ichi Kaneko and
Manabu Hashimoto and
Yutaka Satoh and
Dong Liang},
title = {Foreground detection based on co-occurrence background model with
hypothesis on degradation modification in dynamic scenes},
journal = {Signal Process.},
volume = {160},
pages = {66--79},
year = {2019}
}
@article{DBLP:journals/tcsv/GaoXL19,
author = {Pan Gao and
Wei Xiang and
Dong Liang},
title = {Texture-Distortion-Constrained Joint Source-Channel Coding of Multi-View
Video Plus Depth-Based 3D Video},
journal = {{IEEE} Trans. Circuits Syst. Video Technol.},
volume = {29},
number = {11},
pages = {3326--3340},
year = {2019}
}
@inproceedings{DBLP:conf/icassp/WuLPSKKZ19,
author = {Tianpeng Wu and
Dong Liang and
Jiaxing Pan and
Han Sun and
Bin Kang and
Shun'ichi Kaneko and
Huiyu Zhou},
title = {Score-specific Non-maximum Suppression and Coexistence Prior for Multi-scale
Face Detection},
booktitle = {{ICASSP}},
pages = {1957--1961},
publisher = {{IEEE}},
year = {2019}
}
@inproceedings{DBLP:conf/icip/WuLPK19,
author = {Tianpeng Wu and
Dong Liang and
Jiaxing Pan and
Shun'ichi Kaneko},
title = {Context-Anchors for Hybrid Resolution Face Detection},
booktitle = {{ICIP}},
pages = {3297--3301},
publisher = {{IEEE}},
year = {2019}
}
@inproceedings{DBLP:conf/icpr/ZhouKHSL18,
author = {Wenjun Zhou and
Shun'ichi Kaneko and
Manabu Hashimoto and
Yutaka Satoh and
Dong Liang},
title = {A Co-occurrence Background Model with Hypothesis on Degradation Modification
for Object Detection in Strong Background Changes},
booktitle = {{ICPR}},
pages = {1743--1748},
publisher = {{IEEE} Computer Society},
year = {2018}
}
@inproceedings{DBLP:conf/visapp/ZhouKHSL18,
author = {Wenjun Zhou and
Shun'ichi Kaneko and
Manabu Hashimoto and
Yutaka Satoh and
Dong Liang},
title = {Co-occurrence Background Model with Hypothesis on Degradation Modification
for Robust Object Detection},
booktitle = {{VISIGRAPP} {(5:} {VISAPP)}},
pages = {266--273},
publisher = {SciTePress},
year = {2018}
}
@article{DBLP:journals/iet-ipr/KangZL17,
author = {Bin Kang and
Wei{-}Ping Zhu and
Dong Liang},
title = {Robust multi-feature visual tracking via multi-task kernel-based sparse
learning},
journal = {{IET} Image Process.},
volume = {11},
number = {12},
pages = {1172--1178},
year = {2017}
}
@inproceedings{DBLP:conf/ccbr/PanL17,
author = {Jiaxing Pan and
Dong Liang},
title = {Holistic Crowd Interaction Modelling for Anomaly Detection},
booktitle = {{CCBR}},
series = {Lecture Notes in Computer Science},
volume = {10568},
pages = {642--649},
publisher = {Springer},
year = {2017}
}
@inproceedings{DBLP:conf/icip/LiangKSK17,
author = {Dong Liang and
Shun'ichi Kaneko and
Han Sun and
Bin Kang},
title = {Adaptive local spatial modeling for online change detection under
abrupt dynamic background},
booktitle = {{ICIP}},
pages = {2020--2024},
publisher = {{IEEE}},
year = {2017}
}
@inproceedings{DBLP:conf/icip/KangLZ17,
author = {Bin Kang and
Dong Liang and
Suofei Zhang},
title = {Robust visual tracking via multi-view discriminant based sparse representation},
booktitle = {{ICIP}},
pages = {2587--2591},
publisher = {{IEEE}},
year = {2017}
}
@article{DBLP:journals/ijon/ZhaoHZL15,
author = {Xinyue Zhao and
Zaixing He and
Shuyou Zhang and
Dong Liang},
title = {A sparse-representation-based robust inspection system for hidden
defects classification in casting components},
journal = {Neurocomputing},
volume = {153},
pages = {1--10},
year = {2015}
}
@article{DBLP:journals/jrm/LiangKS15,
author = {Dong Liang and
Shun'ichi Kaneko and
Yutaka Satoh},
title = {A Robust Appearance Model and Similarity Measure for Image Matching},
journal = {J. Robotics Mechatronics},
volume = {27},
number = {2},
pages = {126--135},
year = {2015}
}
@article{DBLP:journals/pr/LiangKHIZ15,
author = {Dong Liang and
Shun'ichi Kaneko and
Manabu Hashimoto and
Kenji Iwata and
Xinyue Zhao},
title = {Co-occurrence probability-based pixel pairs background model for robust
object detection in dynamic scenes},
journal = {Pattern Recognit.},
volume = {48},
number = {4},
pages = {1374--1390},
year = {2015}
}
@article{DBLP:journals/pr/ZhaoHZL15,
author = {Xinyue Zhao and
Zaixing He and
Shuyou Zhang and
Dong Liang},
title = {Robust pedestrian detection in thermal infrared imagery using a shape
distribution histogram feature and modified sparse representation
classification},
journal = {Pattern Recognit.},
volume = {48},
number = {6},
pages = {1947--1960},
year = {2015}
}
@article{DBLP:journals/corr/LiangK14a,
author = {Dong Liang and
Shun'ichi Kaneko},
title = {Improvements and Experiments of a Compact Statistical Background Model},
journal = {CoRR},
volume = {abs/1405.6275},
year = {2014}
}
@inproceedings{DBLP:conf/avss/LiangKHIZS13,
author = {Dong Liang and
Shun'ichi Kaneko and
Manabu Hashimoto and
Kenji Iwata and
Xinyue Zhao and
Yutaka Satoh},
title = {Co-occurrence-based adaptive background model for robust object detection},
booktitle = {{AVSS}},
pages = {401--406},
publisher = {{IEEE} Computer Society},
year = {2013}
}
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.
last updated on 2025-11-09 23:11 CET by the dblp team
all metadata released as open data under CC0 1.0 license
see also: Terms of Use | Privacy Policy | Imprint
dblp was originally created in 1993 at:
since 2018, dblp has been operated and maintained by:
the dblp computer science bibliography is funded and supported by: