课题组近5年在多项国家自然科学基金项目的资助下，在多传感器图像/视频融合、单模态/多模态图像显著性目标检测、多模态图像语义分割、多模态医学图像分割、多模态目标跟踪、跨模态行人重识别、伪装目标检测等多模态图像处理及相关计算机视觉任务方面进行了深入、系统地研究，取得了一系列创新性研究成果。

• 基于伪装机制的伪装目标检测：从伪装机制的角度重新审视伪装目标检测任务，首次尝试以一种去伪装的方式发现目标物体。相应成果被IEEE TCSVT接收。

• 基于特征级模态补偿的可见光-红外跨模态行人重识别:在特征级而非图像级补偿缺失模态的特有信息, 通过补偿具有辨别力的模态特有特征来减小模态差异和丰富辨别特征，以利于跨模态行人重识别。相应成果被CVPR2022录取。

• 基于跨模态知识蒸馏的高效RGB-T目标跟踪：第一个基于深度卷积神经网络的端对端RGB-T显著性目标检测模型。提出一种跨模态知识蒸馏学习框架，并用于RGB-T目标跟踪中，相应成果被CVPR2023录取，并入选Highligh work（录取率为2.5%）。

• 基于多层卷积特征融合的RGB-T多模态图像显著目标检测：第一个基于深度卷积神经网络的端对端RGB-T显著性目标检测模型。相应成果已发表在《IEEE Transactions on Image Processing》。

• 基于质量感知的RGB-D显著性目标检测：相关成果发表在《IEEE Transactions on Multimedia》、《IEEETransactions on Circuits and Systems for Video Technology》等期刊。

• 轻量化RGB-D 显著性目标检测：首次从模型框架的角度进行RGB-D图像显著目标检测模型的轻量化设计,提出了一种新的中间层融合结构实现RGB-D图像显著性目检测。相应成果被《IEEE Transactions on Image Processing》期刊接收。

• 基于双向模态差异缩减的RGB-T多模态图像语义分割：相应成果已发表在《IEEE Conference on Computer Vision and Pattern Recognition》（2021），其扩展版被《IEEE Transactions on Neural Networks and Learning Systems》接收（2022）。

• 基于互补和干扰感知的RGB-T多模态图像目标跟踪：相应成果已发表在《IEEE Transactions on Circuits and Systems for Video Technology》。

• 基于多模态特征学习的MRI脑瘤图像分割：相应成果发表在《IEEE Transactions on Image Processing》, 《Pattern Recognition》等期刊。

• 基于二分流“部分-目标”匹配的深度显著性目标检测：首次将胶囊网络用于稠密预测视觉任务中。相应成果发表《IEEE International Conference on Computer Vision 2019》，其扩展版本被《IEEE Transactions on Pattern Analysis and Machine Intelligence》期刊接收。

部分成果如下：

【2024年】

²Nianchang Huang, Baichao Xing,Qiang Zhang*, Jungong Han, Jin Huang. Co-segmentation assisted cross-modality person re-identification,Information Fusion, 2024, 104: 102194.

【2023年】

²Yang Yang,Qiang Zhang*, Finding Camouflaged Objects along the Camouflage Mechanisms,IEEE Transactions on Circuits and Systems for Video Technology, 2023.DOI:10.1109/TCSVT.2023.3308964

²Qiang Zhang, Qi Qin, Yang Yang*, Qiang Jiao*, Jungong Han. Feature calibrating and fusing network for RGB-D salient object detection. IEEE Transactions on Circuits and Systems for Video Technology. 2023, DOI: 10.1109/TCSVT.2023.3296581. Accepted.

²张天路，张强*.基于深度学习的RGB-T目标跟踪技术综述.模式识别与人工智能, 2023, 36(4): 327-353.

²赵什陆，张强*.深度学习多模态图象语义分割前沿进展.中国图形图象学报，2023.

²Jianan Liu, Jian Liu,Qiang Zhang*, M2FINet:Modality-specific and Modality-shared Features Interaction Network for RGB-IR Person Re-Identification, Computer Vision and Image Understanding, 2023, 232:103708.

²Zixuan Ding, Ao Wang, Hui Chen,Qiang Zhang, Pengzhang Liu, Yongjun Bao, Weipeng Yan, Jungong Han. Exploring Structured Semantic Prior for Multi Label Recognition with Incomplete Labels, 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Vancouver, Canada, 2023.

²Tianlu Zhang, Hongyuan Guo, Qiao Jiao,Qiang Zhang*, Jungong Han. Effiecient RGB-T Tracking via Cross-Modality Distillation, 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Vancouver, Canada, 2023. (Highlight work, 2.5%)

²De Cheng, Gerong Wang, Bo Wang,Qiang Zhang*, Junong Han, Dingwen Zhang, Hybrid routing transformer for zero-shot learning,Pattern Recognition, 2023, 137: 109270.

²Nianchang Huang, Jianan Liu, Yunqi Miao,Qiang Zhang* and Jungong Han, Deep learning for visible-infrared cross-modality person re-identification: A comprehensive review,Information Fusion, 2023,91:396-411.

²Nianchang Huang, Jianan Liu, Yongjiang Luo,Qiang Zhang* and Jungong Han, Exploring modality-shared appearance features and modality-invariant relation features for cross-modality person re-identification,Pattern Recognition, 2023, 135:109145.

【2022年】

²Shenlu Zhao, Yichen Liu, Qiang Jiao,Qiang Zhang*, Jungong Han, Mitigating Modality Discrepancies for RGB-T Semantic Segmentation,IEEE Transactions on Neural Networks and Learning Systems, 2022. Accepted.

²Shenlu Zhao,Qiang Zhang*, A feature divide-and-conquer network for RGB-T semantic segmentation,IEEE Transactions on Circuits and Systems for Video Technology, 2022. DOI: 10.1109/TCSVT.2022.3229359.

²De Cheng, Gerong Wang, Bo Wang,Qiang Zhang*, Junong Han, Dingwen Zhang, Hybrid routing transformer for zero-shot learning,Pattern Recognition, 2022. DOI: https://doi.org/10.1016/j.patcog.2022.109270.

²Nianchang Huang, Jianan Liu, Yunqi Miao,Qiang Zhang* and Jungong Han, Deep learning for visible-infrared cross-modality person re-identification: A comprehensive review,Information Fusion, 2023,91:396-411. DOI:10.1016/j.inffus.2022.10.024.

²Nianchang Huang, Jianan Liu, Yongjiang Luo,Qiang Zhang* and Jungong Han, Exploring modality-shared appearance features and modality-invariant relation features for cross-modality person re-identification,Pattern Recognition, 2023, 135:109145. DOI:10.1016/j.patcog.2022.109 145.

²Nianchang Huang, Qiang Jiao,Qiang Zhang* ,Jungong Han. Middle-level Feature Fusion for Lightweight RGB-D Salient Object Detection,IEEE Transactions on Image Processing, 2022. DOI:10.1109/TIP.2022.3214092.

²Qiang Zhang, Ruida Xi, Tonglin Xiao, Nianchang Huang, Yongjiang Luo. Enabling modality interactions for RGB-T salient object detection.Computer Vision and Image Understanding, 2022, 222:102514.

²Qiang Zhang, Xueru Liu, Tianlu Zhang. RGB-T tracking by modality difference reduction and feature re-selection.Image and Vision Computing, 2022, 127: 104547.

²Nianchang Huang, Yongjiang Luo,Qiang Zhang*, Jungong Han. Discriminative Unimodal Feature Selection and Fusion for RGB-D Salient Object Detection,Pattern Recognition, 2022, 122: 108359.

²Nianchang Huang, Kunlong Liu, Yang Liu,Qiang Zhang*, Jungong Han*, Cross-modality person re-identification via multi-task learning,Pattern Recognition, 2022,128:108653-108653.

²Tianlu Zhang, Xueru Liu,Qiang Zhang*, Jungong Han*. SiamCDA: Complementarity- and distractor-aware RGB-T tracking based on Siamese network.IEEE Transactions on Circuits and Systems for Video Technology, 2022, 32(3): 1403 - 1417.

²Jianan Liu, Jialiang Wang, Nianchang Huang*,Qiang Zhang*, Jungong Han, Revisiting modality-specific feature compensation for visible-infrared person re-identification,IEEE Transactions on Circuits and Systems for Video Technology, 2022. Accepted. DOI：10.1109/TCSVT.2022.3168999.（中科院1区, Top）

²Yang Yang, Qi Qin, Yongjiang Luo, Yi Liu*,Qiang Zhang*, Jungong Han. Bi-directional progressive guidance network for RGB-D salient object detection.IEEE Transactions on Circuits and Systems for Video Technology, 2022. Accepted. Doi: 10.1109/TCSVT.2022.3144852.（中科院1区, Top）

²Qiang Zhang, Changzhou Lai, Jianan Liu, Nianchang Huang*, Jungong Han, FMCNet: feature-level modality compensation for visible-infrared person re-identification, Proceedings of the Conference on Computer Vision and Pattern Recognition (CVPR), 2022. Accepted. (CCF-A类，计算机视觉3大顶会之一)

²Qiang Zhang, Mingxing Duanmu, Yongjiang Luo, Yi Liu*, Jungong Han*. Engaging Part-whole Hierarchies and Contrast Cues for Salient Object Detection.IEEE Transactions on Circuits and Systems for Video Technology, 2022，32（6）：3644 - 3658. (中科院1区，Top)

²Yi Liu, Dingwen Zhang,Qiang Zhang*, Jungong Han*. Part-object relational visual saliency.IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022, 44 (7): 3688-3704.（中科院1区，Top）

²Nianchang Huang, Yang Yang, Dingwen Zhang,Qiang Zhang*, Jungong Han*. Employing bilinear fusion and saliency prior information for RGB-D salient object detection.IEEE Transactions on Multimedia, 2022, 24: 1651-1664.（中科院1区，Top）

【2021年】

²Qiang Zhang, Tonglin Xiao, Nianchang Huang, Dingwen Zhang, Jungong Han. Revisiting feature fusion for RGB-T salient object detection.IEEE Transactions on Circuits and Systems for Video Technology. 2021, 31(5):1804 - 1818.（中科院2区，检索号：WOS:000647394100011）

²Qiang Zhang, Fan Wang, Yongjiang Luo, Jungong Han. Exploring a unified low rank representation for multi-focus image fusion.Pattern Recognition, 2021, 113: 107752.（中科院1区，Top,检索号：WOS:000626268400005）

²Qiang Zhang, Shenlu Zhao, Yongjiang Luo, Dingwen Zhang, Nianchang Huang*, Jungong Han*. ABMDRNet: Adaptive-weighted bi-directional modality difference reduction network for RGB-T semantic segmentation. 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA, 2021: 2633-2642.

²Nianchang Huang, Yi Liu,Qiang Zhang*, Jungong Han*. Joint cross-modal and unimodal features for RGB-D salient object detection. IEEE Transactions on Multimedia, 2021,23: 2428-2441.

²Dingwen Zhang, Guohai Huang,Qiang Zhang*, Jungong Han*, Junwei Han, Yizhou Yu. Cross-modality deep feature learning for brain tumor segmentation.Pattern Recognition, 2021, 110: 107562.（中科院1区，Top,检索号：WOS:000585302200004）

²Dingwen Zhang, Jiajia Zhang,Qiang Zhang*, Jungong Han*, Shu Zhang, Junwei Han. Automatic pancreas segmentation based on lightweight DCNN modules and spatial prior propagation.Pattern Recognition, 2021,114: 107762.（中科院1区，Top,检索号：WOS:000632383600003）

²Dingwen Zhang, Bo Wang, Gerong Wang,Qiang Zhang*, Jiajia Zhang, Jungong Han*, Zhen You. Onfocus detection: Identifying individual-camera eye contact from unconstrained images.SCIENCE CHINA Information Sciences, 2021. Accepted. DOI：10.1007/s11432-020-3181-9.（中科院2区）

²Yongjiang Luo, Jiali Yang,Qiang Zhangand Canglong Wang. A Fractional-Order Adaptive Filtering Algorithm in Impulsive Noise Environments. inIEEE Transactions on Circuits and Systems II: Express Briefs, DOI: 10.1109/TCSII.2021.3073961.（中科院2区）

²Yi Liu, Dingwen Zhang,Qiang Zhang*, Jungong Han*. Integrating part-object relationship and contrast for camouflaged object detection.IEEE Transactions on Information Forensics and Security, 2021, 16: 5154-5166.

【2020年】

²Qiang Zhang, Nianchang Huang, Lin Yao, Dingwen Zhang, Caifeng Shan, Jungong Han. RGB-T salient object detection via fusion multi-level CNN features.IEEE Transactions on Image Processing, 2020, 29:3321-3335.（中科院1区，Top，检索号：WOS:000510750900034）

²Qiang Zhang, Guanghe Li, Yunfeng Cao, Jungong Han. Multi-focus image fusion based on non-negative sparse representation and patch-level consistency rectification.Pattern Recognition, 2020, 104:107325.（中科院1区，Top，检索号：WOS:000532701300006）

²Qiang Zhang, Jinghan Wang, Zaihao Liu, Dingwen Zhang. A structure-aware splitting framework for separating cell clumps in biomedical images.Signal Processing, 2020, 168: 107331.（中科院2区，检索号：WOS:000503095100011）

²Yi Liu, Jungong Han,Qiang Zhang*, Caifeng Shan. Deep salient object detection with contextual information guidance.IEEE Transactions on Image Processing, 2020, 29:360-374.（中科院1区，Top,检索号：WOS:000497434700008）

²Dingwen Zhang, Guohai Huang,Qiang Zhang*, Jungong Han*, Junwei Han, Yizhou Wang, Yizhou Yu. Exploring task structure for brain tumor segmentation from multi-modality MR images.IEEE Transactions on Image Processing, 2020, 29: 9032-9043.（中科院1区，Top,检索号：WOS:000464149700009）

【2019年】

²Qiang Zhang, Zhen Huo, Yi Liu, Yunhui Pan, Caifeng Shan, Jungong Han. Salient object detection employing a local tree-structured low-rank representation and foreground consistency.Pattern Recognition, 2019, 92:119-134.（中科院1区，Top，检索号：WOS:000468013000010）

²Qiang Zhang, Lin Yao, Yajun Li. et al. Video Synchronization Based on Projective-Invariant Descriptor.Neural Processing Letters, 2019, 49:1093–1110 (2019).（中科院4区，检索号：WOS:000483206800015）

²Yi Liu,Qiang Zhang*, Dingwen Zhang, Jungong Han. Employing deep part-object relationships for salient object detection.IEEE International Conference on Computer Vision (ICCV),Seoul, Korea, 2019, pp. 1232-1241.（CCF A类）

²Yi Liu, Jungong Han,Qiang, Zhang*, Long Wang. Salient object detection via two-stage graphs.IEEE Transactions on Circuits and Systems for Video Technology, 2019, 29(4): 1023-1037.（中科院2区，检索号：WOS:000464149700009）

【2018年】

²Qiang Zhang, Yi Liu, Rick S. Blum, Jungong Han, Dacheng Tao, Sparse representation based multi-sensor image fusion for multi-focus and multi-modality images: A review.Information Fusion, 2018, 40: 57-75.（中科院1区，Top，检索号：WOS:000413059200006）(ESI)

²Qiang Zhang, Tao Shi, Fan Wang, Rick S. Blum, Jungong Han. Robust sparse representation based multi-focus image fusion with dictionary construction and local spatial consistency.Pattern Recognition, 2018, 83: 299-313.（中科院1区，Top，检索号：WOS:000442172200023）

²Yi Liu,Qiang Zhang*, Jungong Han, Long Wang. Salient object detection employing robust sparse representation and local consistency.Image and Vision Computing, 2018, 69: 155-167.（中科院3区，检索号：WOS:000425075100013）

【2018年之前】

²Qiang Zhang, Martin D. Levine. Robust multi-focus image fusion using multi-task sparse representation and spatial context.IEEE Transactions on Image Processing, 2016, 25(5): 2045-2058.（中科院1区，Top，检索号：WOS:000373131000007）

²Qiang Zhang, Yi Liu, Siyang Zhu, Jungong Han. Salient object detection based on super-pixel clustering and unified low-rank representation.Computer Vision and Image Understanding, 2017, 161: 51-64.（中科院3区，检索号：WOS:000410718600006）

²Qiang Zhang, Martin D. Levine. Robust multi-focus image fusion using multi-task sparse representation and spatial context.IEEE Transactions on Image Processing, 2016, 25(5): 2045-2058.（中科院1区，Top，检索号：WOS:000373131000007）

课题组在多传感器图像融合、单模态/多模态图像显著性目标检测等方面以申请国家发明专利近30项，其中已获授权国家发明专利20项，转让国家发明专利2项；部分发明技术已经成功应用于多家企业，产生了显著的经济和社会效益，荣获“吴文俊人工智能技术奖（技术发明奖）”1项（2018年）。部分专利如下：

[1].张强，刘毅，关永强，霍臻，王龙.基于鲁棒稀疏表示与拉普拉斯正则项的显著目标检测方法.国家发明专利，2019年授权，授权号：ZL 201710419857.0.（已转让）

[2].张强，梁宁，朱四洋，王龙.基于稀疏子空间聚类和低秩表示的显著性目标检测方法.国家发明专利，2019年授权，授权号：ZL 201510951934.8.

[3].张强，刘健，刘宰豪，王军伟，韩军功.基于霍夫圆变换的网格菌落图像分割方法.国家发明专利，2020年授权，授权号：ZL 201810086989.0.（已转让）

[4].张强，汪星，曹运峰，史涛，韩军功，王龙.基于一致性非负稀疏表示的多聚焦图像融合方法.国家发明专利，2019年授权，授权号：ZL 201810086733.X.

[5].张强，邵蓓，韩军功，王龙.基于单应变换的视频同步方法.国家发明专利，2019年授权，授权号：ZL 2018 10086745.2.

[6].张强，李亚军，朱韵茹，相朋，王龙.基于变换不变低秩纹理的投影变换图像匹配方法.国家发明专利，2019年授权，授权号：ZL 201510969075.5.

[7].张强，邵蓓，关永强，焦强，李亚军.基于投影不变描述子的视频同步方法.国家发明专利，2019年授权，授权号：ZL 201710430461.6.

[8].张强，相朋，王亚彬，王龙.基于最大稳定极值区域相位一致性的图像配准方法.国家发明专利，2017年授权，授权号：ZL 201410696329.6.

[9].张强，毕菲，相朋，王亚彬，王龙.基于运动信息与背景信息相结合的视频序列配准方法.国家发明专利，2017年授权，授权号：ZL 201410482399.1.

[10].张强，郑元世，陈月玲，王亚彬，王龙.结合区域匹配和点匹配的大视角图像匹配方法.国家发明专利，2016年授权，授权号：ZL 201310325400.5.

[11].张强，袁小青，郑元世，王亚彬，王龙.基于高阶奇异值分解的多传感器视频融合方法.国家发明专利，2016年授权，授权号：ZL 201310241978.2.

[12].张强,陈月玲,陈闵利,王龙.基于时空显著性检测的多传感器视频融合方法.国家发明专利，2015年授权，授权号：ZL 201310047223.9.

[13].张强，马兆坤，王龙.基于SCDPT变换及其幅相结合的多模态图像融合方法.国家发明专利，2015年授权，授权号：ZL 201210275279.5.

[14].张强，黄年昌，姚琳，刘健，韩军功.多级深度特征融合的RGB-T图像显著性目标检测方法.国家发明专利，2019年申请，申请号：201910431110.6.

[15].张强，刘毅，姚琳，韩军功，王龙.基于细化空间一致性二阶段图的显著目标检测方法.国家发明专利，2018年申请，申请号：201810116888.3.

[16].张强，王凡，焦强，刘健，韩军功.基于超像素聚类与联合低秩表示的多聚焦图像融合方法.国家发明专利，2019年申请，申请号：201910318421.1.

[17].张强，强晓鹏，李磊，任君，等.一种单色图像的阴影检测方法.国家发明专利，2020年申请，申请号：202010388164.1.

[18].张强，田塞塞，张鼎文，史涛，韩军功，王龙.基于显著性分析与低秩表示的红外与可见光图像融合方法.国家发明专利，2019年申请，申请号：201910397498.2.

[19].张鼎文，黄国海，张强，张佳佳，韩军功，王龙.基于多模态特征融合的多任务MRI脑瘤图像分割方法.国家发明专利，2020年申请，申请号：202010752119.X.

[20].张鼎文，张佳佳，张强，韩军功，王龙.基于轻量级卷积申请网络和空间先验传播的胰腺分割方法.国家发明专利，2020年申请，申请号：202010753872.0.