VI-RGBT1500 Dataset and MGAI_TCSVT2022

Multiple Graph Affinity Interactive Network and A Variable Illumination Dataset for RGBT Image Salient Object Detection, IEEE Transactions on Circuits and Systems for Video Technology, 2022, doi:10.1109/TCSVT.2022.3233131. Paper

Update:

• 2023/06/06-We update the MGAI code.
• 2023/04/17-We fix four wrong T images. Please use the latest dataset.

VI-RGBT1500 Dataset:

• We provide the dataset of VI-RGBT1500:
  • VI-RGBT1500: Baidu Cloud, Password: pzit; Google Cloud.
  • Different Illumination for VI-RGBT1500: Baidu Cloud, Password: zg1v; Google Cloud.
• We provide the dataset of VI-RGBT Training-set:
  • VI-RGBT Training-set: Baidu Cloud, Password: 9c7v; Google Cloud.

Results of MGAI:

• We provide the resutls of our MGAI on VI-RGBT1500:
  • Saliency maps of our MGAI on VI-RGBT1500 trained on VI-RGBT Training-set: Baidu Cloud, Password: da85; Google Cloud.
  • Saliency maps of our MGAI on VI-RGBT1500 trained on VT5000: Baidu Cloud, Password: jij3; Google Cloud.
• We provide the resutls of our MGAI on VT821, VT1000, and VT5000:
  • Saliency maps of our MGAI on VT821, VT1000, VT5000 trained on VT5000: Baidu Cloud, Password: dfhy; Google Cloud.

Results of MGFL and LTCR:

• We provide the resutls of our MGFL and LTCR on VI-RGBT1500, VT821, VT1000, and VT5000:
  • Saliency maps of our MGFL and LTCR on VI-RGBT1500, VT821, VT1000, and VT5000: Baidu Cloud, Password: k0un; Google Cloud.

If you find our VI-RGBT1500 dataset and MGAI useful, please cite our papers:

@ARTICLE{10003255,
  author={Song, Kechen and Huang, Liming and Gong, Aojun and Yan, Yunhui},
  journal={IEEE Transactions on Circuits and Systems for Video Technology}, 
  title={Multiple Graph Affinity Interactive Network and a Variable Illumination Dataset for RGBT Image Salient Object Detection}, 
  year={2023}, volume={33}, number={7}, pages={3104-3118},
  doi={10.1109/TCSVT.2022.3233131}}
  
@ARTICLE{9389777, 
   author={Huang, Liming and Song, Kechen and Wang, Jie and Niu, Menghui and Yan, Yunhui},  
   journal={IEEE Transactions on Circuits and Systems for Video Technology},   
   title={Multi-Graph Fusion and Learning for RGBT Image Saliency Detection},  
   year={2022},  volume={32},  number={3},  pages={1366-1377},  
   doi={10.1109/TCSVT.2021.3069812}}    
   
@ARTICLE{9184226,  
   author={Huang, Liming and Song, Kechen and Gong, Aojun and Liu, Chuang and Yan, Yunhui},  
   journal={IEEE Signal Processing Letters},   
   title={RGB-T Saliency Detection via Low-Rank Tensor Learning and Unified Collaborative Ranking},   
   year={2020},  volume={27},  number={},  pages={1585-1589},  
   doi={10.1109/LSP.2020.3020735}}

Contact Us:

If you have any questions, please contact Liming Huang (huanglm.me@gmail.com). Many thanks.