add svtr cite link

doc/doc_ch/algorithm_rec_nrtr.md

@@ -144,9 +144,9 @@ Predicts of ./doc/imgs_words_en/word_10.png:('pain', 0.9265879392623901)
 
 ```bibtex
 @article{Sheng2019NRTR,
-  author    = {Fenfen Sheng and Zhineng Chen andBo Xu},
   title     = {NRTR: A No-Recurrence Sequence-to-Sequence Model For Scene Text Recognition},
-  journal   = {ICDAR},
+  author    = {Fenfen Sheng and Zhineng Chen andBo Xu},
+  booktitle = {ICDAR},
   year      = {2019},
   url       = {http://arxiv.org/abs/1806.00926},
   pages     = {781-786}

doc/doc_ch/algorithm_rec_svtr.md

@@ -165,9 +165,9 @@ Predicts of ./doc/imgs_words_en/word_10.png:('pain', 0.9999998807907104)
 
 ```bibtex
 @article{Du2022SVTR,
-  author = {Du, Yongkun and Chen, Zhineng and Jia, Caiyan and Yin, Xiaoting and Zheng, Tianlun and Li, Chenxia and Du, Yuning and Jiang, Yu-Gang},
   title     = {SVTR: Scene Text Recognition with a Single Visual Model},
-  publisher = {IJCAI},
+  author    = {Du, Yongkun and Chen, Zhineng and Jia, Caiyan and Yin, Xiaoting and Zheng, Tianlun and Li, Chenxia and Du, Yuning and Jiang, Yu-Gang},
+  booktitle = {IJCAI},
   year      = {2022},
   url       = {https://arxiv.org/abs/2205.00159}
 }

doc/doc_en/algorithm_rec_nrtr_en.md

@@ -125,9 +125,9 @@ Not supported
 
 ```bibtex
 @article{Sheng2019NRTR,
-  author    = {Fenfen Sheng and Zhineng Chen andBo Xu},
   title     = {NRTR: A No-Recurrence Sequence-to-Sequence Model For Scene Text Recognition},
-  journal   = {ICDAR},
+  author    = {Fenfen Sheng and Zhineng Chen andBo Xu},
+  booktitle = {ICDAR},
   year      = {2019},
   url       = {http://arxiv.org/abs/1806.00926},
   pages     = {781-786}

doc/doc_en/algorithm_rec_svtr_en.md

@@ -130,15 +130,15 @@ Not supported
 <a name="5"></a>
 ## 5. FAQ
 
-1. Since most of the op operators used by `SVTR` are matrix multiplication, in the GPU environment, the speed has an advantage, but in the environment where mkldnn is enabled on the CPU, `SVTR` has no advantage over the optimized convolutional network.
+1. Since most of the operators used by `SVTR` are matrix multiplication, in the GPU environment, the speed has an advantage, but in the environment where mkldnn is enabled on the CPU, `SVTR` has no advantage over the optimized convolutional network.
 
 ## Citation
 
 ```bibtex
 @article{Du2022SVTR,
-  author = {Du, Yongkun and Chen, Zhineng and Jia, Caiyan and Yin, Xiaoting and Zheng, Tianlun and Li, Chenxia and Du, Yuning and Jiang, Yu-Gang},
   title     = {SVTR: Scene Text Recognition with a Single Visual Model},
-  publisher = {IJCAI},
+  author    = {Du, Yongkun and Chen, Zhineng and Jia, Caiyan and Yin, Xiaoting and Zheng, Tianlun and Li, Chenxia and Du, Yuning and Jiang, Yu-Gang},
+  booktitle = {IJCAI},
   year      = {2022},
   url       = {https://arxiv.org/abs/2205.00159}
 }