Update README.md

README.md

@@ -52,4 +52,21 @@ print(time_reduced_hidden_states.shape) # [13, 768]
 aggregator = nn.Conv1d(in_channels=13, out_channels=1, kernel_size=1)
 weighted_avg_hidden_states = aggregator(time_reduced_hidden_states.unsqueeze(0)).squeeze()
 print(weighted_avg_hidden_states.shape) # [768]
+```
+
+# Citation
+```shell
+@article{li2022large,
+  title={Large-Scale Pretrained Model for Self-Supervised Music Audio Representation Learning},
+  author={Li, Yizhi and Yuan, Ruibin and Zhang, Ge and Ma, Yinghao and Lin, Chenghua and Chen, Xingran and Ragni, Anton and Yin, Hanzhi and Hu, Zhijie and He, Haoyu and others},
+  year={2022}
+}
+
+@article{li2022map,
+  title={MAP-Music2Vec: A Simple and Effective Baseline for Self-Supervised Music Audio Representation Learning},
+  author={Li, Yizhi and Yuan, Ruibin and Zhang, Ge and Ma, Yinghao and Lin, Chenghua and Chen, Xingran and Ragni, Anton and Yin, Hanzhi and Hu, Zhijie and He, Haoyu and others},
+  journal={arXiv preprint arXiv:2212.02508},
+  year={2022}
+}
+
 ```