Update app.py

app.py

@@ -155,7 +155,8 @@ title = "End-to-End Referring Video Object Segmentation with Multimodal Transfor
 
 description = "This notebook provides a (limited) hands-on demonstration of MTTR.\n Given a text query and a short clip based on a YouTube video, we demonstrate how MTTR can be used to segment the referred object instance throughout the video. To use it, upload an .mp4 video file and input a text query which describes one of the instances in that video. \n Disclaimer: \n This is a limited demonstration of MTTR's performance. The model used here was trained exclusively on Refer-YouTube-VOS with window size w=12 (as described in our paper). No additional training data was used whatsoever. Hence, the model's performance may be limited, especially on instances from unseen categories. Additionally, slow processing times may be encountered, depending on the input clip length and/or resolution, and due to HuggingFace's limited computational resources (no GPU acceleration unfortunately).Finally, we emphasize that this demonstration is intended to be used for academic purposes only. We do not take any responsibility for how the created content is used or distributed."
 
-article = "<p style='text-align: center'><a href='https://github.com/mttr2021/MTTR'>Github Repo</a></p>"
+# article = "<p style='text-align: center'><a href='https://github.com/mttr2021/MTTR'>Github Repo</a></p>"
+article = "<p style='text-align: center'><a href='https://arxiv.org/abs/2111.14821'>End-to-End Referring Video Object Segmentation with Multimodal Transformers</a> | <a href='https://github.com/mttr2021/MTTR'>Github Repo</a></p>"
 
 iface = gr.Interface(fn=process, 
                      inputs=[gr.inputs.Textbox(label="text query"), gr.inputs.Video(label="Input video. First 10 seconds of the video are used.")],