update

app_regression.py

@@ -62,6 +62,20 @@ all the frames of video are as follows:
 """
 
 
+
+space_description="""\
+[📃Paper](https://arxiv.org/abs/2406.15252) | [🌐Website](https://tiger-ai-lab.github.io/VideoScore/) | [💻Github](https://github.com/TIGER-AI-Lab/VideoScore) | [🛢️Datasets](https://huggingface.co/datasets/TIGER-Lab/VideoFeedback) | [🤗Model](https://huggingface.co/TIGER-Lab/VideoScore) | [🤗Demo](https://huggingface.co/spaces/TIGER-Lab/VideoScore)
+
+- VideoScore is a video quality evaluation model, taking [Mantis-8B-Idefics2](https://huggingface.co/TIGER-Lab/Mantis-8B-Idefics2) as base-model
+and trained on [VideoFeedback](https://huggingface.co/datasets/TIGER-Lab/VideoFeedback),
+a large video evaluation dataset with multi-aspect human scores. 
+
+- VideoScore can reach 75+ Spearman correlation with humans on VideoEval-test, surpassing all the MLLM-prompting methods and feature-based metrics. 
+
+- VideoScore also beat the best baselines on other three benchmarks EvalCrafter, GenAI-Bench and VBench, showing high alignment with human evaluations.
+"""
+
+
 aspect_mapping= [
     "visual quality",
     "temporal consistency",
@@ -148,10 +162,15 @@ def eval_video(prompt, video:str):
 
 def build_demo():
     with gr.Blocks() as demo:
-        gr.Markdown("""
-            ## Video Evaluation
-            upload a video along with a text prompt when generating the video, this model will evaluate the video's quality from 7 different dimensions.
-        """)
+
+        gr.Markdown("## VideoScore: Building Automatic Metrics to Simulate Fine-grained Human Feedback for Video Generation")
+        with gr.Row():
+            gr.Markdown(space_description)
+            gr.Image("https://tiger-ai-lab.github.io/VideoScore/static/images/teaser.png", label="Teaser")
+        
+        gr.Markdown("---")
+        
+        gr.Markdown("### Try VideoScore (Regression) with your own text prompt and videos.")
         with gr.Row():
             video = gr.Video(width=500, label="Video")
             with gr.Column():
@@ -169,31 +188,35 @@ def build_demo():
         )
         
         dummy_id = gr.Textbox("id", label="id", visible=False, min_width=50)
-        dummy_output = gr.Textbox("reference score", label="reference scores", visible=False, lines=7)
+        # dummy_output = gr.Textbox("reference score", label="reference scores", visible=False, lines=7)
         
         gr.Examples(
             examples=
             [
                 [
-                    item['id'], 
+                    # item['id'], 
                     item['prompt'],
                     item['video'],
-                    item['conversations'][1]['value']
-                ] for item in examples
+                    # item['conversations'][1]['value']
+                ] for item in examples if item['prompt']
             ],
-            inputs=[dummy_id, video_prompt, video, dummy_output],
+            inputs=[video_prompt, video],
+            # inputs=[dummy_id, video_prompt, video, dummy_output],
+            
         )        
         
-#         gr.Markdown("""
-# ## Citation
-# ```
-# @article{jiang2024mantis,
-#   title={MANTIS: Interleaved Multi-Image Instruction Tuning},
-#   author={Jiang, Dongfu and He, Xuan and Zeng, Huaye and Wei, Con and Ku, Max and Liu, Qian and Chen, Wenhu},
-#   journal={arXiv preprint arXiv:2405.01483},
-#   year={2024}
-# }
-# ```""")
+        gr.Markdown("""
+## Citation
+```
+@article{he2024videoscore,
+  title = {VideoScore: Building Automatic Metrics to Simulate Fine-grained Human Feedback for Video Generation},
+  author = {He, Xuan and Jiang, Dongfu and Zhang, Ge and Ku, Max and Soni, Achint and Siu, Sherman and Chen, Haonan and Chandra, Abhranil and Jiang, Ziyan and Arulraj, Aaran and Wang, Kai and Do, Quy Duc and Ni, Yuansheng and Lyu, Bohan and Narsupalli, Yaswanth and Fan, Rongqi and Lyu, Zhiheng and Lin, Yuchen and Chen, Wenhu},
+  journal = {ArXiv},
+  year = {2024},
+  volume={abs/2406.15252},
+  url = {https://arxiv.org/abs/2406.15252},
+}
+```""")
     return demo