Matyáš Boháček commited on
Commit
e1c499b
1 Parent(s): 55f4bdb

Update the description

Browse files
Files changed (1) hide show
  1. app.py +2 -1
app.py CHANGED
@@ -106,7 +106,8 @@ def greet(label, video0, video1):
106
  label = gr.outputs.Label(num_top_classes=5, label="Top class probabilities")
107
  demo = gr.Interface(fn=greet, inputs=[gr.Dropdown(["Webcam", "Video"], label="Please select the input type:", type="value"), gr.Video(source="webcam", label="Webcam recording", type="mp4"), gr.Video(source="upload", label="Video upload", type="mp4")], outputs=label,
108
  title="🤟 SPOTER Sign language recognition",
109
- description="""Try out our recent model for sign language recognition right in your browser! The model below takes a video of a single sign in the American Sign Language at the input and provides you with probabilities of the lemmas (equivalent to words in natural language).
 
110
  ### Our work at CVPR
111
  Our efforts on lightweight and efficient models for sign language recognition were first introduced at WACV with our SPOTER paper. We now presented a work-in-progress follow-up here at CVPR's AVA workshop. Be sure to check our work and code below:
112
  - **WACV2022** - Original SPOTER paper - [Paper](https://openaccess.thecvf.com/content/WACV2022W/HADCV/papers/Bohacek_Sign_Pose-Based_Transformer_for_Word-Level_Sign_Language_Recognition_WACVW_2022_paper.pdf), [Code](https://github.com/matyasbohacek/spoter)
106
  label = gr.outputs.Label(num_top_classes=5, label="Top class probabilities")
107
  demo = gr.Interface(fn=greet, inputs=[gr.Dropdown(["Webcam", "Video"], label="Please select the input type:", type="value"), gr.Video(source="webcam", label="Webcam recording", type="mp4"), gr.Video(source="upload", label="Video upload", type="mp4")], outputs=label,
108
  title="🤟 SPOTER Sign language recognition",
109
+ description="""Current user interfaces are not accessible for D/deaf and hard-of-hearing users, whose natural communication medium is sign language. We work on AI systems for sign language to come closer to sign-driven technology and empower accessible apps, websites, and video conferencing platforms.
110
+ Try out our recent model for sign language recognition right in your browser! The model below takes a video of a single sign in the American Sign Language at the input and provides you with probabilities of the lemmas (equivalent to words in natural language).
111
  ### Our work at CVPR
112
  Our efforts on lightweight and efficient models for sign language recognition were first introduced at WACV with our SPOTER paper. We now presented a work-in-progress follow-up here at CVPR's AVA workshop. Be sure to check our work and code below:
113
  - **WACV2022** - Original SPOTER paper - [Paper](https://openaccess.thecvf.com/content/WACV2022W/HADCV/papers/Bohacek_Sign_Pose-Based_Transformer_for_Word-Level_Sign_Language_Recognition_WACVW_2022_paper.pdf), [Code](https://github.com/matyasbohacek/spoter)