Changed description

app.py

@@ -420,5 +420,5 @@ def segment(image):
 examples = os.listdir('../../Examples')
 examples = ['../../Examples/' + item for item in examples]
 title="Context R-CNN"
-description=f"Gradio demo for **Context R-CNN**: [[Paper]](https://arxiv.org/abs/1912.03538). This model is a real-time neural network for object detection of Gopher Tortoises. Faster R-CNN is used to get a context feature matrix which is used by Context R-CNN to improve detection. Uploaded images need to have date taken attribute in the metadata for it to work. Context R-CNN improves upon Faster R-CNN by building a contextual memory bank using environmental factors like time of day, seasonal changes, etc."
+description=f'<p class="has-line-data" data-line-start="0" data-line-end="2">Gradio demo for <strong>Context R-CNN</strong>: <a href="https://arxiv.org/abs/1912.03538">[Paper]</a>.<br>Context R-CNN is an object detection algorithm that uses contextual features to improve object detection. It is based on Faster R-CNN, but it adds a module that can incorporate contextual features from surrounding frames. This allows Context R-CNN to better identify objects that are partially obscured or that are moving quickly.</p><p class="has-line-data" data-line-start="3" data-line-end="4">The contextual features are stored in a memory bank, which is built up over time as the camera captures images. The memory bank is indexed using an attention mechanism, which allows Context R-CNN to focus on the most relevant contextual features for each object.</p><p class="has-line-data" data-line-start="5" data-line-end="6">Context R-CNN has been shown to improve object detection performance on a variety of datasets, including camera trap data and traffic camera data. It is a promising approach for improving object detection in static monitoring cameras, where the sampling rate is low and the objects may exhibit long-term behavior.</p><p class="has-line-data" data-line-start="7" data-line-end="8">This application of Context R-CNN demonstrates a possible use case for Context R-CNN (camera trap images of Gopher Tortoises in the wild), while showcasing improvements made over an existing Faster R-CNN implementation. Both models of R-CNN were trained on the exact same train, test and validation datasets for best comparison. Context R-CNN improves upon Faster R-CNN by building a contextual memory bank using environmental factors like time of day, seasonal changes, etc. The contextual feature matrix used by Context R-CNN model was build using Faster R-CNN model.</p><p class="has-line-data" data-line-start="10" data-line-end="11"><strong>Examples images provided in this demo were not a part of the dataset used for training or testing the models.</strong></p><p class="has-line-data" data-line-start="12" data-line-end="13">Note: Uploaded images need to have date taken attribute in the metadata for the model to process it correctly.</p>'
 gr.Interface(fn=segment, inputs = "file",outputs = "image" ,title=title, description=description ,examples=examples,enable_queue=True).launch()