Update README.md

omitum · Sep 20, 2017 · 9171d7a · 9171d7a
1 parent 6f4bf4d
commit 9171d7a
Showing 1 changed file with 15 additions and 1 deletion.
diff --git a/README.md b/README.md
@@ -1 +1,15 @@
-# adapt_yto
+# Adapting Object Detectors 
+
+Implementation of the paper [Adapting Object Detectors from Images toWeakly Labeled Videos](http://www.cs.umanitoba.ca/~ywang/papers/bmvc17_adapt.pdf). 
+
+### Usage
+The first step of our approach is to generate a shortlist of object proposals from source and target images. We use the edge boxes algorithm for generating the object proposals. 
+Let K be the number of object proposals generated on the image. We represent each proposal as a 4096-dimensional CNN feature vector. 
+
+### Run the experiment
+
+### Model Architecture
+
+![model architecture](./data/architecture.png)
+
+