Update README.md

Notice! It will never  be updated!

README.md

@@ -1,10 +1,11 @@
-# Differentiable Cross Modal Hashing via Multimodal Transformers
+# Differentiable Cross Modal Hashing via Multimodal Transformers [paper](https://dl.acm.org/doi/abs/10.1145/3503161.3548187)
+# This project has been moved to [clip-based-cross-modal-hash](https://github.com/kalenforn/clip-based-cross-modal-hash/tree/main)
 
 ## Framework
 The main architecture of our method.
 ![framework](./data/structure.jpg)
 
-We propose a selecting mechanism to generate hash code that will transfor the discrete space into a continuous space. Hash code will be encoded as a $2D$ vector.
+We propose a selecting mechanism to generate hash code that will transfor the discrete space into a continuous space. Hash code will be encoded as a seires of $2D$ vectors.
 ![hash](./data/method.jpg)
 
 ## Dependencies
@@ -24,7 +25,7 @@ then use the "data/make_XXX.py" to generate .mat file
 For example:
 > cd COCO_DIR # include train val images and annotations files
 >
-> make mat
+> mkdir mat
 >
 > cp DCMHT/data/make_coco.py mat 
 >
@@ -64,6 +65,18 @@ After the dataset has been prepared, we could run the follow command to train.
 ## Result
 ![result](./data/result.png)
 
+## Citation
+``` 
+inproceedings{10.1145/3503161.3548187,
+author = {Tu, Junfeng and Liu, Xueliang and Lin, Zongxiang and Hong, Richang and Wang, Meng},
+title = {Differentiable Cross-Modal Hashing via Multimodal Transformers},
+year = {2022},
+booktitle = {Proceedings of the 30th ACM International Conference on Multimedia},
+pages = {453–461},
+numpages = {9},
+}
+```
+
 ## Acknowledegements
 [CLIP](https://github.com/openai/CLIP)
 
@@ -76,3 +89,9 @@ After the dataset has been prepared, we could run the follow command to train.
 [DADH](https://github.com/Zjut-MultimediaPlus/DADH)
 
 [deep-cross-modal-hashing](https://github.com/WangGodder/deep-cross-modal-hashing)
+
+
+## Apologize:
+*2023/03/01*
+
+I find figure 1 with the wrong formula for the vartheta, the right one is the function (10). It has been published, so I can't fix it.