Zequn Zeng
Zequn Zeng
Hello, I was wondering about the role of auxiliary losses on each intermediate decoder layer. Can it help to accelerate the model convergence or for other purposes? Thanks!
I want to reproduce the results on Composite dataset 1) I downloaded Composite dataset from https://imagesdg.wordpress.com/image-to-scene-description-graph/, there are two types :correctness and throughness. I use the first one, **correctness**. 2)...
I want to reproduce the results on Composite dataset 1) Firstly, I downloaded Composite dataset from https://imagesdg.wordpress.com/image-to-scene-description-graph/, there are two types :**correctness** and **throughness**. I use the first one, **correctness**....
Hi, I would like to know which TSNE tool you utilize to visualize your image samples like **Fig. 6** in your paper? It takes a large amount of time when...
Thanks for your great work! I want to know whether there is any theoretical proof about **Discriminability Score is a submodular function**?