gimpong / www22-hcq Goto Github PK

Hi, much thanks for your nice paper and the well-organized open-resourced codebase.

I have some questions about HCQ after reading your paper:

• Are the text and video embeddings using the same codebooks?

• In section 3.6, when calculating the Asymmetric Quantized Contrastive Learning (AQ-CL) loss, why did you consider using raw embeddings on one side and quantized embeddings on the other side? Why aren't both the text and video using quantized embeddings? Have you compared this setting?

• In section 3.7, you mentioned To accelerate the computation, we can set up a query-specific lookup table. Why is it possible to build such a lookup table in advance, when the actual retrieval scenario should have text queries appearing randomly and in real-time? How is the Ad-hoc text-to-video retrieval done in terms of inference and retrieval?

• Regarding the storage capacity of HCQ, you mentioned The proposed HCQ represents an instance by 8 256-bit codes. Could you explain in more detail how you arrived at the 8 256-bit codes for each instance?

Looking forward to your reply.

Hi, congratulations to your WWW22 paper!

This is a kind reminder of your [66] paper reference. I think the name of the cited paper is wrong. I assume you want to cite "Learning Discrete Representations via Constrained Clustering for Effective and Efficient Dense Retrieval", but the current name is the same as [65].

Maybe consider an update of the arxiv paper?