BUAADreamer
/

SPN4CIR

Visual Question Answering

composed image retrieval

image retrieval

Model card Files Files and versions Community

BUAADreamer commited on Oct 13, 2024

Commit

364c738

·

verified ·

1 Parent(s): 868966b

Update README.md

Files changed (1) hide show

README.md +2 -4

README.md CHANGED Viewed

@@ -1,8 +1,7 @@
 ---
 license: mit
 datasets:
-- Plachta/FashionIQ
-- royokong/cirr_imgs
 language:
 - en
 metrics:
@@ -541,5 +540,4 @@ About code, our project is based on [CLIP4Cir](https://github.com/ABaldrati/CLIP
 About data, we train and evaluate on two CIR dataset [FashionIQ](https://github.com/XiaoxiaoGuo/fashion-iq/) and [CIRR](https://github.com/Cuberick-Orion/CIRR). We use [LLaVA](https://github.com/haotian-liu/LLaVA) to do caption generation and [Unicom](https://github.com/deepglint/unicom) to do image pair match.
-Thanks for their great jobs! If you need to use a particular part of our code, please cite the relevant papers.

 ---
 license: mit
 datasets:
+- BUAADreamer/cir_dataset
 language:
 - en
 metrics:
 About data, we train and evaluate on two CIR dataset [FashionIQ](https://github.com/XiaoxiaoGuo/fashion-iq/) and [CIRR](https://github.com/Cuberick-Orion/CIRR). We use [LLaVA](https://github.com/haotian-liu/LLaVA) to do caption generation and [Unicom](https://github.com/deepglint/unicom) to do image pair match.
+Thanks for their great jobs! If you need to use a particular part of our code, please cite the relevant papers.