SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1905.12794 · 2019

Fashion IQ: A New Dataset Towards Retrieving Images by Natural Language Feedback

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 12 functions out of this paper's own repositories and ran 7 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
XiaoxiaoGuo/fashion-iq canonical 1 of 1
hssip/fashionsap pwc_unofficial 5 of 10
copy not recorded — 1 of 1
FunctionStatusWhere it lives
acc_eval Ran hssip/fashionsap/fashion_catereg.py
code served (permissive licence) · get_code("ea09138f37a962f8")
attention Ran XiaoxiaoGuo/fashion-iq/transformer/interactive_retrieval/models.py
pointer only (licence: NONE) · get_code("875f05a473ae1687")
conv1x1 Ran hssip/fashionsap/models/resnet.py
code served (permissive licence) · get_code("2a80220dabcb742a")
conv3x3 Ran hssip/fashionsap/models/resnet.py
code served (permissive licence) · get_code("600ff2c45e0de056")
get_clones Ran this paper's copy was not recorded; identical code first harvested from arshadshk/SAINT-pytorch
pointer only · get_code("891b8ebab395921f")
interpolate_pos_embed Ran hssip/fashionsap/models/vit.py
code served (permissive licence) · get_code("c6ec173f19f5c34d")
numpy_to_python Ran hssip/fashionsap/prepare_dataset.py
code served (permissive licence) · get_code("96c16bbc416eedfb")
concat_all_gather Not yet run hssip/fashionsap/models/model_fashion_pretrain.py
code served (permissive licence) · get_code("73cecca9f3575f09")
itm_eval Not yet run hssip/fashionsap/fashion_retrieval.py
code served (permissive licence) · get_code("a27c5ba736300cb3")
itm_eval Not yet run hssip/fashionsap/fashion_tgir.py
code served (permissive licence) · get_code("7ccaf9ff38a2204b")
load_tf_weights_in_bert Not yet run hssip/fashionsap/models/xbert.py
code served (permissive licence) · get_code("26be70dca3249c0b")
resnet18 Not yet run hssip/fashionsap/models/resnet.py
code served (permissive licence) · get_code("c645f4947c305a25")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Conversational interfaces for the detail-oriented retail fashion domain are more natural, expressive, and user friendly than classical keyword-based search interfaces. In this paper, we introduce the Fashion IQ dataset to support and advance research on interactive fashion image retrieval. Fashion IQ is the first fashion dataset to provide human-generated captions that distinguish similar pairs of garment images together with side-information consisting of real-world product descriptions and derived visual attribute labels for these images. We provide a detailed analysis of the characteristics of the Fashion IQ data, and present a transformer-based user simulator and interactive image retriever that can seamlessly integrate visual attributes with image features, user feedback, and dialog history, leading to improved performance over the state of the art in dialog-based image retrieval. We believe that our dataset will encourage further work on developing more natural and real-world applicable conversational shopping assistants.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("1905.12794")
get_code_for_paper("1905.12794")
have("1905.12794")

Connect an agent — have() is free.