AI Paper Atlas

Research map / Vision-language and multimodal / Human and embodied modeling

Location Sensitive Image Retrieval and Tagging

Raul Gomez, Jaume Gibert, Lluis Gomez, Dimosthenis Karatzas

ECCV 2020 · Vision-language and multimodal › Human and embodied modeling · approach: Composed and text-based image retrieval · 4 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use multi-class softmax training instead of multi-label classification for hashtag supervisionResNet-50 hashtag model · YFCC100M hashtag retrievalP@10: 1.01 -> 14.07Improved
use multi-class softmax training instead of GloVe embedding regressionResNet-50 hashtag model · YFCC100M hashtag retrievalP@10: 7.02 -> 14.07Improved
add raw locations to LocSens (ablation)LocSens · YFCC100M location sensitive retrieval, street (1 km)P@10: 3.74 -> 4.83Improved
add raw locations to LocSens (ablation)LocSens · YFCC100M location agnostic retrievalP@10: 40.05 -> 32.74Hurt
add location dropout and progressive fusion instead of raw locationsLocSens · YFCC100M retrieval, continent (2500 km)P@10: 28.42 -> 30.42Improved
add location dropout and progressive fusion instead of raw locationsLocSens · YFCC100M location agnostic retrievalP@10: 32.74 -> 36.95Improved
add location dropout and progressive fusion instead of raw locationsLocSens · YFCC100M retrieval, street (1 km)P@10: 4.83 -> 4.64Hurt
add location sampling with sigma=0.05 compared to sigma=1 (uninformative locations) (ablation)LocSens · YFCC100M retrieval, continent (2500 km)P@10: 28.40 -> 31.25Improved
lower sigma from 0.05 to 0 in location sampling (ablation)LocSens · YFCC100M location agnostic retrievalP@10: 39.80 -> 35.95Hurt
lower sigma from 0.05 to 0 in location sampling (ablation)LocSens · YFCC100M retrieval, street (1 km)P@10: 4.30 -> 4.83Improved
add location input (raw) to the tagging model (ablation)LocSens vs zeroed locations · YFCC100M image taggingA@1: 15.92 -> 28.10Improved
add location input (raw) to the tagging model (ablation)LocSens vs zeroed locations · YFCC100M image taggingA@10: 46.60 -> 68.21Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy