AI Paper Atlas

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

TextPlace: Visual Place Recognition and Topological Localization Through Reading Scene Texts

Ziyang Hong, Yvan Petillot, David Lane, Yishu Miao, Sen Wang

ICCV 2019 · Vision-language and multimodal › Human and embodied modeling · approach: Language-grounded scene text and structure · 61 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
add a 10 m position prior to NetVLADNetVLAD · Street 1 day-night, recall 0.8precision: 0.76 -> 0.95Improved
enlarge the NetVLAD position-prior search space from 10 m to 30 m (ablation)NetVLAD · Street 1 day-night, recall 0.9precision: 0.93 -> 0.83Hurt
enlarge the FAB-MAP position-prior search space from 10 m to 30 m (ablation)FAB-MAP · Street 1 day-night, recall 0.9precision: 0.63 -> 0.58Hurt
add VO tracking, topological graph and adaptive search window (versus global search) (ablation)TextPlace · Street 1 day-night, recall 0.9precision: 0.84 -> 0.91Improved
add VO tracking, topological graph and adaptive search window (versus global search) (ablation)TextPlace · Street 1 day-night, recall 0.8precision: 0.92 -> 0.96Improved
replace NetVLAD with TextPlace under global searchNetVLAD (global) · Street 1 day-night, recall 0.9precision: 0.74 -> 0.84Improved
increase the search window size (ablation)TextPlace · V4RL sequence 2precisionImproved
use denser map nodes (smaller displacement between nodes) (ablation)TextPlace · V4RL sequence 2precisionNo clear effect
use a larger search window to offset the Levenshtein distance threshold (ablation)TextPlace · V4RL sequence 2precisionImproved
raise the Levenshtein threshold to reach recall above 0.9 (ablation)TextPlace · MallprecisionHurt

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