AI Paper Atlas

Research map / Vision-language and multimodal / Robot action and navigation

ESceme: Vision-and-Language Navigation with Episodic Scene Memory

Qi Zheng, Daqing Liu, Chaoyue Wang, Jing Zhang, Dadong Wang, Dacheng Tao

IJCV 2024 · Vision-language and multimodal › Robot action and navigation · approach: Reasoning-enhanced vision-language navigation · 25 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 ESceme with max poolingHAMT · R2R val unseenSPL: 60.9 -> 63.2Improved
use max pooling instead of mean pooling (ablation)ESceme · R2R val unseenSPL: 62.3 -> 63.2Improved
add candidate enhancing with mean pooling (ablation)HAMT · R2R val unseenSPL: 60.9 -> 62.3Improved
use graph encoding branch instead of candidate enhancing (ablation)HAMT + ESceme · R2R val unseenSPL: 60.9 -> 60.9No clear effect
add ESceme to TDSTPTDSTP · R2R val unseenSPL: 62.1 -> 63.0Improved
add ESceme to TDSTPTDSTP · R2R val seenSPL: 70.9 -> 74.4Improved
use nearly complete scene memory (ESceme*) instead of progressive (ablation)ESceme on HAMT · R2R val unseenSPL: 63.2 -> 64.0Improved
use nearly complete scene memory (ESceme*) (ablation)ESceme on TDSTP · R2R val unseenSPL: 63.0 -> 64.3Improved
use nearly complete scene memory (ESceme*) (ablation)ESceme · R4R val unseenSPL: 43.2 -> 43.4No clear effect
keep scene memory across episodes instead of re-initializing (ablation)ESceme · R2R val unseenSPL: 51 -> 64Improved
add ESceme to HAMTHAMT · R4R val unseenCLS: 57.7 -> 62.7Improved
add ESceme to HAMTHAMT · CVDN test unseenGoal Progress: 5.58 -> 5.99Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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