AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

Vision-Language Fusion for Object Recognition

Sz-Rung Shiang, Stephanie Rosenthal, Anatole Gershman, Jaime Carbonell, Jean Oh

AAAI 2017 · Detection and segmentation › Open-set and few-shot detection · approach: Open-vocabulary 3D and world perception · 5 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 10 spatial relations per imageMultiRank · ground-truth boxesaccuracy: 0.6299 -> 0.7240Improved
add 10 spatial relations per imageMultiRank · ground-truth boxesmAP: 0.7240 -> 0.8002Improved
add only 1 spatial relation (ablation)MultiRank · ground-truth boxesaccuracy: 0.6299 -> 0.6331No clear effect
increase number of relations from 1 to 10 (ablation)MultiRank · ground-truth boxesaccuracy: 0.6331 -> 0.7240Improved
use naive fusion instead of MultiRank with 10 relations (ablation)naive fusion · ground-truth boxesaccuracy: 0.7240 -> 0.6527Hurt
use confusion matrix plus co-occurrence without human descriptionsMultiRank · ground-truth boxesaccuracy: 0.6299 -> 0.6558Improved
use co-occurrence only (ablation)MultiRank · ground-truth boxesaccuracy: 0.6299 -> 0.6331No clear effect
use detected instead of ground-truth boxes for vision-onlyvision-only · detected boxesaccuracy: 62.99% to 42.28%Hurt
add 10 relations on detected boxesMultiRank · detected boxesaccuracy: 0.4229 -> 0.5885Improved
choose relations on error-prone boxes (10 relations, detected boxes)MultiRank · detected boxesaccuracy: 0.5885 -> 0.6857Improved
choose relations on error-prone boxes (1 relation, ground-truth boxes)MultiRank · ground-truth boxesaccuracy: 0.6331 -> 0.6526Improved
choose relations on error-prone boxes (10 relations, ground-truth boxes)MultiRank · ground-truth boxesaccuracy: 0.7240 -> 0.7241No clear effect

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