AI Paper Atlas

Research map / Vision-language and multimodal / Visual question answering

Visual Reasoning with Multi-hop Feature Modulation

Florian Strub, Mathieu Seurin, Ethan Perez, Harm de Vries, Jeremie Mary, Philippe Preux, Aaron CourvilleOlivier Pietquin

ECCV 2018 · Vision-language and multimodal › Visual question answering · approach: Vision-language model VQA evaluation · 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
use attention over the dialogue to update the context (instead of a shared MLP update) (ablation)Multi-hop FiLM · GuessWhat?! Guessertest error: 37.3 -> 30.5Improved
replace single-hop FiLM generator with multi-hopFiLM model · GuessWhat?! Guessertest error: 35.6% -> 30.5%Improved
replace single-hop FiLM generator with multi-hopFiLM model · GuessWhat?! Oracletest error: 17.6% -> 16.9%Improved
replace single-hop FiLM generator with multi-hopFiLM model · RefCOCO+ valaccuracy: 72.1% -> 73.4%Improved
add visual feedback to the context embedding (ablation)Multi-hop FiLM · ReferIt (RefCOCO, RefCOCO+, RefCOCOg, RefClef)accuracy: 83.5% -> 84.9% (RefCOCO val)Improved
add visual feedback to the context embedding (ablation)Multi-hop FiLM · GuessWhat?! Oracletest error: 16.9% -> 17.1%No clear effect
add visual feedback to the context embedding (ablation)Multi-hop FiLM · GuessWhat?! Guesser (crop+img)test error: 35.3% -> 34.3% (pointing task crop)No clear effect
add object category label (ablation)Multi-hop FiLM · GuessWhat?! Guesser (crop+img)test error: 33.4% -> 30.5%Improved
add crop input on top of image input (ablation)Multi-hop FiLM · GuessWhat?! Guessertest error: 35.0% -> 30.5%Improved
add image and crop inputs to a baseline using only object category and spatial location (ablation)Baseline NN + MLB Oracle · GuessWhat?! Oracletest error: 20.6% -> 21.1%Hurt
add previous question-answer pairs (dialogue) to the question input (ablation)Baseline NN + MLB Oracle · GuessWhat?! Oracletest error: 21.8% -> 21.1%Improved
add crop and image together to the baseline Guesser (ablation)Baseline NN Guesser · GuessWhat?! Guessertest error: 38.3% -> 45.1%Hurt

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