AI Paper Atlas

Research map / Vision-language and multimodal / CLIP and zero-shot

ViCo: Word Embeddings From Visual Co-Occurrences

Tanmay Gupta, Alexander Schwing, Derek Hoiem

ICCV 2019 · Vision-language and multimodal › CLIP and zero-shot · approach: Recaptioning and text-supervised pretraining · 21 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
concatenate ViCo(linear,100) embeddings to GloVeGloVe · Visual Genome clustering (fine categories)V-Measure: 0.50 -> 0.61Improved
concatenate ViCo(linear,100) embeddings to GloVeGloVe · Visual Genome clustering (coarse categories)V-Measure: 0.52 -> 0.65Improved
train ViCo with WordNet synsets and Object-Hypernym co-occurrences (ablation)GloVe+ViCo(linear,100) · Visual Genome clustering (fine categories)V-Measure: 0.54 -> 0.61Improved
train ViCo with WordNet synsets and Object-Hypernym co-occurrences (ablation)GloVe+ViCo(linear,100) · Visual Genome clustering (coarse categories)V-Measure: 0.58 -> 0.65Improved
concatenate random 100-dim vectors to GloVe (ablation)GloVe · Visual Genome clustering (coarse categories)V-Measure: 0.52 -> 0.49No clear effect
use linear 100-dim transformation instead of select 200-dim transformation, combined with GloVe (ablation)GloVe+ViCo · Visual Genome clustering (fine categories)V-Measure: 0.57 -> 0.61Improved
use select instead of linear 100-dim compression (ablation)GloVe+ViCo · zero-shot-like unseen class predictionaccuracyImproved
concatenate ViCo (linear) to GloVeGloVe · Discriminative Attributesavg F1: 63.85 -> 64.46Improved
concatenate ViCo (linear) to GloVeGloVe · MS-COCO caption-image retrievalRecall@1 (Im2Cap): 44.8 -> 46.3Improved
concatenate ViCo (linear) to GloVeGloVe · VQA v2.0 test-devoverall accuracy: 67.5 -> 67.7Improved
replace GloVe with random vectorsGloVe · Discriminative Attributesavg F1: 63.85 -> 50.03Hurt
replace GloVe with random vectorsGloVe · VQA v2.0 test-devoverall accuracy: 67.5 -> 66.1No 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