SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1908.08527 · 2019

ViCo: Word Embeddings from Visual Co-occurrences

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

We propose to learn word embeddings from visual co-occurrences. Two words co-occur visually if both words apply to the same image or image region. Specifically, we extract four types of visual co-occurrences between object and attribute words from large-scale, textually-annotated visual databases like VisualGenome and ImageNet. We then train a multi-task log-bilinear model that compactly encodes word "meanings" represented by each co-occurrence type into a single visual word-vector. Through unsupervised clustering, supervised partitioning, and a zero-shot-like generalization analysis we show that our word embeddings complement text-only embeddings like GloVe by better representing similarities and differences between visual concepts that are difficult to obtain from text corpora alone. We further evaluate our embeddings on five downstream applications, four of which are vision-language tasks. Augmenting GloVe with our embeddings yields gains on all tasks. We also find that random embeddings perform comparably to learned embeddings on all supervised vision-language tasks, contrary to conventional wisdom.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("1908.08527")
get_code_for_paper("1908.08527")
have("1908.08527")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/1908.08527.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/1908.08527.svg)](https://syntology.ai/paper/1908.08527)

Connect an agent — have() is free.