AI Paper Atlas

Research map / Vision-language and multimodal / Human and embodied modeling

Creating Images by Learning Image Semantics Using Vector Space Models

Derrall Heath, Dan Ventura

AAAI 2016 · Vision-language and multimodal › Human and embodied modeling · approach: Neural image captioning · 6 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
predict word vectors (Vector) instead of adjectives directly (Binary relevance)visual semantic model · 145 adjectives 10-fold CVcoverage: 0.533 -> 0.628Hurt
predict word vectors (Vector) instead of adjectives directly (Binary relevance)visual semantic model · 145 adjectives 10-fold CVranking loss: 0.297 -> 0.357Hurt
Vector model versus random ranking on trained adjectivesvisual semantic model · 145 adjectives 10-fold CVcoverage: 0.768 -> 0.628Improved
Vector model versus random ranking on unseen adjectivesvisual semantic model · Zero-shot, 10 unseen adjectivescoverage: 0.709 -> 0.444Improved
Vector model versus random ranking on unseen adjectivesvisual semantic model · Zero-shot, 10 unseen adjectivesranking loss: 0.502 -> 0.199Improved
cluster images of similar versus distinct SEEN adjectivesDARCI · SEEN adjective setsentropy: 0.857 -> 0.714Mixed
cluster images of similar versus distinct SEEN adjectivesDARCI · SEEN adjective setspurity: 0.360 -> 0.440Mixed
similar versus dissimilar seen partner for unseen adjectivesDARCI · UNSEEN adjectivesentropy: 0.691 -> 0.480Mixed
similar versus dissimilar seen partner for unseen adjectivesDARCI · UNSEEN adjectivespurity: 0.775 -> 0.850Mixed
similar versus dissimilar seen partner for non-adjectivesDARCI · non-adjectivesentropy: 0.828 -> 0.479Mixed
similar versus dissimilar seen partner for non-adjectivesDARCI · non-adjectivespurity: 0.680 -> 0.840Mixed

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