CoChat

Deep visual-semantic alignments for generating image descriptions

Karpathy, Andrej, Fei-Fei, Li · 2015 · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

The DOI matches its Crossref record; 63 of the 67 references it cites were found in a registry or an index.

Abstract

We present a model that generates natural language descriptions of images and their regions. Our approach leverages datasets of images and their sentence descriptions to learn about the inter-modal correspondences between language and visual data. Our alignment model is based on a novel combination of Convolutional Neural Networks over image regions, bidirectional Recurrent Neural Networks over sentences, and a structured objective that aligns the two modalities through a multimodal embedding. We then describe a Multimodal Recurrent Neural Network architecture that uses the inferred alignments to learn to generate novel descriptions of image regions. We demonstrate that our alignment model produces state of the art results in retrieval experiments on Flickr8K, Flickr30K and MSCOCO datasets. We then show that the generated descriptions significantly outperform retrieval baselines on both full images and on a new dataset of region-level annotations.

Overview

Integrity signals

Registry

Crossref · 10.1109/cvpr.2015.7298932

Cites

63 of 63 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Verification

Claims the paper makes

This paper’s full text isn’t openly available, so its claims and self-check weren’t run. The registry and citation checks still apply.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Citations

Cites

Research works printed but not linked: 2

  1. 10.1016/0364-0213(90)90002-E · doi:10.1016/0364-0213(90)90002-e · Paper page
  2. 10.1007/3-540-33486-6_6 · doi:10.1007/3-540-33486-6_6 · Paper page

Cited by

See all 4,902

Metadata

Authors
Karpathy, A., & Fei-Fei, L.
Affiliations
Stanford University (US)
Venue
2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Publisher
IEEE
Published
2015-06
Pages
3128-3137
ISSN
1063-6919 (ISSN-L)
OpenAlex
W1905882502
Cited by
4,902
References
67
Citations by year
2026: 145 · 2025: 313 · 2024: 387 · 2023: 464 · 2022: 427 · 2021: 542 · 2020: 509 · 2019: 621 · 2018: 555 · 2017: 471 · 2016: 324 · 2015: 141
FWCI
203.84
Type
conference paper
Language
en
Open access
closed
Locations
IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings (publishedVersion)
Topics
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Multimodal Machine Learning Applications
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image Retrieval and Classification Techniques
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Image and Video Retrieval Techniques
Keywords
image description generation, visual-semantic alignment, multimodal alignment, convolutional neural networks, bidirectional recurrent neural network, multimodal embeddings, image retrieval, Flickr8k, Flickr30k, MS COCO

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.