Show and Tell
E899056
Show and Tell is a neural network-based image captioning model developed by Google that automatically generates natural language descriptions for images.
All labels observed (2)
| Label | Occurrences |
|---|---|
| Show & Tell | 1 |
| Show and Tell canonical | 1 |
How this entity was disambiguated
This entity first appeared as the object of triple T11003500 — resolving that mention is where its identity was fixed. The disambiguator weighed these candidate entities and picked the highlighted one (or “None”, minting a new entity). This is how homonymy is resolved: the same surface form can point to different entities.
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Show and Tell Context triple: [Show and Tell: A Neural Image Caption Generator, abbreviation, Show and Tell]
-
A.
Stories That Matter
Stories That Matter is the guiding motto of the Peabody Awards, emphasizing their focus on honoring impactful and socially significant storytelling in media.
-
B.
Making Things Up Again
"Making Things Up Again" is a comedic musical number from the Broadway show *The Book of Mormon*, in which Elder Cunningham humorously improvises and embellishes religious stories.
-
C.
Every Picture Tells a Story
Every Picture Tells a Story is a critically acclaimed 1971 rock album by Rod Stewart that blends rock, folk, and blues and includes some of his most iconic songs.
-
D.
Every Picture Tells a Story
Every Picture Tells a Story is a British film featuring actress Shirley Henderson in one of her notable early screen roles.
-
E.
The Show of Shows
The Show of Shows is a 1929 Warner Bros. all-star revue film from the early sound era, featuring numerous studio contract players in musical and comedy sketches.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Show and Tell Target entity description: Show and Tell is a neural network-based image captioning model developed by Google that automatically generates natural language descriptions for images.
-
A.
Stories That Matter
Stories That Matter is the guiding motto of the Peabody Awards, emphasizing their focus on honoring impactful and socially significant storytelling in media.
-
B.
Making Things Up Again
"Making Things Up Again" is a comedic musical number from the Broadway show *The Book of Mormon*, in which Elder Cunningham humorously improvises and embellishes religious stories.
-
C.
Every Picture Tells a Story
Every Picture Tells a Story is a critically acclaimed 1971 rock album by Rod Stewart that blends rock, folk, and blues and includes some of his most iconic songs.
-
D.
Every Picture Tells a Story
Every Picture Tells a Story is a British film featuring actress Shirley Henderson in one of her notable early screen roles.
-
E.
The Show of Shows
The Show of Shows is a 1929 Warner Bros. all-star revue film from the early sound era, featuring numerous studio contract players in musical and comedy sketches.
- F. None of above. chosen
Statements (47)
| Predicate | Object |
|---|---|
| instanceOf |
deep learning model
ⓘ
image captioning model ⓘ neural network ⓘ |
| achieves | state-of-the-art performance on MSCOCO (2015) ⓘ |
| approach |
end-to-end training
ⓘ
maximum likelihood training ⓘ |
| author |
Alexander Toshev
NERFINISHED
ⓘ
Dumitru Erhan NERFINISHED ⓘ Oriol Vinyals NERFINISHED ⓘ Samy Bengio NERFINISHED ⓘ |
| basedOn |
convolutional neural network
ⓘ
encoder-decoder architecture ⓘ recurrent neural network ⓘ sequence-to-sequence model ⓘ |
| captionStyle | descriptive sentences ⓘ |
| developer |
Google
ⓘ
Google Research NERFINISHED ⓘ |
| domain |
computer vision
ⓘ
multimodal learning ⓘ natural language processing ⓘ |
| evaluationMetric |
BLEU
NERFINISHED
ⓘ
CIDEr NERFINISHED ⓘ METEOR ⓘ |
| featureExtractor | Inception CNN GENERATED ⓘ |
| implementedIn | TensorFlow (research implementation) NERFINISHED ⓘ |
| influenced |
Neural image captioning research
ⓘ
Show, Attend and Tell NERFINISHED ⓘ |
| input | image ⓘ |
| language | English ⓘ |
| learningType | supervised learning ⓘ |
| modality | vision-to-language ⓘ |
| optimizationAlgorithm | stochastic gradient descent ⓘ |
| organization | Google Brain NERFINISHED ⓘ |
| output | natural language caption ⓘ |
| paperTitle | Show and Tell: A Neural Image Caption Generator NERFINISHED ⓘ |
| publicationVenue | CVPR NERFINISHED ⓘ |
| publicationYear | 2015 ⓘ |
| relatedTo | encoder-decoder neural networks for machine translation ⓘ |
| task |
automatic image captioning
ⓘ
natural language description generation ⓘ |
| trainedOn |
Flickr30k dataset
NERFINISHED
ⓘ
Flickr8k dataset NERFINISHED ⓘ MSCOCO dataset ⓘ |
| uses |
CNN encoder
ⓘ
LSTM NERFINISHED ⓘ RNN decoder ⓘ word embeddings ⓘ |
How these facts were elicited
The pipeline generated the facts above by prompting gpt-5.1 with this entity's name + description and the instruction below.
Instruction
You are a knowledge base construction expert. Given a subject entity and a description of it, return factual statements that you know for the subject as a JSON list of dictionaries(triples), where keys must be "subject", "predicate" and "object". The number of facts may be very high, between 25 to 50 or more, for very popular subjects. For less popular subjects, the number of facts can be very low, like 5 or 10. # Requirements - If you don't know the subject at all, return an empty list. - If the subject is not a named entity, return an empty list. - Include at least one triple where predicate is "instanceOf". - Do not get too wordy. - Separate several objects into multiple triples with one object.
Input
Subject: Show and Tell Description of subject: Show and Tell is a neural network-based image captioning model developed by Google that automatically generates natural language descriptions for images.
Referenced by (2)
Full triples — surface form annotated when it differs from this entity's canonical label.
this entity surface form:
Show & Tell