Long-term Recurrent Convolutional Networks for Visual Recognition and Description

E260050

computer vision paper research paper scientific publication

"Long-term Recurrent Convolutional Networks for Visual Recognition and Description" is a research paper that introduces a deep learning architecture combining convolutional and recurrent neural networks to perform tasks like video recognition and automatic image or video captioning.

Try in SPARQL Jump to: Surface forms Disambiguation Statements Elicitation Referenced by

All labels observed (3)

Label	Occurrences
Long-term Recurrent Convolutional Networks for Visual Recognition and Description canonical	2
Long-term Recurrent Convolutional Network	1
Long-term Recurrent Convolutional Network architecture	1

How this entity was disambiguated

This entity first appeared as the object of triple T2373684 — 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: Long-term Recurrent Convolutional Networks for Visual Recognition and Description
Context triple: [Quoc V. Le, coAuthorOf, Long-term Recurrent Convolutional Networks for Visual Recognition and Description]

A. Inception architecture
The Inception architecture is a deep convolutional neural network design that introduced parallel multi-scale processing modules to achieve state-of-the-art image recognition performance with improved computational efficiency.
B. “Learning representations by back-propagating errors”
“Learning representations by back-propagating errors” is a landmark 1986 research paper that popularized the backpropagation algorithm for training multi-layer neural networks, helping to launch the modern field of deep learning.
C. Generative Adversarial Networks
Generative Adversarial Networks are a class of machine learning models in which two neural networks compete to generate highly realistic synthetic data, such as images, audio, or text.
D. Gradient-based learning applied to document recognition
"Gradient-based learning applied to document recognition" is a seminal 1998 paper by Yann LeCun and colleagues that introduced and demonstrated the effectiveness of convolutional neural networks for tasks like handwritten digit recognition, helping to lay the foundations of modern deep learning.
E. Large-Scale Distributed Deep Networks
Large-Scale Distributed Deep Networks is a seminal research work that introduced methods for training deep neural networks efficiently across large-scale distributed computing infrastructure, enabling breakthroughs in modern large-scale AI systems.
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: Long-term Recurrent Convolutional Networks for Visual Recognition and Description
Target entity description: "Long-term Recurrent Convolutional Networks for Visual Recognition and Description" is a research paper that introduces a deep learning architecture combining convolutional and recurrent neural networks to perform tasks like video recognition and automatic image or video captioning.

A. Inception architecture
The Inception architecture is a deep convolutional neural network design that introduced parallel multi-scale processing modules to achieve state-of-the-art image recognition performance with improved computational efficiency.
B. “Learning representations by back-propagating errors”
“Learning representations by back-propagating errors” is a landmark 1986 research paper that popularized the backpropagation algorithm for training multi-layer neural networks, helping to launch the modern field of deep learning.
C. Generative Adversarial Networks
Generative Adversarial Networks are a class of machine learning models in which two neural networks compete to generate highly realistic synthetic data, such as images, audio, or text.
D. Gradient-based learning applied to document recognition
"Gradient-based learning applied to document recognition" is a seminal 1998 paper by Yann LeCun and colleagues that introduced and demonstrated the effectiveness of convolutional neural networks for tasks like handwritten digit recognition, helping to lay the foundations of modern deep learning.
E. Large-Scale Distributed Deep Networks
Large-Scale Distributed Deep Networks is a seminal research work that introduced methods for training deep neural networks efficiently across large-scale distributed computing infrastructure, enabling breakthroughs in modern large-scale AI systems.
F. None of above. chosen

Statements (46)

Predicate	Object
instanceOf	computer vision paper ⓘ research paper ⓘ scientific publication ⓘ
addresses	long-range temporal dependencies in video ⓘ sequence learning for visual data ⓘ
appliesTo	image data ⓘ video data ⓘ
approach	combining CNN feature extraction with RNN sequence modeling ⓘ
basedOn	supervised learning ⓘ
citationForm	Long-term Recurrent Convolutional Networks for Visual Recognition and Description ⓘ
contribution	framework for generating natural language descriptions from visual input ⓘ integration of convolutional and recurrent networks for visual recognition ⓘ
demonstrates	end-to-end training for image captioning ⓘ end-to-end training for video description ⓘ joint modeling of vision and language ⓘ
field	computer vision ⓘ deep learning ⓘ machine learning ⓘ
focusesOn	image captioning ⓘ video captioning ⓘ video recognition ⓘ visual recognition ⓘ
hasAbbreviation	LRCN ⓘ
input	raw image frames ⓘ video frame sequences ⓘ
languageOutput	natural language sentences ⓘ
learningParadigm	end-to-end learning ⓘ
methodType	deep neural network architecture ⓘ
models	sequences of visual features ⓘ temporal dynamics in visual data ⓘ
output	class labels for visual recognition ⓘ textual descriptions of images ⓘ textual descriptions of videos ⓘ
proposes	Long-term Recurrent Convolutional Network architecture ⓘ linked to: Long-term Recurrent Convolutional Networks for Visual Recognition and Description
relatedTo	LSTM ⓘ linked to: LSTM networks convolutional neural network ⓘ image understanding ⓘ recurrent neural network ⓘ video understanding ⓘ vision and language models ⓘ
task	automatic caption generation ⓘ video classification ⓘ visual sequence modeling ⓘ
uses	LSTM units ⓘ convolutional neural networks ⓘ recurrent neural networks ⓘ

How these facts were elicited

Referenced by (4)

Full triples — surface form annotated when it differs from this entity's canonical label.

Quoc V. Le → coAuthorOf → Long-term Recurrent Convolutional Networks for Visual Recognition and Description ⓘ

Long-term Recurrent Convolutional Networks for Visual Recognition and Description → proposes → Long-term Recurrent Convolutional Network architecture ⓘ

linked to: Long-term Recurrent Convolutional Networks for Visual Recognition and Description

Long-term Recurrent Convolutional Networks for Visual Recognition and Description → citationForm → Long-term Recurrent Convolutional Networks for Visual Recognition and Description ⓘ

LRCN → fullName → Long-term Recurrent Convolutional Network ⓘ