Long-Term Recurrent Convolutional Networks for Visual Recognition and Description

University of California, Berkeley · International Computer Science Institute · +2 more institutions

PubMed
Indexed incrossrefpubmed

Abstract

Models based on deep convolutional networks have dominated recent image interpretation tasks; we investigate whether models which are also recurrent are effective for tasks involving sequences, visual and otherwise. We describe a class of recurrent convolutional architectures which is end-to-end trainable and suitable for large-scale visual understanding tasks, and demonstrate the value of these models for activity recognition, image captioning, and video description. In contrast to previous models which assume a fixed visual representation or perform simple temporal averaging for sequential processing, recurrent convolutional models are "doubly deep" in that they learn compositional representations in space…

Citation impact

1,571
total citations
FWCI
80.08
Percentile
100%
References
111
Citations per year

Authors

7

Topics & keywords

Keywords
  • Computer science
  • Artificial intelligence
  • Convolutional neural network
  • Recurrent neural network
  • Pattern recognition (psychology)
  • Representation (politics)
  • Deep learning
  • Differentiable function
UN Sustainable Development Goals
  • Quality Education
No related works found for this paper.

Funding