Long-Term Recurrent Convolutional Networks for Visual Recognition and Description

TitleLong-Term Recurrent Convolutional Networks for Visual Recognition and Description
Publication TypeConference Paper
Year of Publication2015
AuthorsDonahue, J., Hendricks L. Anne, Guadarrama S., Rohrbach M., Venugopalan S., Saenko K., & Darrell T.
Other Numbers3751
Abstract

Models based on deep convolutional networks have dominated recent image interpretation tasks; we investigate whether models which are also recurrent, or "temporally deep", are effective for tasks involving sequences, visual and otherwise. We develop a novel recurrent convolutional architecture suitable for large-scale visual learning which is end-to-end trainable, and demonstrate the value of these models on benchmark video recognition tasks, image description and retrieval problems, and video narration challenges. In contrast to current models which assume a fixed spatio-temporal receptive field or simple temporal averaging for sequential processing, recurrent convolutional models are "doubly deep"' in that they can be compositional in spatial and temporal "layers". Such models may have advantages when target concepts are complex and/or training data are limited. Learning long-term dependencies is possible when nonlinearities are incorporated into the network state updates. Long-term RNN models are appealing in that they directly can map variable-length inputs (e.g., video frames) to variable length outputs (e.g., natural language text) and can model complex temporal dynamics; yet they can be optimized with backpropagation. Our recurrent long-term models are directly connected to modern visual convnet models and can be jointly trained to simultaneously learn temporal dynamics and convolutional perceptual representations. Our results show such models have distinct advantages over state-of-the-art models for recognition or generation which are separately defined and/or optimized.

Acknowledgment

This work was partially supported by a postdoctoral fellowship funded by the Federal Ministry of Education and Research (BMBF) through the FITweltweit program, administered by the German Academic Exchange Service (DAAD).

URLhttp://www.icsi.berkeley.edu/pubs/vision/longtermrecurrent15.pdf
Bibliographic Notes

Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2015), Boston, Massachusetts

Abbreviated Authors

J. Donahue, L. A. Hendricks, S. Guadarrama, M. Rohrbach, S. Venugopalan, K. Saenko, and T. Darrell

ICSI Research Group

Vision

ICSI Publication Type

Article in conference proceedings