English

Mean Box Pooling: A Rich Image Representation and Output Embedding for the Visual Madlibs Task

Computer Vision and Pattern Recognition 2016-08-10 v1 Artificial Intelligence Computation and Language Machine Learning

Abstract

We present Mean Box Pooling, a novel visual representation that pools over CNN representations of a large number, highly overlapping object proposals. We show that such representation together with nCCA, a successful multimodal embedding technique, achieves state-of-the-art performance on the Visual Madlibs task. Moreover, inspired by the nCCA's objective function, we extend classical CNN+LSTM approach to train the network by directly maximizing the similarity between the internal representation of the deep learning architecture and candidate answers. Again, such approach achieves a significant improvement over the prior work that also uses CNN+LSTM approach on Visual Madlibs.

Keywords

Cite

@article{arxiv.1608.02717,
  title  = {Mean Box Pooling: A Rich Image Representation and Output Embedding for the Visual Madlibs Task},
  author = {Ashkan Mokarian and Mateusz Malinowski and Mario Fritz},
  journal= {arXiv preprint arXiv:1608.02717},
  year   = {2016}
}

Comments

Accepted to BMVC'16

R2 v1 2026-06-22T15:15:38.493Z