@article{WangYangMeinel2018,
  author    = {Wang, Cheng and Yang, Haojin and Meinel, Christoph},
  title     = {Image Captioning with Deep Bidirectional LSTMs and Multi-Task Learning},
  series = {ACM transactions on multimedia computing, communications, and applications},
  volume    = {14},
  journal   = {ACM transactions on multimedia computing, communications, and applications},
  number    = {2},
  publisher = {Association for Computing Machinery},
  address   = {New York},
  issn      = {1551-6857},
  doi       = {10.1145/3115432},
  pages     = {20},
  year      = {2018},
  abstract  = {Generating a novel and descriptive caption of an image is drawing increasing interests in computer vision, natural language processing, and multimedia communities. In this work, we propose an end-to-end trainable deep bidirectional LSTM (Bi-LSTM (Long Short-Term Memory)) model to address the problem. By combining a deep convolutional neural network (CNN) and two separate LSTM networks, our model is capable of learning long-term visual-language interactions by making use of history and future context information at high-level semantic space. We also explore deep multimodal bidirectional models, in which we increase the depth of nonlinearity transition in different ways to learn hierarchical visual-language embeddings. Data augmentation techniques such as multi-crop, multi-scale, and vertical mirror are proposed to prevent over-fitting in training deep models. To understand how our models "translate" image to sentence, we visualize and qualitatively analyze the evolution of Bi-LSTM internal states over time. The effectiveness and generality of proposed models are evaluated on four benchmark datasets: Flickr8K, Flickr30K, MSCOCO, and Pascal1K datasets. We demonstrate that Bi-LSTM models achieve highly competitive performance on both caption generation and image-sentence retrieval even without integrating an additional mechanism (e.g., object detection, attention model). Our experiments also prove that multi-task learning is beneficial to increase model generality and gain performance. We also demonstrate the performance of transfer learning of the Bi-LSTM model significantly outperforms previous methods on the Pascal1K dataset.},
  language  = {en}
}