Incorporating Copying Mechanism in Image Captioning for Learning Novel Objects

Abstract

Image captioning often requires a large set of training image-sentence pairs. In practice, however, acquiring sufficient training pairs is always expensive, making the recent captioning models limited in their ability to describe objects outside of training corpora (i.e., novel objects). In this paper, we present Long Short-Term Memory with Copying Mechanism (LSTM-C) --- a new architecture that incorporates copying into the Convolutional Neural Networks (CNN) plus Recurrent Neural Networks (RNN) image captioning framework, for describing novel objects in captions. Specifically, freely available object recognition datasets are leveraged to develop classifiers for novel objects. Our LSTM-C then nicely integrates the standard word-by-word sentence generation by a decoder RNN with copying mechanism which may instead select words from novel objects at proper places in the output sentence. Extensive experiments are conducted on both MSCOCO image captioning and ImageNet datasets, demonstrating the ability of our proposed LSTM-C architecture to describe novel objects. Furthermore, superior results are reported when compared to state-of-the-art deep models.

CVPR17

References in corpus (7)

• Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
• Caffe: Convolutional Architecture for Fast Feature Embedding
• Image Captioning with Semantic Attention
• Language Models for Image Captioning: The Quirks and What Works
• Learning like a Child: Fast Novel Visual Concept Learning from Sentence Descriptions of Images
• Boosting Image Captioning with Attributes
• Video Captioning with Transferred Semantic Attributes

Cited by in corpus (15)

• Trends in Integration of Vision and Language Research: A Survey of Tasks, Datasets, and Methods
• Exploring Visual Relationship for Image Captioning
• Jointly Localizing and Describing Events for Dense Video Captioning
• Auto-captions on GIF: A Large-scale Video-sentence Dataset for Vision-language Pre-training
• Partially-Supervised Image Captioning
• To Create What You Tell: Generating Videos from Captions
• Temporal Deformable Convolutional Encoder-Decoder Networks for Video Captioning
• A Comprehensive Survey of Deep Learning for Image Captioning
• YH Technologies at ActivityNet Challenge 2018
• X-Linear Attention Networks for Image Captioning
• Trimmed Action Recognition, Dense-Captioning Events in Videos, and Spatio-temporal Action Localization with Focus on ActivityNet Challenge 2019
• Hierarchy Parsing for Image Captioning
• Pointing Novel Objects in Image Captioning
• Explain Me the Painting: Multi-Topic Knowledgeable Art Description Generation
• X-modaler: A Versatile and High-performance Codebase for Cross-modal Analytics