Dense Captioning with Joint Inference and Visual Context
arXiv:1611.06949
Abstract
Dense captioning is a newly emerging computer vision topic for understanding images with dense language descriptions. The goal is to densely detect visual concepts (e.g., objects, object parts, and interactions between them) from images, labeling each with a short descriptive phrase. We identify two key challenges of dense captioning that need to be properly addressed when tackling the problem. First, dense visual concept annotations in each image are associated with highly overlapping target regions, making accurate localization of each visual concept challenging. Second, the large amount of visual concepts makes it hard to recognize each of them by appearance alone. We propose a new model pipeline based on two novel ideas, joint inference and context fusion, to alleviate these two challenges. We design our model architecture in a methodical manner and thoroughly evaluate the variations in architecture. Our final model, compact and efficient, achieves state-of-the-art accuracy on Visual Genome for dense captioning with a relative gain of 73\% compared to the previous best algorithm. Qualitative experiments also reveal the semantic capabilities of our model in dense captioning.
References in corpus (18)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
- Caffe: Convolutional Architecture for Fast Feature Embedding
- Microsoft COCO Captions: Data Collection and Evaluation Server
- VQA: Visual Question Answering
- Fully Convolutional Networks for Semantic Segmentation
- Deep Fragment Embeddings for Bidirectional Image Sentence Mapping
- Rich feature hierarchies for accurate object detection and semantic segmentation
- Explain Images with Multimodal Recurrent Neural Networks
- Show and Tell: A Neural Image Caption Generator
- Ask Your Neurons: A Neural-based Approach to Answering Questions about Images
- Generation and Comprehension of Unambiguous Object Descriptions
- Visual Relationship Detection with Language Priors
- Aligning where to see and what to tell: image caption with region-based attention and scene factorization
- From Captions to Visual Concepts and Back
- CIDEr: Consensus-based Image Description Evaluation
- Modeling Context in Referring Expressions
- Face Detection with the Faster R-CNN