Dual-Level Collaborative Transformer for Image Captioning

By Yunpeng Luo, Jiayi Ji, Xiaoshuai Sun, Liujuan Cao, Yongjian Wu, Feiyue Huang, Chia-Wen Lin, Rongrong Ji. 2021

360 citations recorded by the source corpus.

Descriptive region features extracted by object detection networks have played an important role in the recent advancements of image captioning. However, they are still criticized for the lack of contextual information and fine-grained details, which in contrast are the merits of traditional grid features. In this paper, we introduce a novel Dual-Level Collaborative Transformer (DLCT) network to realize the complementary advantages of the two features. Concretely, in DLCT, these two features are first processed by a novel Dual-way Self Attenion (DWSA) to mine their intrinsic properties, where a Comprehensive Relation Attention component is also introduced to embed the geometric information. In addition, we propose a Locality-Constrained Cross Attention module to address the semantic noises caused by the direct fusion of these two features, where a geometric alignment graph is constructed to accurately align and reinforce region and grid features. To validate our model, we conduct extensive experiments on the highly competitive MS-COCO dataset, and achieve new state-of-the-art performance on both local and online test sets, i.e., 133.8% CIDEr on Karpathy split and 135.4% CIDEr on the official split.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Multimodal Learning, Natural Language Generation

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

  1. Giuseppe Fiameni
  2. Rita Cucchiara
  3. Marcella Cornia
  4. Lorenzo Baraldi
  5. Silvia Cascianelli
  6. Matteo Stefanini
  7. Lior Wolf
  8. Yoav Shalev

In Computer Vision and Pattern Recognition

  1. Rita Cucchiara
  2. Lorenzo Baraldi
  3. Marcella Cornia
  4. Giuseppe Fiameni
  5. Matteo Stefanini
  6. Rongrong Ji
  7. Silvia Cascianelli
  8. Feiyue Huang

In Multimodal Learning

  1. Giuseppe Fiameni
  2. Rita Cucchiara
  3. Lorenzo Baraldi
  4. Marcella Cornia
  5. Matteo Stefanini
  6. Silvia Cascianelli
  7. Rongrong Ji
  8. Xiaoshuai Sun

In Natural Language Generation

  1. Rita Cucchiara
  2. Lorenzo Baraldi
  3. Marcella Cornia
  4. Giuseppe Fiameni
  5. Matteo Stefanini
  6. Lior Wolf
  7. Ron Mokady
  8. Silvia Cascianelli

Citations in the corpus