Cross-Modality Attention with Semantic Graph Embedding for Multi-Label Classification


  • Renchun You Baidu VIS
  • Zhiyao Guo Computer Science Department, Xiamen University
  • Lei Cui Tsinghua University
  • Xiang Long Baidu VIS
  • Yingze Bao Baidu VIS
  • Shilei Wen Baidu VIS



Multi-label image and video classification are fundamental yet challenging tasks in computer vision. The main challenges lie in capturing spatial or temporal dependencies between labels and discovering the locations of discriminative features for each class. In order to overcome these challenges, we propose to use cross-modality attention with semantic graph embedding for multi-label classification. Based on the constructed label graph, we propose an adjacency-based similarity graph embedding method to learn semantic label embeddings, which explicitly exploit label relationships. Then our novel cross-modality attention maps are generated with the guidance of learned label embeddings. Experiments on two multi-label image classification datasets (MS-COCO and NUS-WIDE) show our method outperforms other existing state-of-the-arts. In addition, we validate our method on a large multi-label video classification dataset (YouTube-8M Segments) and the evaluation results demonstrate the generalization capability of our method.




How to Cite

You, R., Guo, Z., Cui, L., Long, X., Bao, Y., & Wen, S. (2020). Cross-Modality Attention with Semantic Graph Embedding for Multi-Label Classification. Proceedings of the AAAI Conference on Artificial Intelligence, 34(07), 12709-12716.



AAAI Technical Track: Vision