English

UniVSE: Robust Visual Semantic Embeddings via Structured Semantic Representations

Computer Vision and Pattern Recognition 2019-04-30 v2 Computation and Language Machine Learning

Abstract

We propose Unified Visual-Semantic Embeddings (UniVSE) for learning a joint space of visual and textual concepts. The space unifies the concepts at different levels, including objects, attributes, relations, and full scenes. A contrastive learning approach is proposed for the fine-grained alignment from only image-caption pairs. Moreover, we present an effective approach for enforcing the coverage of semantic components that appear in the sentence. We demonstrate the robustness of Unified VSE in defending text-domain adversarial attacks on cross-modal retrieval tasks. Such robustness also empowers the use of visual cues to resolve word dependencies in novel sentences.

Keywords

Cite

@article{arxiv.1904.05521,
  title  = {UniVSE: Robust Visual Semantic Embeddings via Structured Semantic Representations},
  author = {Hao Wu and Jiayuan Mao and Yufeng Zhang and Yuning Jiang and Lei Li and Weiwei Sun and Wei-Ying Ma},
  journal= {arXiv preprint arXiv:1904.05521},
  year   = {2019}
}

Comments

v1 is the full version which is accepted by CVPR 2019. v2 is the short version accepted by NAACL 2019 SpLU-RoboNLP workshop (in non-archival proceedings)

R2 v1 2026-06-23T08:36:17.073Z