Deeply Supervised Multimodal Attentional Translation Embeddings for Visual Relationship Detection
This addresses scene understanding for computer vision applications, but appears incremental as it builds on prior work with a novel hybrid approach.
The paper tackles visual relationship detection by introducing a deeply supervised two-branch architecture with multimodal attentional translation embeddings, which outperforms all existing methods on the VRD dataset.
Detecting visual relationships, i.e. <Subject, Predicate, Object> triplets, is a challenging Scene Understanding task approached in the past via linguistic priors or spatial information in a single feature branch. We introduce a new deeply supervised two-branch architecture, the Multimodal Attentional Translation Embeddings, where the visual features of each branch are driven by a multimodal attentional mechanism that exploits spatio-linguistic similarities in a low-dimensional space. We present a variety of experiments comparing against all related approaches in the literature, as well as by re-implementing and fine-tuning several of them. Results on the commonly employed VRD dataset [1] show that the proposed method clearly outperforms all others, while we also justify our claims both quantitatively and qualitatively.