2019/06/17 by Aly Magassouba, Magassouba, Aly, Komei Sugiura +5
Computer Science · #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Multimodal Machine Learning Applications #Robotics (cs.RO) #Topic Modeling
paper · pdf · doi:10.48550/arxiv.1906.06830
openalex publication_date 2019/06/17 · openalex created_date 2019/06/27 · openalex updated_date 2026/07/28
In this paper, we address multimodal language understanding for unconstrained fetching instruction in domestic service robots context. A typical fetching instruction such as "Bring me the yellow toy from the white shelf" requires to infer the user intention, that is what object (target) to fetch and from where (source). To solve the task, we propose a Multimodal Target-source Classifier Model (MTCM), which predicts the region-wise likelihood of target and source candidates in the scene. Unlike other methods, MTCM can handle regionwise classification based on linguistic and visual features. We evaluated our approach that outperformed the state-of-the-art method on a standard data set. In addition, we extended MTCM with Generative Adversarial Nets (MTCM-GAN), and enabled simultaneous data augmentation and classification.