Finding Everyday Objects Using Physical-World Search Engines: a Learning–To–Rank Approach

Abstract

In this study, we focus on the learning-to-rank physical objects task, which involves retrieving target objects from open-vocabulary user instructions in a human-in-the-loop setting. We propose MultiRankIt, which introduces the Crossmodal Noun Phrase Encoder to model the relationship between referring expressions and target bounding box, and the Crossmodal Region Feature Encoder to model the relationship between the target object and its surrounding contextual environment. Our model outperforms the baseline method in terms of mean reciprocal rank and recall@K.