MSRC: multimodal spatial regression with semantic context for phrase grounding

Given a textual description of an image, phrase grounding localizes objects in the image referred by query phrases in the description. State-of-the-art methods treat phrase grounding as a ranking problem and address it by retrieving a set of proposals according to the query’s semantics, which are limited by the performance of independent proposal generation systems and ignore useful cues from context in the description. In this paper, we propose a novel multimodal spatial regression with semantic context (MSRC) system which not only predicts the location of ground truth based on proposal bounding boxes, but also refines prediction results by penalizing similarities of different queries coming from same sentences. There are two advantages of MSRC: First, it sidesteps the performance upper bound from independent proposal generation systems by adopting regression mechanism. Second, MSRC not only encodes the semantics of a query phrase, but also considers its relation with context (i.e., other queries from the same sentence) via a context refinement network. Experiments show MSRC system achieves a significant improvement in accuracy on two popular datasets: Flickr30K Entities and Refer-it Game, with 6.64 and 5.28% increase over the state of the arts, respectively.