Weakly-Supervised Video Object Grounding by Exploring Spatio-Temporal Contexts

Grounding objects in visual context from natural language queries is a crucial yet challenging vision-and-language task, which has gained increasing attention in recent years. Existing work has primarily investigated this task in the context of still images. Despite their effectiveness, these methods cannot be directly migrated into the video context, mainly due to 1) the complex spatio-temporal structure of videos and 2) the scarcity of fine-grained annotations of videos. To effectively ground objects in videos is profoundly more challenging and less explored.