Video Understanding
task
ID: videounderstanding
Related Papers
In-the-Wild Video Question Answering
AbstractExisting video understanding datasets mostly focus on human interactions, with little attention being paid to the “in the wild” settings, where the videos are recorded outdoors. We propose WILDQA, a …...
Learning to Focus on the Foreground for Temporal Sentence Grounding
AbstractTemporal sentence grounding (TSG) is crucial and fundamental for video understanding. Previous works typically model the target activity referred to the sentence query in a video by extracting the appearance …...