Localizing Moments in Video with Temporal Language
This work addresses the challenge of video moment localization for applications in video search and understanding, presenting an incremental improvement with a new dataset for controlled studies.
The paper tackles the problem of localizing moments in videos using natural language queries by proposing a model that explicitly reasons about temporal segments, showing that temporal context is crucial for handling phrases with temporal language. They introduce the TEMPO dataset with real videos and human-annotated sentences to benchmark temporal reasoning in video localization.
Localizing moments in a longer video via natural language queries is a new, challenging task at the intersection of language and video understanding. Though moment localization with natural language is similar to other language and vision tasks like natural language object retrieval in images, moment localization offers an interesting opportunity to model temporal dependencies and reasoning in text. We propose a new model that explicitly reasons about different temporal segments in a video, and shows that temporal context is important for localizing phrases which include temporal language. To benchmark whether our model, and other recent video localization models, can effectively reason about temporal language, we collect the novel TEMPOral reasoning in video and language (TEMPO) dataset. Our dataset consists of two parts: a dataset with real videos and template sentences (TEMPO - Template Language) which allows for controlled studies on temporal language, and a human language dataset which consists of temporal sentences annotated by humans (TEMPO - Human Language).