Test of Time: Instilling Video-Language Models with a Sense of Time
This work addresses a key limitation in video understanding for AI applications, offering a low-cost method to improve temporal awareness in existing models, though it is incremental as it builds on prior models without re-training from scratch.
The paper tackled the problem of video-language models lacking temporal understanding, specifically consistency of time order, and found that seven existing models struggled with this. By proposing a temporal adaptation recipe on VideoCLIP with post-pretraining on small data, they achieved performance gains in zero-shot evaluations on tasks requiring higher time awareness.
Modelling and understanding time remains a challenge in contemporary video understanding models. With language emerging as a key driver towards powerful generalization, it is imperative for foundational video-language models to have a sense of time. In this paper, we consider a specific aspect of temporal understanding: consistency of time order as elicited by before/after relations. We establish that seven existing video-language models struggle to understand even such simple temporal relations. We then question whether it is feasible to equip these foundational models with temporal awareness without re-training them from scratch. Towards this, we propose a temporal adaptation recipe on top of one such model, VideoCLIP, based on post-pretraining on a small amount of video-text data. We conduct a zero-shot evaluation of the adapted models on six datasets for three downstream tasks which require varying degrees of time awareness. We observe encouraging performance gains especially when the task needs higher time awareness. Our work serves as a first step towards probing and instilling a sense of time in existing video-language models without the need for data and compute-intense training from scratch.