Verbs in Action: Improving verb understanding in video-language models
This addresses a critical bottleneck for video-language models in applications requiring action and temporal understanding, offering a novel solution rather than just highlighting the issue.
The paper tackles the problem of limited verb understanding in CLIP-based video-language models, which restricts their performance in real-world video applications, by proposing a Verb-Focused Contrastive (VFC) framework that achieves state-of-the-art results in zero-shot performance on three downstream tasks.
Understanding verbs is crucial to modelling how people and objects interact with each other and the environment through space and time. Recently, state-of-the-art video-language models based on CLIP have been shown to have limited verb understanding and to rely extensively on nouns, restricting their performance in real-world video applications that require action and temporal understanding. In this work, we improve verb understanding for CLIP-based video-language models by proposing a new Verb-Focused Contrastive (VFC) framework. This consists of two main components: (1) leveraging pretrained large language models (LLMs) to create hard negatives for cross-modal contrastive learning, together with a calibration strategy to balance the occurrence of concepts in positive and negative pairs; and (2) enforcing a fine-grained, verb phrase alignment loss. Our method achieves state-of-the-art results for zero-shot performance on three downstream tasks that focus on verb understanding: video-text matching, video question-answering and video classification. To the best of our knowledge, this is the first work which proposes a method to alleviate the verb understanding problem, and does not simply highlight it.