Pre-trained vision-language models (VLMs) have enabled significant progress in open vocabulary computer vision tasks such as image classification, object detection and image segmentation. Some recent works have focused on extending VLMs to open vocabulary single label action classification in videos. However, previous methods fall short in holistic video understanding which requires the ability to simultaneously recognize multiple actions and entities e.g., objects in the video in an open vocabulary setting. We formulate this problem as open vocabulary multilabel video classification and propose a method to adapt a pre-trained VLM such as CLIP to solve this task. We leverage large language models (LLMs) to provide semantic guidance to the VLM about class labels to improve its open vocabulary performance with two key contributions. First, we propose an end-to-end trainable architecture that learns to prompt an LLM to generate soft attributes for the CLIP text-encoder to enable it to recognize novel classes. Second, we integrate a temporal modeling module into CLIP's vision encoder to effectively model the spatio-temporal dynamics of video concepts as well as propose a novel regularized finetuning technique to ensure strong open vocabulary classification performance in the video domain. Our extensive experimentation showcases the efficacy of our approach on multiple benchmark datasets.

翻译：预训练视觉语言模型（VLM）已在开放词汇计算机视觉任务（如图像分类、目标检测和图像分割）中取得显著进展。近期一些研究致力于将VLM扩展至视频中的开放词汇单标签动作分类。然而，先前方法在整体视频理解方面存在不足——这需要模型在开放词汇环境下同时识别视频中的多个动作与实体（例如物体）。我们将此问题形式化为开放词汇多标签视频分类，并提出一种适配预训练VLM（如CLIP）以解决该任务的方法。通过利用大语言模型（LLM）为VLM提供关于类别标签的语义指导，我们以两项关键贡献提升其开放词汇性能：首先，我们提出一种端到端可训练架构，该架构学习提示LLM为CLIP文本编码器生成软属性，使其能够识别新类别；其次，我们在CLIP视觉编码器中集成时序建模模块，以有效建模视频概念的时空动态特性，并提出一种新颖的正则化微调技术，确保在视频领域实现强大的开放词汇分类性能。大量实验验证了我们的方法在多个基准数据集上的有效性。