Current text-video retrieval methods mainly rely on cross-modal matching between queries and videos to calculate their similarity scores, which are then sorted to obtain retrieval results. This method considers the matching between each candidate video and the query, but it incurs a significant time cost and will increase notably with the increase of candidates. Generative models are common in natural language processing and computer vision, and have been successfully applied in document retrieval, but their application in multimodal retrieval remains unexplored. To enhance retrieval efficiency, in this paper, we introduce a model-based video indexer named T2VIndexer, which is a sequence-to-sequence generative model directly generating video identifiers and retrieving candidate videos with constant time complexity. T2VIndexer aims to reduce retrieval time while maintaining high accuracy. To achieve this goal, we propose video identifier encoding and query-identifier augmentation approaches to represent videos as short sequences while preserving their semantic information. Our method consistently enhances the retrieval efficiency of current state-of-the-art models on four standard datasets. It enables baselines with only 30\%-50\% of the original retrieval time to achieve better retrieval performance on MSR-VTT (+1.0%), MSVD (+1.8%), ActivityNet (+1.5%), and DiDeMo (+0.2%). The code is available at https://github.com/Lilidamowang/T2VIndexer-generativeSearch.

翻译：当前文本-视频检索方法主要依赖于查询与视频之间的跨模态匹配来计算相似度分数，进而排序获得检索结果。该方法考虑了每个候选视频与查询的匹配，但会产生显著的时间成本，且随着候选视频数量的增加而急剧上升。生成式模型在自然语言处理和计算机视觉领域已很常见，并已成功应用于文档检索，但其在多模态检索中的应用尚未得到探索。为提升检索效率，本文提出了一种基于模型的视频索引器T2VIndexer，该模型是一种序列到序列的生成式模型，能够直接生成视频标识符并以恒定时间复杂度检索候选视频。T2VIndexer旨在保持高精度的同时减少检索时间。为实现这一目标，我们提出了视频标识符编码和查询-标识符增强方法，将视频表示为短序列的同时保留其语义信息。我们的方法在四个标准数据集上持续提升了当前最先进模型的检索效率。该方法使基线模型仅需原始检索时间的30%-50%，即可在MSR-VTT（+1.0%）、MSVD（+1.8%）、ActivityNet（+1.5%）和DiDeMo（+0.2%）数据集上实现更好的检索性能。代码发布于https://github.com/Lilidamowang/T2VIndexer-generativeSearch。