CLIP2TV: Align, Match and Distill for Video-Text Retrieval
This work addresses video-text retrieval for multimedia applications, presenting an incremental improvement with specific performance gains.
The paper tackles video-text retrieval by exploring critical elements in transformer-based methods, achieving a state-of-the-art result of 52.9% R1 on the MSR-VTT dataset, which is a 4.1% improvement over previous methods.
Modern video-text retrieval frameworks basically consist of three parts: video encoder, text encoder and the similarity head. With the success on both visual and textual representation learning, transformer based encoders and fusion methods have also been adopted in the field of video-text retrieval. In this report, we present CLIP2TV, aiming at exploring where the critical elements lie in transformer based methods. To achieve this, We first revisit some recent works on multi-modal learning, then introduce some techniques into video-text retrieval, finally evaluate them through extensive experiments in different configurations. Notably, CLIP2TV achieves 52.9@R1 on MSR-VTT dataset, outperforming the previous SOTA result by 4.1%.