Lightweight Attentional Feature Fusion: A New Baseline for Text-to-Video Retrieval

Hu, Fan; Chen, Aozhu; Ziyue, Wang,; Zhou, Fangming; Dong, Jianfeng; Li, Xirong

doi:10.1007/978-3-031-19781-9_26

Cited by 23 publications

(1 citation statement)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Details are listed in the supplementary material. Following existing literature (Croitoru et al 2021;Li et al 2020Li et al , 2019Ge et al 2022;Hu et al 2022a;Luo et al 2022;Zhao et al 2022;Gorti et al 2022;Ma et al 2022;Xue et al 2023;Liu et al 2022), we report Recall@1 (R@1), Recall@5 (R@5), Recall@10 (R@10), and mean result of them (Mean) for comparison. We use FLOPs to evaluate efficiency for text-video similarity calculation, which is calculated by THOP 2 .…”

Section: Methodsmentioning

confidence: 99%

Towards Efficient and Effective Text-to-Video Retrieval with Coarse-to-Fine Visual Representation Learning

Tian,

Cheng,

Liu

et al. 2024

AAAI

View full text Add to dashboard Cite

In recent years, text-to-video retrieval methods based on CLIP have experienced rapid development. The primary direction of evolution is to exploit the much wider gamut of visual and textual cues to achieve alignment. Concretely, those methods with impressive performance often design a heavy fusion block for sentence (words)-video (frames) interaction, regardless of the prohibitive computation complexity. Nevertheless, these approaches are not optimal in terms of feature utilization and retrieval efficiency. To address this issue, we adopt multi-granularity visual feature learning, ensuring the model's comprehensiveness in capturing visual content features spanning from abstract to detailed levels during the training phase. To better leverage the multi-granularity features, we devise a two-stage retrieval architecture in the retrieval phase. This solution ingeniously balances the coarse and fine granularity of retrieval content. Moreover, it also strikes a harmonious equilibrium between retrieval effectiveness and efficiency. Specifically, in training phase, we design a parameter-free text-gated interaction block (TIB) for fine-grained video representation learning and embed an extra Pearson Constraint to optimize cross-modal representation learning. In retrieval phase, we use coarse-grained video representations for fast recall of top-k candidates, which are then reranked by fine-grained video representations. Extensive experiments on four benchmarks demonstrate the efficiency and effectiveness. Notably, our method achieves comparable performance with the current state-of-the-art methods while being nearly 50 times faster.

show abstract