{"ID":2874086,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.04773","arxiv_id":"2509.04773","title":"Hybrid-Tower: Fine-grained Pseudo-query Interaction and Generation for Text-to-Video Retrieval","abstract":"The Text-to-Video Retrieval (T2VR) task aims to retrieve unlabeled videos by textual queries with the same semantic meanings. Recent CLIP-based approaches have explored two frameworks: Two-Tower versus Single-Tower framework, yet the former suffers from low effectiveness, while the latter suffers from low efficiency. In this study, we explore a new Hybrid-Tower framework that can hybridize the advantages of the Two-Tower and Single-Tower framework, achieving high effectiveness and efficiency simultaneously. We propose a novel hybrid method, Fine-grained Pseudo-query Interaction and Generation for T2VR, ie, PIG, which includes a new pseudo-query generator designed to generate a pseudo-query for each video. This enables the video feature and the textual features of pseudo-query to interact in a fine-grained manner, similar to the Single-Tower approaches to hold high effectiveness, even before the real textual query is received. Simultaneously, our method introduces no additional storage or computational overhead compared to the Two-Tower framework during the inference stage, thus maintaining high efficiency. Extensive experiments on five commonly used text-video retrieval benchmarks demonstrate that our method achieves a significant improvement over the baseline, with an increase of $1.6\\% \\sim 3.9\\%$ in R@1. Furthermore, our method matches the efficiency of Two-Tower models while achieving near state-of-the-art performance, highlighting the advantages of the Hybrid-Tower framework.","short_abstract":"The Text-to-Video Retrieval (T2VR) task aims to retrieve unlabeled videos by textual queries with the same semantic meanings. Recent CLIP-based approaches have explored two frameworks: Two-Tower versus Single-Tower framework, yet the former suffers from low effectiveness, while the latter suffers from low efficiency. I...","url_abs":"https://arxiv.org/abs/2509.04773","url_pdf":"https://arxiv.org/pdf/2509.04773v1","authors":"[\"Bangxiang Lan\",\"Ruobing Xie\",\"Ruixiang Zhao\",\"Xingwu Sun\",\"Zhanhui Kang\",\"Gang Yang\",\"Xirong Li\"]","published":"2025-09-05T03:05:50Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false}