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

arXiv: https://arxiv.org/abs/2401.00701 · HTML: https://mlsanity.com/paper/2401.00701/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 28 references that are in the map.
- First posted on arXiv 1 Jan 2024.

## Builds on (most cited first, 21 of 21)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models](https://mlsanity.com/paper/2112.10741/) (2021)
- [VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding](https://mlsanity.com/paper/2109.14084/) (2021)
- [ClipCap: CLIP Prefix for Image Captioning](https://mlsanity.com/paper/2111.09734/) (2021)
- [VATEX: A Large-Scale, High-Quality Multilingual Dataset for Video-and-Language Research](https://mlsanity.com/paper/1904.03493/) (2019)
- [Multi-modal Transformer for Video Retrieval](https://mlsanity.com/paper/2007.10639/) (2020)
- [X-CLIP: End-to-End Multi-grained Contrastive Learning for Video-Text Retrieval](https://mlsanity.com/paper/2207.07285/) (2022)
- [Advancing High-Resolution Video-Language Representation with Large-Scale Video Transcriptions](https://mlsanity.com/paper/2111.10337/) (2021)
- [CLIP2Video: Mastering Video-Text Retrieval via Image CLIP](https://mlsanity.com/paper/2106.11097/) (2021)
- [Knowledge Distillation from A Stronger Teacher](https://mlsanity.com/paper/2205.10536/) (2022)
- [X-Pool: Cross-Modal Language-Video Attention for Text-Video Retrieval](https://mlsanity.com/paper/2203.15086/) (2022)
- [TS2-Net: Token Shift and Selection Transformer for Text-Video Retrieval](https://mlsanity.com/paper/2207.07852/) (2022)
- [HiT: Hierarchical Transformer with Momentum Contrast for Video-Text Retrieval](https://mlsanity.com/paper/2103.15049/) (2021)
- [TEACHTEXT: CrossModal Generalized Distillation for Text-Video Retrieval](https://mlsanity.com/paper/2104.08271/) (2021)
- [Bridging Video-text Retrieval with Multiple Choice Questions](https://mlsanity.com/paper/2201.04850/) (2022)
- [Disentangled Representation Learning for Text-Video Retrieval](https://mlsanity.com/paper/2203.07111/) (2022)
- [CLIP-Art: Contrastive Pre-training for Fine-Grained Art Classification](https://mlsanity.com/paper/2204.14244/) (2022)
- [SEA: Sentence Encoder Assembly for Video Retrieval by Textual Queries](https://mlsanity.com/paper/2011.12091/) (2020)
- [Lightweight Attentional Feature Fusion: A New Baseline for Text-to-Video Retrieval](https://mlsanity.com/paper/2112.01832/) (2021)

## Built on by (most cited first, 12 of 12)

- [HVD: Human Vision-Driven Video Representation Learning for Text-Video Retrieval](https://mlsanity.com/paper/2601.16155/) (2026)
- [TokenBinder: Text-Video Retrieval with One-to-Many Alignment Paradigm](https://mlsanity.com/paper/2409.19865/) (2024)
- [NeighborRetr: Balancing Hub Centrality in Cross-Modal Retrieval](https://mlsanity.com/paper/2503.10526/) (2025)
- [Quantifying and Narrowing the Unknown: Interactive Text-to-Video Retrieval via Uncertainty Minimization](https://mlsanity.com/paper/2507.15504/) (2025)
- [Hybrid-Tower: Fine-grained Pseudo-query Interaction and Generation for Text-to-Video Retrieval](https://mlsanity.com/paper/2509.04773/) (2025)
- [Rebalancing Contrastive Alignment with Bottlenecked Semantic Increments in Text-Video Retrieval](https://mlsanity.com/paper/2505.12499/) (2025)
- [Adversarial Video Promotion Against Text-to-Video Retrieval](https://mlsanity.com/paper/2508.06964/) (2025)
- [TCMA: Text-Conditioned Multi-granularity Alignment for Drone Cross-Modal Text-Video Retrieval](https://mlsanity.com/paper/2510.10180/) (2025)
- [Vote-in-Context: Turning VLMs into Zero-Shot Rank Fusers](https://mlsanity.com/paper/2511.01617/) (2025)
- [SAVE: Speech-Aware Video Representation Learning for Video-Text Retrieval](https://mlsanity.com/paper/2603.08224/) (2026)
- [MoVA: Learning Asymmetric Dual Projections for Modular Long Video-Text Alignment](https://mlsanity.com/paper/2607.00858/) (2026)
- [TAME: Temporal-Aware Mixture-of-Experts for Text-Video Retrieval](https://mlsanity.com/paper/2609.02204/) (2026)

## Abstract (arXiv)

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.