# Narrating the Video: Boosting Text-Video Retrieval via Comprehensive Utilization of Frame-Level Captions

arXiv: https://arxiv.org/abs/2503.05186 · HTML: https://mlsanity.com/paper/2503.05186/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Placed in Video understanding with MLLMs, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 37 of its 47 references that are in the map.
- First posted on arXiv 7 Mar 2025.

## Placed in

- Multimodal LLMs / vision-language models / [Video understanding with MLLMs](https://mlsanity.com/mllm/video-understanding-with-mllms/)

## Builds on (most cited first, 30 of 37)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks](https://mlsanity.com/paper/1908.02265/) (2019)
- [Localizing Moments in Video with Natural Language](https://mlsanity.com/paper/1708.01641/) (2017)
- [CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval](https://mlsanity.com/paper/2104.08860/) (2021)
- [Contrastive Learning with Hard Negative Samples](https://mlsanity.com/paper/2010.04592/) (2020)
- [VATEX: A Large-Scale, High-Quality Multilingual Dataset for Video-and-Language Research](https://mlsanity.com/paper/1904.03493/) (2019)
- [X-CLIP: End-to-End Multi-grained Contrastive Learning for Video-Text Retrieval](https://mlsanity.com/paper/2207.07285/) (2022)
- [Improving CLIP Training with Language Rewrites](https://mlsanity.com/paper/2305.20088/) (2023)
- [A Joint Sequence Fusion Model for Video Question Answering and Retrieval](https://mlsanity.com/paper/1808.02559/) (2018)
- [X-Pool: Cross-Modal Language-Video Attention for Text-Video Retrieval](https://mlsanity.com/paper/2203.15086/) (2022)
- [Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss](https://mlsanity.com/paper/2109.04290/) (2021)
- [Learning a Text-Video Embedding from Incomplete and Heterogeneous Data](https://mlsanity.com/paper/1804.02516/) (2018)
- [Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?](https://mlsanity.com/paper/2301.00184/) (2022)
- [Cross Modal Retrieval with Querybank Normalisation](https://mlsanity.com/paper/2112.12777/) (2021)
- [ALIP: Adaptive Language-Image Pre-training with Synthetic Caption](https://mlsanity.com/paper/2308.08428/) (2023)
- [Revisiting Temporal Modeling for CLIP-based Image-to-Video Knowledge Transferring](https://mlsanity.com/paper/2301.11116/) (2023)
- [UATVR: Uncertainty-Adaptive Text-Video Retrieval](https://mlsanity.com/paper/2301.06309/) (2023)
- [Unified Coarse-to-Fine Alignment for Video-Text Retrieval](https://mlsanity.com/paper/2309.10091/) (2023)
- [Text Is MASS: Modeling as Stochastic Embedding for Text-Video Retrieval](https://mlsanity.com/paper/2403.17998/) (2024)
- [Composed Video Retrieval via Enriched Context and Discriminative Embeddings](https://mlsanity.com/paper/2403.16997/) (2024)
- [Prototype-based Aleatoric Uncertainty Quantification for Cross-modal Retrieval](https://mlsanity.com/paper/2309.17093/) (2023)
- [Audio-Enhanced Text-to-Video Retrieval using Text-Conditioned Feature Alignment](https://mlsanity.com/paper/2307.12964/) (2023)

## Built on by (most cited first, 10 of 10)

- [BiMa: Towards Biases Mitigation for Text-Video Retrieval via Scene Element Guidance](https://mlsanity.com/paper/2506.03589/) (2025)
- [Captioning for Text-Video Retrieval via Dual-Group Direct Preference Optimization](https://mlsanity.com/paper/2509.16560/) (2025)
- [Binding Multiple Modalities via Multimodal Wasserstein Barycenter](https://mlsanity.com/paper/2609.33800/) (2026)
- [T2VParser: Adaptive Decomposition Tokens for Partial Alignment in Text to Video Retrieval](https://mlsanity.com/paper/2507.20518/) (2025)
- [Adaptive Multi-Agent Reasoning for Text-to-Video Retrieval](https://mlsanity.com/paper/2602.19040/) (2025)
- [GenState-AI: State-Aware Dataset for Text-to-Video Retrieval on AI-Generated Videos](https://mlsanity.com/paper/2603.14426/) (2026)
- [Distribution-Alignment Bridge for Uncertainty-Aware Text-to-Video Retrieval](https://mlsanity.com/paper/2607.20984/) (2026)
- [TraVEL: Trajectory-Guided Video Embedding Learning for Driving-Video Retrieval](https://mlsanity.com/paper/2608.13495/) (2026)
- [ViTAL-X: Video-Text Alignment with Cross-Modal Temporal Edits](https://mlsanity.com/paper/2609.00505/) (2026)
- [Position Aware Layer Queries for Test Time Training in Vision Language Models](https://mlsanity.com/paper/2609.34021/) (2026)

## Abstract (arXiv)

In recent text-video retrieval, the use of additional captions from vision-language models has shown promising effects on the performance. However, existing models using additional captions often have struggled to capture the rich semantics, including temporal changes, inherent in the video. In addition, incorrect information caused by generative models can lead to inaccurate retrieval. To address these issues, we propose a new framework, Narrating the Video (NarVid), which strategically leverages the comprehensive information available from frame-level captions, the narration. The proposed NarVid exploits narration in multiple ways: 1) feature enhancement through cross-modal interactions between narration and video, 2) query-aware adaptive filtering to suppress irrelevant or incorrect information, 3) dual-modal matching score by adding query-video similarity and query-narration similarity, and 4) hard-negative loss to learn discriminative features from multiple perspectives using the two similarities from different views. Experimental results demonstrate that NarVid achieves state-of-the-art performance on various benchmark datasets.