# DiffusionRet: Generative Text-Video Retrieval with Diffusion Model

arXiv: https://arxiv.org/abs/2303.09867 · HTML: https://mlsanity.com/paper/2303.09867/

## Key facts

- Cited by 52 papers in the map (data through 14 Oct 2026).
- Placed in Video generation, one of 14 directions in Diffusion models.
- Builds on 59 of its 95 references that are in the map.
- First posted on arXiv 17 Mar 2023.

## Placed in

- Diffusion models / [Video generation](https://mlsanity.com/diffusion/video-generation/)

## Builds on (most cited first, 30 of 59)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [Large Scale GAN Training for High Fidelity Natural Image Synthesis](https://mlsanity.com/paper/1809.11096/) (2018)
- [WaveNet: A Generative Model for Raw Audio](https://mlsanity.com/paper/1609.03499/) (2016)
- [Structured Denoising Diffusion Models in Discrete State-Spaces](https://mlsanity.com/paper/2107.03006/) (2021)
- [Generating Diverse High-Fidelity Images with VQ-VAE-2](https://mlsanity.com/paper/1906.00446/) (2019)
- [Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval](https://mlsanity.com/paper/2104.00650/) (2021)
- [Human Motion Diffusion Model](https://mlsanity.com/paper/2209.14916/) (2022)
- [Diffusion-LM Improves Controllable Text Generation](https://mlsanity.com/paper/2205.14217/) (2022)
- [HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips](https://mlsanity.com/paper/1906.03327/) (2019)
- [Dense-Captioning Events in Videos](https://mlsanity.com/paper/1705.00754/) (2017)
- [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)
- [Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Model](https://mlsanity.com/paper/2212.00490/) (2022)
- [Jukebox: A Generative Model for Music](https://mlsanity.com/paper/2005.00341/) (2020)
- [Label-Efficient Semantic Segmentation with Diffusion Models](https://mlsanity.com/paper/2112.03126/) (2021)

## Built on by (most cited first, 30 of 52)

- [Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding](https://mlsanity.com/paper/2311.08046/) (2023)
- [A Survey on Video Diffusion Models](https://mlsanity.com/paper/2310.10647/) (2023)
- [Video Understanding with Large Language Models: A Survey](https://mlsanity.com/paper/2312.17432/) (2023)
- [MomentDiff: Generative Video Moment Retrieval from Random to Real](https://mlsanity.com/paper/2307.02869/) (2023)
- [Act As You Wish: Fine-Grained Control of Motion Diffusion Model with Hierarchical Semantic Graphs](https://mlsanity.com/paper/2311.01015/) (2023)
- [MoH: Multi-Head Attention as Mixture-of-Head Attention](https://mlsanity.com/paper/2410.11842/) (2024)
- [TempMe: Video Temporal Token Merging for Efficient Text-Video Retrieval](https://mlsanity.com/paper/2409.01156/) (2024)
- [Text Is MASS: Modeling as Stochastic Embedding for Text-Video Retrieval](https://mlsanity.com/paper/2403.17998/) (2024)
- [Text-Video Retrieval with Disentangled Conceptualization and Set-to-Set Alignment](https://mlsanity.com/paper/2305.12218/) (2023)
- [DGL: Dynamic Global-Local Prompt Tuning for Text-Video Retrieval](https://mlsanity.com/paper/2401.10588/) (2024)
- [Delving Deeper: Hierarchical Visual Perception for Robust Video-Text Retrieval](https://mlsanity.com/paper/2601.12768/) (2026)
- [FreestyleRet: Retrieving Images from Style-Diversified Queries](https://mlsanity.com/paper/2312.02428/) (2023)
- [AE-NeRF: Augmenting Event-Based Neural Radiance Fields for Non-ideal Conditions and Larger Scene](https://mlsanity.com/paper/2501.02807/) (2025)
- [Continuous-Multiple Image Outpainting in One-Step via Positional Query and A Diffusion-based Approach](https://mlsanity.com/paper/2401.15652/) (2024)
- [ReVisionLLM: Recursive Vision-Language Model for Temporal Grounding in Hour-Long Videos](https://mlsanity.com/paper/2411.14901/) (2024)
- [GMMFormer v2: An Uncertainty-aware Framework for Partially Relevant Video Retrieval](https://mlsanity.com/paper/2405.13824/) (2024)
- [Continual Text-to-Video Retrieval with Frame Fusion and Task-Aware Routing](https://mlsanity.com/paper/2503.10111/) (2025)
- [LDMol: A Text-to-Molecule Diffusion Model with Structurally Informative Latent Space Surpasses AR Models](https://mlsanity.com/paper/2405.17829/) (2024)
- [Retrieval is Accurate Generation](https://mlsanity.com/paper/2402.17532/) (2024)
- [Local Action-Guided Motion Diffusion Model for Text-to-Motion Generation](https://mlsanity.com/paper/2407.10528/) (2024)
- [Prototypes are Balanced Units for Efficient and Effective Partially Relevant Video Retrieval](https://mlsanity.com/paper/2504.13035/) (2025)
- [MUSE: Mamba is Efficient Multi-scale Learner for Text-video Retrieval](https://mlsanity.com/paper/2408.10575/) (2024)
- [TG-VQA: Ternary Game of Video Question Answering](https://mlsanity.com/paper/2305.10049/) (2023)
- [NeighborRetr: Balancing Hub Centrality in Cross-Modal Retrieval](https://mlsanity.com/paper/2503.10526/) (2025)
- [VidLA: Video-Language Alignment at Scale](https://mlsanity.com/paper/2403.14870/) (2024)
- [Unveiling Discrete Clues: Superior Healthcare Predictions for Rare Diseases](https://mlsanity.com/paper/2501.16373/) (2025)
- [Are Synthetic Videos Useful? A Benchmark for Retrieval-Centric Evaluation of Synthetic Videos](https://mlsanity.com/paper/2507.02316/) (2025)
- [Towards Unified Vision-Language Models with Incomplete Multi-Modal Inputs](https://mlsanity.com/paper/2605.27894/) (2026)
- [3DifFusionDet: Diffusion Model for 3D Object Detection with Robust LiDAR-Camera Fusion](https://mlsanity.com/paper/2311.03742/) (2023)
- [Towards Retrieval Augmented Generation over Large Video Libraries](https://mlsanity.com/paper/2406.14938/) (2024)

## Abstract (arXiv)

Existing text-video retrieval solutions are, in essence, discriminant models focused on maximizing the conditional likelihood, i.e., p(candidates|query). While straightforward, this de facto paradigm overlooks the underlying data distribution p(query), which makes it challenging to identify out-of-distribution data. To address this limitation, we creatively tackle this task from a generative viewpoint and model the correlation between the text and the video as their joint probability p(candidates,query). This is accomplished through a diffusion-based text-video retrieval framework (DiffusionRet), which models the retrieval task as a process of gradually generating joint distribution from noise. During training, DiffusionRet is optimized from both the generation and discrimination perspectives, with the generator being optimized by generation loss and the feature extractor trained with contrastive loss. In this way, DiffusionRet cleverly leverages the strengths of both generative and discriminative methods. Extensive experiments on five commonly used text-video retrieval benchmarks, including MSRVTT, LSMDC, MSVD, ActivityNet Captions, and DiDeMo, with superior performances, justify the efficacy of our method. More encouragingly, without any modification, DiffusionRet even performs well in out-domain retrieval settings. We believe this work brings fundamental insights into the related fields. Code is available at https://github.com/jpthu17/DiffusionRet.