# MomentDiff: Generative Video Moment Retrieval from Random to Real

arXiv: https://arxiv.org/abs/2307.02869 · HTML: https://mlsanity.com/paper/2307.02869/

## Key facts

- Cited by 58 papers in the map (data through 14 Oct 2026).
- Builds on 65 of its 87 references that are in the map.
- First posted on arXiv 6 Jul 2023.

## Builds on (most cited first, 30 of 65)

- [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)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [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)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [Video Diffusion Models](https://mlsanity.com/paper/2204.03458/) (2022)
- [SlowFast Networks for Video Recognition](https://mlsanity.com/paper/1812.03982/) (2018)
- [Structured Denoising Diffusion Models in Discrete State-Spaces](https://mlsanity.com/paper/2107.03006/) (2021)
- [Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression](https://mlsanity.com/paper/1902.09630/) (2019)
- [Diffusion-LM Improves Controllable Text Generation](https://mlsanity.com/paper/2205.14217/) (2022)
- [Dense-Captioning Events in Videos](https://mlsanity.com/paper/1705.00754/) (2017)
- [Vector Quantized Diffusion Model for Text-to-Image Synthesis](https://mlsanity.com/paper/2111.14822/) (2021)
- [Localizing Moments in Video with Natural Language](https://mlsanity.com/paper/1708.01641/) (2017)
- [TALL: Temporal Activity Localization via Language Query](https://mlsanity.com/paper/1705.02101/) (2017)
- [PANNs: Large-Scale Pretrained Audio Neural Networks for Audio Pattern Recognition](https://mlsanity.com/paper/1912.10211/) (2019)
- [End-to-End Learning of Visual Representations from Uncurated Instructional Videos](https://mlsanity.com/paper/1912.06430/) (2019)
- [VideoComposer: Compositional Video Synthesis with Motion Controllability](https://mlsanity.com/paper/2306.02018/) (2023)
- [Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speech](https://mlsanity.com/paper/2105.06337/) (2021)
- [Analog Bits: Generating Discrete Data using Diffusion Models with Self-Conditioning](https://mlsanity.com/paper/2208.04202/) (2022)
- [Uni-ControlNet: All-in-One Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2305.16322/) (2023)
- [DiffusionDet: Diffusion Model for Object Detection](https://mlsanity.com/paper/2211.09788/) (2022)
- [Learning 2D Temporal Adjacent Networks for Moment Localization with Natural Language](https://mlsanity.com/paper/1912.03590/) (2019)
- [SegDiff: Image Segmentation with Diffusion Probabilistic Models](https://mlsanity.com/paper/2112.00390/) (2021)
- [Span-based Localizing Network for Natural Language Video Localization](https://mlsanity.com/paper/2004.13931/) (2020)

## Built on by (most cited first, 30 of 58)

- [A Survey on Video Diffusion Models](https://mlsanity.com/paper/2310.10647/) (2023)
- [Act As You Wish: Fine-Grained Control of Motion Diffusion Model with Hierarchical Semantic Graphs](https://mlsanity.com/paper/2311.01015/) (2023)
- [VideoMind: A Chain-of-LoRA Agent for Temporal-Grounded Video Reasoning](https://mlsanity.com/paper/2503.13444/) (2025)
- [Towards Surveillance Video-and-Language Understanding: New Dataset, Baselines, and Challenges](https://mlsanity.com/paper/2309.13925/) (2023)
- [Video-Language Understanding: A Survey from Model Architecture, Model Training, and Data Perspectives](https://mlsanity.com/paper/2406.05615/) (2024)
- [R2-Tuning: Efficient Image-to-Video Transfer Learning for Video Temporal Grounding](https://mlsanity.com/paper/2404.00801/) (2024)
- [BAM-DETR: Boundary-Aligned Moment Detection Transformer for Temporal Sentence Grounding in Videos](https://mlsanity.com/paper/2312.00083/) (2023)
- [SpaceVLLM: Endowing Multimodal Large Language Model with Spatio-Temporal Video Grounding Capability](https://mlsanity.com/paper/2503.13983/) (2025)
- [Towards Balanced Alignment: Modal-Enhanced Semantic Modeling for Video Moment Retrieval](https://mlsanity.com/paper/2312.12155/) (2023)
- [FlashVTG: Feature Layering and Adaptive Score Handling Network for Video Temporal Grounding](https://mlsanity.com/paper/2412.13441/) (2024)
- [GMMFormer: Gaussian-Mixture-Model Based Transformer for Efficient Partially Relevant Video Retrieval](https://mlsanity.com/paper/2310.05195/) (2023)
- [Hybrid-Level Instruction Injection for Video Token Compression in Multi-modal Large Language Models](https://mlsanity.com/paper/2503.16036/) (2025)
- [Choose What You Need: Disentangled Representation Learning for Scene Text Recognition, Removal and Editing](https://mlsanity.com/paper/2405.04377/) (2024)
- [Towards Efficient Partially Relevant Video Retrieval with Active Moment Discovering](https://mlsanity.com/paper/2504.10920/) (2025)
- [SALOVA: Segment-Augmented Long Video Assistant for Targeted Retrieval and Routing in Long-Form Video Analysis](https://mlsanity.com/paper/2411.16173/) (2024)
- [GMMFormer v2: An Uncertainty-aware Framework for Partially Relevant Video Retrieval](https://mlsanity.com/paper/2405.13824/) (2024)
- [Enrich and Detect: Video Temporal Grounding with Multimodal LLMs](https://mlsanity.com/paper/2510.17023/) (2025)
- [Beyond Uncertainty: Evidential Deep Learning for Robust Video Temporal Grounding](https://mlsanity.com/paper/2408.16272/) (2024)
- [LD-DETR: Loop Decoder DEtection TRansformer for Video Moment Retrieval and Highlight Detection](https://mlsanity.com/paper/2501.10787/) (2025)
- [TempR1: Improving Temporal Understanding of MLLMs via Temporal-Aware Multi-Task Reinforcement Learning](https://mlsanity.com/paper/2512.03963/) (2025)
- [Let Me Finish My Sentence: Video Temporal Grounding with Holistic Text Understanding](https://mlsanity.com/paper/2410.13598/) (2024)
- [Diversifying Query: Region-Guided Transformer for Temporal Sentence Grounding](https://mlsanity.com/paper/2406.00143/) (2024)
- [Not All Inputs Are Valid: Towards Open-Set Video Moment Retrieval Using Language](https://mlsanity.com/paper/2605.29812/) (2026)
- [Bridging Information Asymmetry in Text-video Retrieval: A Data-centric Approach](https://mlsanity.com/paper/2408.07249/) (2024)
- [Multi-modal Fusion and Query Refinement Network for Video Moment Retrieval and Highlight Detection](https://mlsanity.com/paper/2501.10692/) (2025)
- [Hierarchical Event Memory for Accurate and Low-latency Online Video Temporal Grounding](https://mlsanity.com/paper/2508.04546/) (2025)
- [GranAlign: Granularity-Aware Alignment Framework for Zero-Shot Video Moment Retrieval](https://mlsanity.com/paper/2601.00584/) (2026)
- [Towards Unified Vision-Language Models with Incomplete Multi-Modal Inputs](https://mlsanity.com/paper/2605.27894/) (2026)
- [EtC: Temporal Boundary Expand then Clarify for Weakly Supervised Video Grounding with Multimodal Large Language Model](https://mlsanity.com/paper/2312.02483/) (2023)
- [Commonsense for Zero-Shot Natural Language Video Localization](https://mlsanity.com/paper/2312.17429/) (2023)

## Abstract (arXiv)

Video moment retrieval pursues an efficient and generalized solution to identify the specific temporal segments within an untrimmed video that correspond to a given language description. To achieve this goal, we provide a generative diffusion-based framework called MomentDiff, which simulates a typical human retrieval process from random browsing to gradual localization. Specifically, we first diffuse the real span to random noise, and learn to denoise the random noise to the original span with the guidance of similarity between text and video. This allows the model to learn a mapping from arbitrary random locations to real moments, enabling the ability to locate segments from random initialization. Once trained, MomentDiff could sample random temporal segments as initial guesses and iteratively refine them to generate an accurate temporal boundary. Different from discriminative works (e.g., based on learnable proposals or queries), MomentDiff with random initialized spans could resist the temporal location biases from datasets. To evaluate the influence of the temporal location biases, we propose two anti-bias datasets with location distribution shifts, named Charades-STA-Len and Charades-STA-Mom. The experimental results demonstrate that our efficient framework consistently outperforms state-of-the-art methods on three public benchmarks, and exhibits better generalization and robustness on the proposed anti-bias datasets. The code, model, and anti-bias evaluation datasets are available at https://github.com/IMCCretrieval/MomentDiff.