# Noise Estimation Using Density Estimation for Self-Supervised Multimodal Learning

arXiv: https://arxiv.org/abs/2003.03186 · HTML: https://mlsanity.com/paper/2003.03186/

## Key facts

- Cited by 74 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Mar 2020.

## Built on by (most cited first, 30 of 74)

- [Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval](https://mlsanity.com/paper/2104.00650/) (2021)
- [CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval](https://mlsanity.com/paper/2104.08860/) (2021)
- [MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge](https://mlsanity.com/paper/2206.08853/) (2022)
- [MERLOT: Multimodal Neural Script Knowledge Models](https://mlsanity.com/paper/2106.02636/) (2021)
- [X-CLIP: End-to-End Multi-grained Contrastive Learning for Video-Text Retrieval](https://mlsanity.com/paper/2207.07285/) (2022)
- [Zero-Shot Video Question Answering via Frozen Bidirectional Language Models](https://mlsanity.com/paper/2206.08155/) (2022)
- [CLIP2Video: Mastering Video-Text Retrieval via Image CLIP](https://mlsanity.com/paper/2106.11097/) (2021)
- [All in One: Exploring Unified Video-Language Pre-training](https://mlsanity.com/paper/2203.07303/) (2022)
- [Align and Prompt: Video-and-Language Pre-training with Entity Prompts](https://mlsanity.com/paper/2112.09583/) (2021)
- [X-Pool: Cross-Modal Language-Video Attention for Text-Video Retrieval](https://mlsanity.com/paper/2203.15086/) (2022)
- [End-to-end Generative Pretraining for Multimodal Video Captioning](https://mlsanity.com/paper/2201.08264/) (2022)
- [HiT: Hierarchical Transformer with Momentum Contrast for Video-Text Retrieval](https://mlsanity.com/paper/2103.15049/) (2021)
- [Self-Supervised Learning for Videos: A Survey](https://mlsanity.com/paper/2207.00419/) (2022)
- [Provable Dynamic Fusion for Low-Quality Multimodal Data](https://mlsanity.com/paper/2306.02050/) (2023)
- [Learning Audio-Video Modalities from Image Captions](https://mlsanity.com/paper/2204.00679/) (2022)
- [Everything at Once -- Multi-modal Fusion Transformer for Video Retrieval](https://mlsanity.com/paper/2112.04446/) (2021)
- [Bridging Video-text Retrieval with Multiple Choice Questions](https://mlsanity.com/paper/2201.04850/) (2022)
- [Video Graph Transformer for Video Question Answering](https://mlsanity.com/paper/2207.05342/) (2022)
- [Multimodal Clustering Networks for Self-supervised Learning from Unlabeled Videos](https://mlsanity.com/paper/2104.12671/) (2021)
- [Object-aware Video-language Pre-training for Retrieval](https://mlsanity.com/paper/2112.00656/) (2021)
- [LocVTP: Video-Text Pre-training for Temporal Localization](https://mlsanity.com/paper/2207.10362/) (2022)
- [Multilingual Multimodal Pre-training for Zero-Shot Cross-Lingual Transfer of Vision-Language Models](https://mlsanity.com/paper/2103.08849/) (2021)
- [ECLIPSE: Efficient Long-range Video Retrieval using Sight and Sound](https://mlsanity.com/paper/2204.02874/) (2022)
- [HowToCaption: Prompting LLMs to Transform Video Annotations at Scale](https://mlsanity.com/paper/2310.04900/) (2023)
- [COTS: Collaborative Two-Stream Vision-Language Pre-Training Model for Cross-Modal Retrieval](https://mlsanity.com/paper/2204.07441/) (2022)
- [Contrastive Video Question Answering via Video Graph Transformer](https://mlsanity.com/paper/2302.13668/) (2023)
- [Learning to Answer Visual Questions from Web Videos](https://mlsanity.com/paper/2205.05019/) (2022)
- [Joint-Modal Label Denoising for Weakly-Supervised Audio-Visual Video Parsing](https://mlsanity.com/paper/2204.11573/) (2022)
- [MILES: Visual BERT Pre-training with Injected Language Semantics for Video-text Retrieval](https://mlsanity.com/paper/2204.12408/) (2022)
- [Beyond Just Vision: A Review on Self-Supervised Representation Learning on Multimodal and Temporal Data](https://mlsanity.com/paper/2206.02353/) (2022)

## Abstract (arXiv)

One of the key factors of enabling machine learning models to comprehend and solve real-world tasks is to leverage multimodal data. Unfortunately, annotation of multimodal data is challenging and expensive. Recently, self-supervised multimodal methods that combine vision and language were proposed to learn multimodal representations without annotation. However, these methods often choose to ignore the presence of high levels of noise and thus yield sub-optimal results. In this work, we show that the problem of noise estimation for multimodal data can be reduced to a multimodal density estimation task. Using multimodal density estimation, we propose a noise estimation building block for multimodal representation learning that is based strictly on the inherent correlation between different modalities. We demonstrate how our noise estimation can be broadly integrated and achieves comparable results to state-of-the-art performance on five different benchmark datasets for two challenging multimodal tasks: Video Question Answering and Text-To-Video Retrieval. Furthermore, we provide a theoretical probabilistic error bound substantiating our empirical results and analyze failure cases. Code: https://github.com/elad-amrani/ssml.