# Modality-Balanced Embedding for Video Retrieval

arXiv: https://arxiv.org/abs/2204.08182 · HTML: https://mlsanity.com/paper/2204.08182/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 28 references that are in the map.
- First posted on arXiv 18 Apr 2022.

## Builds on (most cited first, 23 of 23)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [REALM: Retrieval-Augmented Language Model Pre-Training](https://mlsanity.com/paper/2002.08909/) (2020)
- [ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT](https://mlsanity.com/paper/2004.12832/) (2020)
- [VideoBERT: A Joint Model for Video and Language Representation Learning](https://mlsanity.com/paper/1904.01766/) (2019)
- [VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding](https://mlsanity.com/paper/2109.14084/) (2021)
- [Less is More: ClipBERT for Video-and-Language Learning via Sparse Sampling](https://mlsanity.com/paper/2102.06183/) (2021)
- [Multi-modal Transformer for Video Retrieval](https://mlsanity.com/paper/2007.10639/) (2020)
- [Pixel-BERT: Aligning Image Pixels with Text by Deep Multi-Modal Transformers](https://mlsanity.com/paper/2004.00849/) (2020)
- [Embedding-based Retrieval in Facebook Search](https://mlsanity.com/paper/2006.11632/) (2020)
- [Optimizing Dense Retrieval Model Training with Hard Negatives](https://mlsanity.com/paper/2104.08051/) (2021)
- [HiT: Hierarchical Transformer with Momentum Contrast for Video-Text Retrieval](https://mlsanity.com/paper/2103.15049/) (2021)
- [Embedding-based Product Retrieval in Taobao Search](https://mlsanity.com/paper/2106.09297/) (2021)
- [Interpolated Adversarial Training: Achieving Robust Neural Networks without Sacrificing Too Much Accuracy](https://mlsanity.com/paper/1906.06784/) (2019)
- [Zero-Resource Translation with Multi-Lingual Neural Machine Translation](https://mlsanity.com/paper/1606.04164/) (2016)
- [RepBERT: Contextualized Text Embeddings for First-Stage Retrieval](https://mlsanity.com/paper/2006.15498/) (2020)
- [Towards Personalized and Semantic Retrieval: An End-to-End Solution for E-commerce Search via Embedding Learning](https://mlsanity.com/paper/2006.02282/) (2020)
- [Pre-trained Language Model for Web-scale Retrieval in Baidu Search](https://mlsanity.com/paper/2106.03373/) (2021)
- [Modality-Balanced Models for Visual Dialogue](https://mlsanity.com/paper/2001.06354/) (2020)

## Built on by (most cited first, 6 of 6)

- [FULLER: Unified Multi-modality Multi-task 3D Perception via Multi-level Gradient Calibration](https://mlsanity.com/paper/2307.16617/) (2023)
- [Improving Video Corpus Moment Retrieval with Partial Relevance Enhancement](https://mlsanity.com/paper/2402.13576/) (2024)
- [I can listen but cannot read: An evaluation of two-tower multimodal systems for instrument recognition](https://mlsanity.com/paper/2407.18058/) (2024)
- [pEBR: A Probabilistic Approach to Embedding Based Retrieval](https://mlsanity.com/paper/2410.19349/) (2024)
- [GREAT: Guiding Query Generation with a Trie for Recommending Related Search about Video at Kuaishou](https://mlsanity.com/paper/2507.15267/) (2025)
- [Towards Debiasing Frame Length Bias in Text-Video Retrieval via Causal Intervention](https://mlsanity.com/paper/2309.09311/) (2023)

## Abstract (arXiv)

Video search has become the main routine for users to discover videos relevant to a text query on large short-video sharing platforms. During training a query-video bi-encoder model using online search logs, we identify a modality bias phenomenon that the video encoder almost entirely relies on text matching, neglecting other modalities of the videos such as vision, audio. This modality imbalanceresults from a) modality gap: the relevance between a query and a video text is much easier to learn as the query is also a piece of text, with the same modality as the video text; b) data bias: most training samples can be solved solely by text matching. Here we share our practices to improve the first retrieval stage including our solution for the modality imbalance issue. We propose MBVR (short for Modality Balanced Video Retrieval) with two key components: manually generated modality-shuffled (MS) samples and a dynamic margin (DM) based on visual relevance. They can encourage the video encoder to pay balanced attentions to each modality. Through extensive experiments on a real world dataset, we show empirically that our method is both effective and efficient in solving modality bias problem. We have also deployed our MBVR in a large video platform and observed statistically significant boost over a highly optimized baseline in an A/B test and manual GSB evaluations.