# MVPTR: Multi-Level Semantic Alignment for Vision-Language Pre-Training via Multi-Stage Learning

arXiv: https://arxiv.org/abs/2201.12596 · HTML: https://mlsanity.com/paper/2201.12596/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Placed in VLM benchmarks and visual reasoning, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 32 of its 45 references that are in the map.
- First posted on arXiv 29 Jan 2022.

## Placed in

- Multimodal LLMs / vision-language models / [VLM benchmarks and visual reasoning](https://mlsanity.com/mllm/vlm-benchmarks-and-visual-reasoning/)

## Builds on (most cited first, 30 of 32)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering](https://mlsanity.com/paper/1612.00837/) (2016)
- [VQA: Visual Question Answering](https://mlsanity.com/paper/1505.00468/) (2015)
- [ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks](https://mlsanity.com/paper/1908.02265/) (2019)
- [Align before Fuse: Vision and Language Representation Learning with Momentum Distillation](https://mlsanity.com/paper/2107.07651/) (2021)
- [LXMERT: Learning Cross-Modality Encoder Representations from Transformers](https://mlsanity.com/paper/1908.07490/) (2019)
- [Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models](https://mlsanity.com/paper/1505.04870/) (2015)
- [Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering](https://mlsanity.com/paper/1707.07998/) (2017)
- [VisualBERT: A Simple and Performant Baseline for Vision and Language](https://mlsanity.com/paper/1908.03557/) (2019)
- [ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision](https://mlsanity.com/paper/2102.03334/) (2021)
- [Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks](https://mlsanity.com/paper/2004.06165/) (2020)
- [Modeling Context in Referring Expressions](https://mlsanity.com/paper/1608.00272/) (2016)
- [Deep Visual-Semantic Alignments for Generating Image Descriptions](https://mlsanity.com/paper/1412.2306/) (2014)
- [VL-BERT: Pre-training of Generic Visual-Linguistic Representations](https://mlsanity.com/paper/1908.08530/) (2019)
- [SPICE: Semantic Propositional Image Caption Evaluation](https://mlsanity.com/paper/1607.08822/) (2016)
- [The Open Images Dataset V4: Unified image classification, object detection, and visual relationship detection at scale](https://mlsanity.com/paper/1811.00982/) (2018)
- [Unified Vision-Language Pre-Training for Image Captioning and VQA](https://mlsanity.com/paper/1909.11059/) (2019)
- [Unicoder-VL: A Universal Encoder for Vision and Language by Cross-modal Pre-training](https://mlsanity.com/paper/1908.06066/) (2019)
- [Large-Scale Adversarial Training for Vision-and-Language Representation Learning](https://mlsanity.com/paper/2006.06195/) (2020)
- [ERNIE: Enhanced Representation through Knowledge Integration](https://mlsanity.com/paper/1904.09223/) (2019)
- [Visual Entailment: A Novel Task for Fine-Grained Image Understanding](https://mlsanity.com/paper/1901.06706/) (2019)
- [UNIMO: Towards Unified-Modal Understanding and Generation via Cross-Modal Contrastive Learning](https://mlsanity.com/paper/2012.15409/) (2020)
- [ERNIE-ViL: Knowledge Enhanced Vision-Language Representations Through Scene Graph](https://mlsanity.com/paper/2006.16934/) (2020)
- [End-to-end people detection in crowded scenes](https://mlsanity.com/paper/1506.04878/) (2015)
- [Grounding of Textual Phrases in Images by Reconstruction](https://mlsanity.com/paper/1511.03745/) (2015)
- [E2E-VLP: End-to-End Vision-Language Pre-training Enhanced by Visual Learning](https://mlsanity.com/paper/2106.01804/) (2021)

## Built on by (most cited first, 13 of 13)

- [EmbSpatial-Bench: Benchmarking Spatial Understanding for Embodied Tasks with Large Vision-Language Models](https://mlsanity.com/paper/2406.05756/) (2024)
- [Arondight: Red Teaming Large Vision Language Models with Auto-generated Multi-modal Jailbreak Prompts](https://mlsanity.com/paper/2407.15050/) (2024)
- [VaQuitA: Enhancing Alignment in LLM-Assisted Video Understanding](https://mlsanity.com/paper/2312.02310/) (2023)
- [A Multi-Modal Context Reasoning Approach for Conditional Inference on Joint Textual and Visual Clues](https://mlsanity.com/paper/2305.04530/) (2023)
- [SoMeLVLM: A Large Vision Language Model for Social Media Processing](https://mlsanity.com/paper/2402.13022/) (2024)
- [DELAN: Dual-Level Alignment for Vision-and-Language Navigation by Cross-Modal Contrastive Learning](https://mlsanity.com/paper/2404.01994/) (2024)
- [Weakly-Supervised Learning of Visual Relations in Multimodal Pretraining](https://mlsanity.com/paper/2305.14281/) (2023)
- [How to Train your Text-to-Image Model: Evaluating Design Choices for Synthetic Training Captions](https://mlsanity.com/paper/2506.16679/) (2025)
- [DALR: Dual-level Alignment Learning for Multimodal Sentence Representation Learning](https://mlsanity.com/paper/2506.21096/) (2025)
- [Language-driven Fine-grained Retrieval](https://mlsanity.com/paper/2512.06255/) (2025)
- [VITR: Augmenting Vision Transformers with Relation-Focused Learning for Cross-Modal Information Retrieval](https://mlsanity.com/paper/2302.06350/) (2023)
- [ConcEPT: Concept-Enhanced Pre-Training for Language Models](https://mlsanity.com/paper/2401.05669/) (2024)
- [FSMR: A Feature Swapping Multi-modal Reasoning Approach with Joint Textual and Visual Clues](https://mlsanity.com/paper/2403.20026/) (2024)

## Abstract (arXiv)

Previous vision-language pre-training models mainly construct multi-modal inputs with tokens and objects (pixels) followed by performing cross-modality interaction between them. We argue that the input of only tokens and object features limits high-level semantic alignment like phrase-to-region grounding. Meanwhile, multi-level alignments are inherently consistent and able to facilitate the representation learning synergistically. Therefore, in this paper, we propose to learn Multi-level semantic alignment for Vision-language Pre-TRaining (MVPTR). In MVPTR, we follow the nested structure of both modalities to introduce concepts as high-level semantics. To ease the learning from multi-modal multi-level inputs, our framework is split into two stages, the first stage focuses on intra-modality multi-level representation learning, the second enforces interactions across modalities via both coarse-grained and fine-grained semantic alignment tasks. In addition to the commonly used image-text matching and masked language model tasks, we introduce a masked concept recovering task in the first stage to enhance the concept representation learning, and two more tasks in the second stage to explicitly encourage multi-level alignments across modalities. Our code is available at https://github.com/Junction4Nako/mvp_pytorch.