# Vision Guided Generative Pre-trained Language Models for Multimodal Abstractive Summarization

arXiv: https://arxiv.org/abs/2109.02401 · HTML: https://mlsanity.com/paper/2109.02401/

## Key facts

- Cited by 32 papers in the map (data through 14 Oct 2026).
- Builds on 49 of its 65 references that are in the map.
- First posted on arXiv 6 Sep 2021.

## Builds on (most cited first, 30 of 49)

- [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)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [Gaussian Error Linear Units (GELUs)](https://mlsanity.com/paper/1606.08415/) (2016)
- [Sequence to Sequence Learning with Neural Networks](https://mlsanity.com/paper/1409.3215/) (2014)
- [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)
- [CIDEr: Consensus-based Image Description Evaluation](https://mlsanity.com/paper/1411.5726/) (2014)
- [The Kinetics Human Action Video Dataset](https://mlsanity.com/paper/1705.06950/) (2017)
- [LXMERT: Learning Cross-Modality Encoder Representations from Transformers](https://mlsanity.com/paper/1908.07490/) (2019)
- [Microsoft COCO Captions: Data Collection and Evaluation Server](https://mlsanity.com/paper/1504.00325/) (2015)
- [Get To The Point: Summarization with Pointer-Generator Networks](https://mlsanity.com/paper/1704.04368/) (2017)
- [ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision](https://mlsanity.com/paper/2102.03334/) (2021)
- [PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization](https://mlsanity.com/paper/1912.08777/) (2019)
- [Effective Approaches to Attention-based Neural Machine Translation](https://mlsanity.com/paper/1508.04025/) (2015)
- [VL-BERT: Pre-training of Generic Visual-Linguistic Representations](https://mlsanity.com/paper/1908.08530/) (2019)
- [VideoBERT: A Joint Model for Video and Language Representation Learning](https://mlsanity.com/paper/1904.01766/) (2019)
- [Multimodal Transformer for Unaligned Multimodal Language Sequences](https://mlsanity.com/paper/1906.00295/) (2019)
- [From Recognition to Cognition: Visual Commonsense Reasoning](https://mlsanity.com/paper/1811.10830/) (2018)
- [Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?](https://mlsanity.com/paper/1711.09577/) (2017)
- [Unified Vision-Language Pre-Training for Image Captioning and VQA](https://mlsanity.com/paper/1909.11059/) (2019)
- [Long-term Recurrent Convolutional Networks for Visual Recognition and Description](https://mlsanity.com/paper/1411.4389/) (2014)
- [A Corpus for Reasoning About Natural Language Grounded in Photographs](https://mlsanity.com/paper/1811.00491/) (2018)

## Built on by (most cited first, 30 of 32)

- [A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivity](https://mlsanity.com/paper/2302.04023/) (2023)
- [Foundations and Trends in Multimodal Machine Learning: Principles, Challenges, and Open Questions](https://mlsanity.com/paper/2209.03430/) (2022)
- [An Empirical Survey on Long Document Summarization: Datasets, Models and Metrics](https://mlsanity.com/paper/2207.00939/) (2022)
- [Plausible May Not Be Faithful: Probing Object Hallucination in Vision-Language Pre-training](https://mlsanity.com/paper/2210.07688/) (2022)
- [Enabling Multimodal Generation on CLIP via Vision-Language Knowledge Distillation](https://mlsanity.com/paper/2203.06386/) (2022)
- [Multimodality Representation Learning: A Survey on Evolution, Pretraining and Its Applications](https://mlsanity.com/paper/2302.00389/) (2023)
- [Speech Summarization using Restricted Self-Attention](https://mlsanity.com/paper/2110.06263/) (2021)
- [Balance Act: Mitigating Hubness in Cross-Modal Retrieval with Query and Gallery Banks](https://mlsanity.com/paper/2310.11612/) (2023)
- [Summary-Oriented Vision Modeling for Multimodal Abstractive Summarization](https://mlsanity.com/paper/2212.07672/) (2022)
- [Meme-ingful Analysis: Enhanced Understanding of Cyberbullying in Memes Through Multimodal Explanations](https://mlsanity.com/paper/2401.09899/) (2024)
- [Hierarchical3D Adapters for Long Video-to-text Summarization](https://mlsanity.com/paper/2210.04829/) (2022)
- [MMSum: A Dataset for Multimodal Summarization and Thumbnail Generation of Videos](https://mlsanity.com/paper/2306.04216/) (2023)
- [Multimodal Dialog Systems with Dual Knowledge-enhanced Generative Pretrained Language Model](https://mlsanity.com/paper/2207.07934/) (2022)
- [Large Scale Generative Multimodal Attribute Extraction for E-commerce Attributes](https://mlsanity.com/paper/2306.00379/) (2023)
- [Exploiting Pseudo Image Captions for Multimodal Summarization](https://mlsanity.com/paper/2305.05496/) (2023)
- [MAMA: Meta-optimized Angular Margin Contrastive Framework for Video-Language Representation Learning](https://mlsanity.com/paper/2407.03788/) (2024)
- [Understanding Social Media Cross-Modality Discourse in Linguistic Space](https://mlsanity.com/paper/2302.13311/) (2023)
- [Interpreting Song Lyrics with an Audio-Informed Pre-trained Language Model](https://mlsanity.com/paper/2208.11671/) (2022)
- [Every picture tells a story: Image-grounded controllable stylistic story generation](https://mlsanity.com/paper/2209.01638/) (2022)
- [Denoising Bottleneck with Mutual Information Maximization for Video Multimodal Fusion](https://mlsanity.com/paper/2305.14652/) (2023)
- [Speech vs. Transcript: Does It Matter for Human Annotators in Speech Summarization?](https://mlsanity.com/paper/2408.07277/) (2024)
- [D2TV: Dual Knowledge Distillation and Target-oriented Vision Modeling for Many-to-Many Multimodal Summarization](https://mlsanity.com/paper/2305.12767/) (2023)
- [READ: Recurrent Adapter with Partial Video-Language Alignment for Parameter-Efficient Transfer Learning in Low-Resource Video-Language Modeling](https://mlsanity.com/paper/2312.06950/) (2023)
- [Grafting Pre-trained Models for Multimodal Headline Generation](https://mlsanity.com/paper/2211.07210/) (2022)
- [Learning Summary-Worthy Visual Representation for Abstractive Summarization in Video](https://mlsanity.com/paper/2305.04824/) (2023)
- [Learning Cluster Patterns for Abstractive Summarization](https://mlsanity.com/paper/2202.10967/) (2022)
- [Kaggle Competition: Cantonese Audio-Visual Speech Recognition for In-car Commands](https://mlsanity.com/paper/2207.02663/) (2022)
- [CFSum: A Coarse-to-Fine Contribution Network for Multimodal Summarization](https://mlsanity.com/paper/2307.02716/) (2023)
- [MMAPS: End-to-End Multi-Grained Multi-Modal Attribute-Aware Product Summarization](https://mlsanity.com/paper/2308.11351/) (2023)
- [Semantic-Enhanced Cross-Modal Place Recognition for Robust Robot Localization](https://mlsanity.com/paper/2509.13474/) (2025)

## Abstract (arXiv)

Multimodal abstractive summarization (MAS) models that summarize videos (vision modality) and their corresponding transcripts (text modality) are able to extract the essential information from massive multimodal data on the Internet. Recently, large-scale generative pre-trained language models (GPLMs) have been shown to be effective in text generation tasks. However, existing MAS models cannot leverage GPLMs' powerful generation ability. To fill this research gap, we aim to study two research questions: 1) how to inject visual information into GPLMs without hurting their generation ability; and 2) where is the optimal place in GPLMs to inject the visual information? In this paper, we present a simple yet effective method to construct vision guided (VG) GPLMs for the MAS task using attention-based add-on layers to incorporate visual information while maintaining their original text generation ability. Results show that our best model significantly surpasses the prior state-of-the-art model by 5.7 ROUGE-1, 5.3 ROUGE-2, and 5.1 ROUGE-L scores on the How2 dataset, and our visual guidance method contributes 83.6% of the overall improvement. Furthermore, we conduct thorough ablation studies to analyze the effectiveness of various modality fusion methods and fusion locations.