# Beyond Image-Text Matching: Verb Understanding in Multimodal Transformers Using Guided Masking

arXiv: https://arxiv.org/abs/2401.16575 · HTML: https://mlsanity.com/paper/2401.16575/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 36 references that are in the map.
- First posted on arXiv 29 Jan 2024.

## Builds on (most cited first, 26 of 26)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [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)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [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)
- [VisualBERT: A Simple and Performant Baseline for Vision and Language](https://mlsanity.com/paper/1908.03557/) (2019)
- [FLAVA: A Foundational Language And Vision Alignment Model](https://mlsanity.com/paper/2112.04482/) (2021)
- [Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality](https://mlsanity.com/paper/2204.03162/) (2022)
- [Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformers](https://mlsanity.com/paper/2103.15679/) (2021)
- [Multi-Grained Vision Language Pre-Training: Aligning Texts with Visual Concepts](https://mlsanity.com/paper/2111.08276/) (2021)
- [UNITER: UNiversal Image-TExt Representation Learning](https://mlsanity.com/paper/1909.11740/) (2019)
- [Visual Semantic Role Labeling](https://mlsanity.com/paper/1505.04474/) (2015)
- [OmniVL:One Foundation Model for Image-Language and Video-Language Tasks](https://mlsanity.com/paper/2209.07526/) (2022)
- [Probing Image-Language Transformers for Verb Understanding](https://mlsanity.com/paper/2106.09141/) (2021)
- [What You See is What You Read? Improving Text-Image Alignment Evaluation](https://mlsanity.com/paper/2305.10400/) (2023)
- [FOIL it! Find One mismatch between Image and Language caption](https://mlsanity.com/paper/1705.01359/) (2017)
- [Vision-and-Language or Vision-for-Language? On Cross-Modal Influence in Multimodal Transformers](https://mlsanity.com/paper/2109.04448/) (2021)
- [Multimodal Pretraining Unmasked: A Meta-Analysis and a Unified Framework of Vision-and-Language BERTs](https://mlsanity.com/paper/2011.15124/) (2020)
- [Trankit: A Light-Weight Transformer-based Toolkit for Multilingual Natural Language Processing](https://mlsanity.com/paper/2101.03289/) (2021)
- [VL-InterpreT: An Interactive Visualization Tool for Interpreting Vision-Language Transformers](https://mlsanity.com/paper/2203.17247/) (2022)
- [Seeing past words: Testing the cross-modal capabilities of pretrained V&L models on counting tasks](https://mlsanity.com/paper/2012.12352/) (2020)
- [Improving Visual Grounding by Encouraging Consistent Gradient-based Explanations](https://mlsanity.com/paper/2206.15462/) (2022)

## Built on by (most cited first, 1 of 1)

- [CV-Probes: Studying the interplay of lexical and world knowledge in visually grounded verb understanding](https://mlsanity.com/paper/2409.01389/) (2024)

## Abstract (arXiv)

The dominant probing approaches rely on the zero-shot performance of image-text matching tasks to gain a finer-grained understanding of the representations learned by recent multimodal image-language transformer models. The evaluation is carried out on carefully curated datasets focusing on counting, relations, attributes, and others. This work introduces an alternative probing strategy called guided masking. The proposed approach ablates different modalities using masking and assesses the model's ability to predict the masked word with high accuracy. We focus on studying multimodal models that consider regions of interest (ROI) features obtained by object detectors as input tokens. We probe the understanding of verbs using guided masking on ViLBERT, LXMERT, UNITER, and VisualBERT and show that these models can predict the correct verb with high accuracy. This contrasts with previous conclusions drawn from image-text matching probing techniques that frequently fail in situations requiring verb understanding. The code for all experiments will be publicly available https://github.com/ivana-13/guided_masking.