# Do Vision-Language Transformers Exhibit Visual Commonsense? An Empirical Study of VCR

arXiv: https://arxiv.org/abs/2405.16934 · HTML: https://mlsanity.com/paper/2405.16934/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 25 of its 50 references that are in the map.
- First posted on arXiv 27 May 2024.

## Placed in

- LLM reasoning / [Multimodal reasoning](https://mlsanity.com/lr/multimodal-reasoning/)

## Builds on (most cited first, 25 of 25)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [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)
- [Show, Attend and Tell: Neural Image Caption Generation with Visual Attention](https://mlsanity.com/paper/1502.03044/) (2015)
- [Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering](https://mlsanity.com/paper/1707.07998/) (2017)
- [ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision](https://mlsanity.com/paper/2102.03334/) (2021)
- [VL-BERT: Pre-training of Generic Visual-Linguistic Representations](https://mlsanity.com/paper/1908.08530/) (2019)
- [FLAVA: A Foundational Language And Vision Alignment Model](https://mlsanity.com/paper/2112.04482/) (2021)
- [Unifying Vision-and-Language Tasks via Text Generation](https://mlsanity.com/paper/2102.02779/) (2021)
- [Large-Scale Adversarial Training for Vision-and-Language Representation Learning](https://mlsanity.com/paper/2006.06195/) (2020)
- [MERLOT: Multimodal Neural Script Knowledge Models](https://mlsanity.com/paper/2106.02636/) (2021)
- [UNIMO: Towards Unified-Modal Understanding and Generation via Cross-Modal Contrastive Learning](https://mlsanity.com/paper/2012.15409/) (2020)
- [Seeing Out of tHe bOx: End-to-End Pre-training for Vision-Language Representation Learning](https://mlsanity.com/paper/2104.03135/) (2021)
- [A Survey of Vision-Language Pre-Trained Models](https://mlsanity.com/paper/2202.10936/) (2022)
- [Interest-aware Message-Passing GCN for Recommendation](https://mlsanity.com/paper/2102.10044/) (2021)
- [On Modality Bias Recognition and Reduction](https://mlsanity.com/paper/2202.12690/) (2022)
- [KVL-BERT: Knowledge Enhanced Visual-and-Linguistic BERT for Visual Commonsense Reasoning](https://mlsanity.com/paper/2012.07000/) (2020)
- [AdaVQA: Overcoming Language Priors with Adapted Margin Cosine Loss](https://mlsanity.com/paper/2105.01993/) (2021)
- [A Survey on Video Moment Localization](https://mlsanity.com/paper/2306.07515/) (2023)
- [Joint Answering and Explanation for Visual Commonsense Reasoning](https://mlsanity.com/paper/2202.12626/) (2022)
- [User Diverse Preference Modeling by Multimodal Attentive Metric Learning](https://mlsanity.com/paper/1908.07738/) (2019)

## Built on by (most cited first, 4 of 4)

- [MAGIC-VQA: Multimodal And Grounded Inference with Commonsense Knowledge for Visual Question Answering](https://mlsanity.com/paper/2503.18491/) (2025)
- [Scale Up Composed Image Retrieval Learning via Modification Text Generation](https://mlsanity.com/paper/2504.05316/) (2025)
- [Why Relational Graphs Will Save the Next Generation of Vision Foundation Models?](https://mlsanity.com/paper/2508.18421/) (2025)
- [DMC3: Dual-Modal Counterfactual Contrastive Construction for Egocentric Video Question Answering](https://mlsanity.com/paper/2510.20285/) (2025)

## Abstract (arXiv)

Visual Commonsense Reasoning (VCR) calls for explanatory reasoning behind question answering over visual scenes. To achieve this goal, a model is required to provide an acceptable rationale as the reason for the predicted answers. Progress on the benchmark dataset stems largely from the recent advancement of Vision-Language Transformers (VL Transformers). These models are first pre-trained on some generic large-scale vision-text datasets, and then the learned representations are transferred to the downstream VCR task. Despite their attractive performance, this paper posits that the VL Transformers do not exhibit visual commonsense, which is the key to VCR. In particular, our empirical results pinpoint several shortcomings of existing VL Transformers: small gains from pre-training, unexpected language bias, limited model architecture for the two inseparable sub-tasks, and neglect of the important object-tag correlation. With these findings, we tentatively suggest some future directions from the aspect of dataset, evaluation metric, and training tricks. We believe this work could make researchers revisit the intuition and goals of VCR, and thus help tackle the remaining challenges in visual reasoning.