# Multi-modal Large Language Model Enhanced Pseudo 3D Perception Framework for Visual Commonsense Reasoning

arXiv: https://arxiv.org/abs/2301.13335 · HTML: https://mlsanity.com/paper/2301.13335/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 18 of its 41 references that are in the map.
- First posted on arXiv 30 Jan 2023.

## Placed in

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

## Builds on (most cited first, 18 of 18)

- [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)
- [Vision Transformers for Dense Prediction](https://mlsanity.com/paper/2103.13413/) (2021)
- [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)
- [VL-BERT: Pre-training of Generic Visual-Linguistic Representations](https://mlsanity.com/paper/1908.08530/) (2019)
- [From Recognition to Cognition: Visual Commonsense Reasoning](https://mlsanity.com/paper/1811.10830/) (2018)
- [UNIMO: Towards Unified-Modal Understanding and Generation via Cross-Modal Contrastive Learning](https://mlsanity.com/paper/2012.15409/) (2020)
- [Enhanced LSTM for Natural Language Inference](https://mlsanity.com/paper/1609.06038/) (2016)
- [MUTAN: Multimodal Tucker Fusion for Visual Question Answering](https://mlsanity.com/paper/1705.06676/) (2017)
- [Visual Commonsense R-CNN](https://mlsanity.com/paper/2002.12204/) (2020)
- [Towards Explainable 3D Grounded Visual Question Answering: A New Benchmark and Strong Baseline](https://mlsanity.com/paper/2209.12028/) (2022)
- [Heterogeneous Graph Learning for Visual Commonsense Reasoning](https://mlsanity.com/paper/1910.11475/) (2019)
- [Joint Answering and Explanation for Visual Commonsense Reasoning](https://mlsanity.com/paper/2202.12626/) (2022)
- [MOTSLAM: MOT-assisted monocular dynamic SLAM using single-view depth estimation](https://mlsanity.com/paper/2210.02038/) (2022)
- [Progressive Fusion for Unsupervised Binocular Depth Estimation using Cycled Networks](https://mlsanity.com/paper/1909.07667/) (2019)

## Built on by (most cited first, 3 of 3)

- [MMFuser: Multimodal Multi-Layer Feature Fuser for Fine-Grained Vision-Language Understanding](https://mlsanity.com/paper/2410.11829/) (2024)
- [LLM-EvRep: Learning an LLM-Compatible Event Representation Using a Self-Supervised Framework](https://mlsanity.com/paper/2502.14273/) (2025)
- [Point Cloud as a Foreign Language for Multi-modal Large Language Model](https://mlsanity.com/paper/2603.09173/) (2026)

## Abstract (arXiv)

The visual commonsense reasoning (VCR) task is to choose an answer and provide a justifying rationale based on the given image and textural question. Representative works first recognize objects in images and then associate them with key words in texts. However, existing approaches do not consider exact positions of objects in a human-like three-dimensional (3D) manner, making them incompetent to accurately distinguish objects and understand visual relation. Recently, multi-modal large language models (MLLMs) have been used as powerful tools for several multi-modal tasks but not for VCR yet, which requires elaborate reasoning on specific visual objects referred by texts. In light of the above, an MLLM enhanced pseudo 3D perception framework is designed for VCR. Specifically, we first demonstrate that the relation between objects is relevant to object depths in images, and hence introduce object depth into VCR frameworks to infer 3D positions of objects in images. Then, a depth-aware Transformer is proposed to encode depth differences between objects into the attention mechanism of Transformer to discriminatively associate objects with visual scenes guided by depth. To further associate the answer with the depth of visual scene, each word in the answer is tagged with a pseudo depth to realize depth-aware association between answer words and objects. On the other hand, BLIP-2 as an MLLM is employed to process images and texts, and the referring expressions in texts involving specific visual objects are modified with linguistic object labels to serve as comprehensible MLLM inputs. Finally, a parameter optimization technique is devised to fully consider the quality of data batches based on multi-level reasoning confidence. Experiments on the VCR dataset demonstrate the superiority of the proposed framework over state-of-the-art approaches.