# Compact Trilinear Interaction for Visual Question Answering

arXiv: https://arxiv.org/abs/1909.11874 · HTML: https://mlsanity.com/paper/1909.11874/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Sep 2019.

## Built on by (most cited first, 24 of 24)

- [Improving Multi-hop Knowledge Base Question Answering by Learning Intermediate Supervision Signals](https://mlsanity.com/paper/2101.03737/) (2021)
- [Multiple Meta-model Quantifying for Medical Visual Question Answering](https://mlsanity.com/paper/2105.08913/) (2021)
- [There is More than Meets the Eye: Self-Supervised Multi-Object Detection and Tracking with Sound by Distilling Multimodal Knowledge](https://mlsanity.com/paper/2103.01353/) (2021)
- [Tensor Networks Meet Neural Networks: A Survey and Future Perspectives](https://mlsanity.com/paper/2302.09019/) (2023)
- [PEVL: Position-enhanced Pre-training and Prompt Tuning for Vision-language Models](https://mlsanity.com/paper/2205.11169/) (2022)
- [Coarse-to-Fine Reasoning for Visual Question Answering](https://mlsanity.com/paper/2110.02526/) (2021)
- [VidLanKD: Improving Language Understanding via Video-Distilled Knowledge Transfer](https://mlsanity.com/paper/2107.02681/) (2021)
- [Categories of Response-Based, Feature-Based, and Relation-Based Knowledge Distillation](https://mlsanity.com/paper/2306.10687/) (2023)
- [Towards Developing a Multilingual and Code-Mixed Visual Question Answering System by Knowledge Distillation](https://mlsanity.com/paper/2109.04653/) (2021)
- [MRI-based Alzheimer's disease prediction via distilling the knowledge in multi-modal data](https://mlsanity.com/paper/2104.03618/) (2021)
- [Interactive Question Answering Systems: Literature Review](https://mlsanity.com/paper/2209.01621/) (2022)
- [Unsupervised Cross-Modal Distillation for Thermal Infrared Tracking](https://mlsanity.com/paper/2108.00187/) (2021)
- [Segment Any Events via Weighted Adaptation of Pivotal Tokens](https://mlsanity.com/paper/2312.16222/) (2023)
- [Cross-modal Contrastive Distillation for Instructional Activity Anticipation](https://mlsanity.com/paper/2201.06734/) (2022)
- [MOI-Mixer: Improving MLP-Mixer with Multi Order Interactions in Sequential Recommendation](https://mlsanity.com/paper/2108.07505/) (2021)
- [Residual Tensor Train: A Quantum-inspired Approach for Learning Multiple Multilinear Correlations](https://mlsanity.com/paper/2108.08659/) (2021)
- [From Shallow to Deep: Compositional Reasoning over Graphs for Visual Question Answering](https://mlsanity.com/paper/2206.12533/) (2022)
- [Audio Representation Learning by Distilling Video as Privileged Information](https://mlsanity.com/paper/2302.02845/) (2023)
- [Attention in Reasoning: Dataset, Analysis, and Modeling](https://mlsanity.com/paper/2204.09774/) (2022)
- [Knowledge-enhanced Iterative Instruction Generation and Reasoning for Knowledge Base Question Answering](https://mlsanity.com/paper/2209.03005/) (2022)
- [Diffusion-based Data Augmentation and Knowledge Distillation with Generated Soft Labels Solving Data Scarcity Problems of SAR Oil Spill Segmentation](https://mlsanity.com/paper/2412.08116/) (2024)
- [VQA with Cascade of Self- and Co-Attention Blocks](https://mlsanity.com/paper/2302.14777/) (2023)
- [ViConsFormer: Constituting Meaningful Phrases of Scene Texts using Transformer-based Method in Vietnamese Text-based Visual Question Answering](https://mlsanity.com/paper/2410.14132/) (2024)
- [ProtoVQA: An Adaptable Prototypical Framework for Explainable Fine-Grained Visual Question Answering](https://mlsanity.com/paper/2509.16680/) (2025)

## Abstract (arXiv)

In Visual Question Answering (VQA), answers have a great correlation with question meaning and visual contents. Thus, to selectively utilize image, question and answer information, we propose a novel trilinear interaction model which simultaneously learns high level associations between these three inputs. In addition, to overcome the interaction complexity, we introduce a multimodal tensor-based PARALIND decomposition which efficiently parameterizes trilinear interaction between the three inputs. Moreover, knowledge distillation is first time applied in Free-form Opened-ended VQA. It is not only for reducing the computational cost and required memory but also for transferring knowledge from trilinear interaction model to bilinear interaction model. The extensive experiments on benchmarking datasets TDIUC, VQA-2.0, and Visual7W show that the proposed compact trilinear interaction model achieves state-of-the-art results when using a single model on all three datasets.