# Cascaded Mutual Modulation for Visual Reasoning

arXiv: https://arxiv.org/abs/1809.01943 · HTML: https://mlsanity.com/paper/1809.01943/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Sep 2018.

## Built on by (most cited first, 5 of 5)

- [Explain Before You Answer: A Survey on Compositional Visual Reasoning](https://mlsanity.com/paper/2508.17298/) (2025)
- [Look, Remember and Reason: Grounded reasoning in videos with language models](https://mlsanity.com/paper/2306.17778/) (2023)
- [A Comprehensive Survey on Visual Question Answering Datasets and Algorithms](https://mlsanity.com/paper/2411.11150/) (2024)
- [Bilateral Cross-Modality Graph Matching Attention for Feature Fusion in Visual Question Answering](https://mlsanity.com/paper/2112.07270/) (2021)
- [lilGym: Natural Language Visual Reasoning with Reinforcement Learning](https://mlsanity.com/paper/2211.01994/) (2022)

## Abstract (arXiv)

Visual reasoning is a special visual question answering problem that is multi-step and compositional by nature, and also requires intensive text-vision interactions. We propose CMM: Cascaded Mutual Modulation as a novel end-to-end visual reasoning model. CMM includes a multi-step comprehension process for both question and image. In each step, we use a Feature-wise Linear Modulation (FiLM) technique to enable textual/visual pipeline to mutually control each other. Experiments show that CMM significantly outperforms most related models, and reach state-of-the-arts on two visual reasoning benchmarks: CLEVR and NLVR, collected from both synthetic and natural languages. Ablation studies confirm that both our multistep framework and our visual-guided language modulation are critical to the task. Our code is available at https://github.com/FlamingHorizon/CMM-VR.