# Cascaded Mutual Modulation for Visual Reasoning

Source: [Cascaded Mutual Modulation for Visual Reasoning](<https://www.sota2.com/research/paper/68fa64c91e209131cea06a33>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T21:11:58.696Z

Authors: Yiqun Yao, Jiaming Xu, Feng Wang, Bo Xu

Published: 2018-09-06T12:26:24.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1809.01943>)

[PDF](<https://arxiv.org/pdf/1809.01943.pdf>)
