# Learning Aligned Cross-Modal Representations from Weakly Aligned Data

arXiv: https://arxiv.org/abs/1607.07295 · HTML: https://mlsanity.com/paper/1607.07295/

## Key facts

- Cited by 34 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Jul 2016.

## Built on by (most cited first, 30 of 34)

- [Context Autoencoder for Self-Supervised Representation Learning](https://mlsanity.com/paper/2202.03026/) (2022)
- [MultiMAE: Multi-modal Multi-task Masked Autoencoders](https://mlsanity.com/paper/2204.01678/) (2022)
- [Omnivore: A Single Model for Many Visual Modalities](https://mlsanity.com/paper/2201.08377/) (2022)
- [OmniMAE: Single Model Masked Pretraining on Images and Videos](https://mlsanity.com/paper/2206.08356/) (2022)
- [Explainability of deep vision-based autonomous driving systems: Review and challenges](https://mlsanity.com/paper/2101.05307/) (2021)
- [DFormer: Rethinking RGBD Representation Learning for Semantic Segmentation](https://mlsanity.com/paper/2309.09668/) (2023)
- [Cross-modal Learning for Domain Adaptation in 3D Semantic Segmentation](https://mlsanity.com/paper/2101.07253/) (2021)
- [Spectral Unsupervised Domain Adaptation for Visual Recognition](https://mlsanity.com/paper/2106.06112/) (2021)
- [SceneTrilogy: On Human Scene-Sketch and its Complementarity with Photo and Text](https://mlsanity.com/paper/2204.11964/) (2022)
- [Lossless Adaptation of Pretrained Vision Models For Robotic Manipulation](https://mlsanity.com/paper/2304.06600/) (2023)
- [You'll Never Walk Alone: A Sketch and Text Duet for Fine-Grained Image Retrieval](https://mlsanity.com/paper/2403.07222/) (2024)
- [Variational Selective Autoencoder: Learning from Partially-Observed Heterogeneous Data](https://mlsanity.com/paper/2102.12679/) (2021)
- [Rapid Network Adaptation: Learning to Adapt Neural Networks Using Test-Time Feedback](https://mlsanity.com/paper/2309.15762/) (2023)
- [Sound and Visual Representation Learning with Multiple Pretraining Tasks](https://mlsanity.com/paper/2201.01046/) (2022)
- [OmniSegmentor: A Flexible Multi-Modal Learning Framework for Semantic Segmentation](https://mlsanity.com/paper/2509.15096/) (2025)
- [Template-Free Try-on Image Synthesis via Semantic-guided Optimization](https://mlsanity.com/paper/2102.03503/) (2021)
- [Machine Learning in Nuclear Physics](https://mlsanity.com/paper/2112.02309/) (2021)
- [Cross-Modal Alignment Learning of Vision-Language Conceptual Systems](https://mlsanity.com/paper/2208.01744/) (2022)
- [Training Transitive and Commutative Multimodal Transformers with LoReTTa](https://mlsanity.com/paper/2305.14243/) (2023)
- [A Client-server Deep Federated Learning for Cross-domain Surgical Image Segmentation](https://mlsanity.com/paper/2306.08720/) (2023)
- [Seeing Faces in Things: A Model and Dataset for Pareidolia](https://mlsanity.com/paper/2409.16143/) (2024)
- [M33D: Learning 3D priors using Multi-Modal Masked Autoencoders for 2D image and video understanding](https://mlsanity.com/paper/2309.15313/) (2023)
- [Domain Adaptation for Large-Vocabulary Object Detectors](https://mlsanity.com/paper/2401.06969/) (2024)
- [Information Theory-Guided Heuristic Progressive Multi-View Coding](https://mlsanity.com/paper/2109.02344/) (2021)
- [SF-FSDA: Source-Free Few-Shot Domain Adaptive Object Detection with Efficient Labeled Data Factory](https://mlsanity.com/paper/2306.04385/) (2023)
- [Distributionally Robust Alignment for Medical Federated Vision-Language Pre-training Under Data Heterogeneity](https://mlsanity.com/paper/2404.03854/) (2024)
- [Artificial Intelligence for Geometry-Based Feature Extraction, Analysis and Synthesis in Artistic Images: A Survey](https://mlsanity.com/paper/2412.01450/) (2024)
- [Weakly-Supervised Action Detection Guided by Audio Narration](https://mlsanity.com/paper/2205.05895/) (2022)
- [Bringing Image Scene Structure to Video via Frame-Clip Consistency of Object Tokens](https://mlsanity.com/paper/2206.06346/) (2022)
- [Unifying Tracking and Image-Video Object Detection](https://mlsanity.com/paper/2211.11077/) (2022)

## Abstract (arXiv)

People can recognize scenes across many different modalities beyond natural images. In this paper, we investigate how to learn cross-modal scene representations that transfer across modalities. To study this problem, we introduce a new cross-modal scene dataset. While convolutional neural networks can categorize cross-modal scenes well, they also learn an intermediate representation not aligned across modalities, which is undesirable for cross-modal transfer applications. We present methods to regularize cross-modal convolutional neural networks so that they have a shared representation that is agnostic of the modality. Our experiments suggest that our scene representation can help transfer representations across modalities for retrieval. Moreover, our visualizations suggest that units emerge in the shared representation that tend to activate on consistent concepts independently of the modality.