# Connecting Multi-modal Contrastive Representations

arXiv: https://arxiv.org/abs/2305.14381 · HTML: https://mlsanity.com/paper/2305.14381/

## Key facts

- Cited by 36 papers in the map (data through 14 Oct 2026).
- Builds on 52 of its 70 references that are in the map.
- First posted on arXiv 22 May 2023.

## Builds on (most cited first, 30 of 52)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [ShapeNet: An Information-Rich 3D Model Repository](https://mlsanity.com/paper/1512.03012/) (2015)
- [Objaverse: A Universe of Annotated 3D Objects](https://mlsanity.com/paper/2212.08051/) (2022)
- [Grounded Language-Image Pre-training](https://mlsanity.com/paper/2112.03857/) (2021)
- [Large-scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation](https://mlsanity.com/paper/2211.06687/) (2022)
- [Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling](https://mlsanity.com/paper/2111.14819/) (2021)
- [CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval](https://mlsanity.com/paper/2104.08860/) (2021)
- [VGGSound: A Large-scale Audio-Visual Dataset](https://mlsanity.com/paper/2004.14368/) (2020)
- [Contrastive Learning of Medical Visual Representations from Paired Images and Text](https://mlsanity.com/paper/2010.00747/) (2020)
- [VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding](https://mlsanity.com/paper/2109.14084/) (2021)
- [Mind the Gap: Understanding the Modality Gap in Multi-modal Contrastive Representation Learning](https://mlsanity.com/paper/2203.02053/) (2022)
- [DenseCLIP: Language-Guided Dense Prediction with Context-Aware Prompting](https://mlsanity.com/paper/2112.01518/) (2021)
- [GroupViT: Semantic Segmentation Emerges from Text Supervision](https://mlsanity.com/paper/2202.11094/) (2022)
- [PointCLIP: Point Cloud Understanding by CLIP](https://mlsanity.com/paper/2112.02413/) (2021)
- [ScanRefer: 3D Object Localization in RGB-D Scans using Natural Language](https://mlsanity.com/paper/1912.08830/) (2019)
- [Clotho: An Audio Captioning Dataset](https://mlsanity.com/paper/1910.09387/) (2019)
- [ScanQA: 3D Question Answering for Spatial Scene Understanding](https://mlsanity.com/paper/2112.10482/) (2021)
- [AudioCLIP: Extending CLIP to Image, Text and Audio](https://mlsanity.com/paper/2106.13043/) (2021)
- [SQA3D: Situated Question Answering in 3D Scenes](https://mlsanity.com/paper/2210.07474/) (2022)
- [ULIP: Learning a Unified Representation of Language, Images, and Point Clouds for 3D Understanding](https://mlsanity.com/paper/2212.05171/) (2022)
- [The Sound of Pixels](https://mlsanity.com/paper/1804.03160/) (2018)
- [MM-Diffusion: Learning Multi-Modal Diffusion Models for Joint Audio and Video Generation](https://mlsanity.com/paper/2212.09478/) (2022)
- [Wav2CLIP: Learning Robust Audio Representations From CLIP](https://mlsanity.com/paper/2110.11499/) (2021)
- [ULIP-2: Towards Scalable Multimodal Pre-training for 3D Understanding](https://mlsanity.com/paper/2305.08275/) (2023)
- [Learning to Localize Sound Source in Visual Scenes](https://mlsanity.com/paper/1803.03849/) (2018)

## Built on by (most cited first, 30 of 36)

- [Chat-Scene: Bridging 3D Scene and Large Language Models with Object Identifiers](https://mlsanity.com/paper/2312.08168/) (2023)
- [Frieren: Efficient Video-to-Audio Generation Network with Rectified Flow Matching](https://mlsanity.com/paper/2406.00320/) (2024)
- [LongVALE: Vision-Audio-Language-Event Benchmark Towards Time-Aware Omni-Modal Perception of Long Videos](https://mlsanity.com/paper/2411.19772/) (2024)
- [OmniBind: Large-scale Omni Multimodal Representation via Binding Spaces](https://mlsanity.com/paper/2407.11895/) (2024)
- [Bridging the Vision-Brain Gap with an Uncertainty-Aware Blur Prior](https://mlsanity.com/paper/2503.04207/) (2025)
- [Extending Multi-modal Contrastive Representations](https://mlsanity.com/paper/2310.08884/) (2023)
- [FreeBind: Free Lunch in Unified Multimodal Space via Knowledge Fusion](https://mlsanity.com/paper/2405.04883/) (2024)
- [ProtoMol: Enhancing Molecular Property Prediction via Prototype-Guided Multimodal Learning](https://mlsanity.com/paper/2510.16824/) (2025)
- [Towards Modality Generalization: A Benchmark and Prospective Analysis](https://mlsanity.com/paper/2412.18277/) (2024)
- [Towards an Explainable Comparison and Alignment of Feature Embeddings](https://mlsanity.com/paper/2506.06231/) (2025)
- [The More, the Merrier: Contrastive Fusion for Higher-Order Multimodal Alignment](https://mlsanity.com/paper/2511.21331/) (2025)
- [Multi-modal Relation Distillation for Unified 3D Representation Learning](https://mlsanity.com/paper/2407.14007/) (2024)
- [CIBR: Cross-modal Information Bottleneck Regularization for Robust CLIP Generalization](https://mlsanity.com/paper/2503.24182/) (2025)
- [SegTalker: Segmentation-based Talking Face Generation with Mask-guided Local Editing](https://mlsanity.com/paper/2409.03605/) (2024)
- [ArcSin: Adaptive ranged cosine Similarity injected noise for Language-Driven Visual Tasks](https://mlsanity.com/paper/2402.17298/) (2024)
- [Multimodal Deep Learning for Low-Resource Settings: A Vector Embedding Alignment Approach for Healthcare Applications](https://mlsanity.com/paper/2406.02601/) (2024)
- [Towards Uniformity and Alignment for Multimodal Representation Learning](https://mlsanity.com/paper/2602.09507/) (2026)
- [InfoMAE: Pair-Efficient Cross-Modal Alignment for Multimodal Time-Series Sensing Signals](https://mlsanity.com/paper/2504.09707/) (2025)
- [Diffusion-Link: Diffusion Probabilistic Model for Bridging the Audio-Text Modality Gap](https://mlsanity.com/paper/2510.11330/) (2025)
- [Learning Brain Representation with Hierarchical Visual Embeddings](https://mlsanity.com/paper/2602.07495/) (2026)
- [Large-vocabulary forensic pathological analyses via prototypical cross-modal contrastive learning](https://mlsanity.com/paper/2407.14904/) (2024)
- [Human-Aligned Procedural Level Generation Reinforcement Learning via Text-Level-Sketch Shared Representation](https://mlsanity.com/paper/2508.09860/) (2025)
- [TextME: Bridging Unseen Modalities Through Text Descriptions](https://mlsanity.com/paper/2602.03098/) (2026)
- [Craft: Cross-modal Aligned Features Improve Robustness of Prompt Tuning](https://mlsanity.com/paper/2407.15894/) (2024)
- [How does Labeling Error Impact Contrastive Learning? A Perspective from Data Dimensionality Reduction](https://mlsanity.com/paper/2507.11161/) (2025)
- [ProM3E: Probabilistic Masked MultiModal Embedding Model for Ecology](https://mlsanity.com/paper/2511.02946/) (2025)
- [EBind: a practical approach to space binding](https://mlsanity.com/paper/2511.14229/) (2025)
- [Unmasking Synthetic Realities in Generative AI: A Comprehensive Review of Adversarially Robust Deepfake Detection Systems](https://mlsanity.com/paper/2507.21157/) (2025)
- [MAJORScore: A Novel Metric for Evaluating Multimodal Relevance via Joint Representation](https://mlsanity.com/paper/2509.21365/) (2025)
- [Text2Loc++: Generalizing 3D Point Cloud Localization from Natural Language](https://mlsanity.com/paper/2511.15308/) (2025)

## Abstract (arXiv)

Multi-modal Contrastive Representation learning aims to encode different modalities into a semantically aligned shared space. This paradigm shows remarkable generalization ability on numerous downstream tasks across various modalities. However, the reliance on massive high-quality data pairs limits its further development on more modalities. This paper proposes a novel training-efficient method for learning MCR without paired data called Connecting Multi-modal Contrastive Representations (C-MCR). Specifically, given two existing MCRs pre-trained on (A, B) and (B, C) modality pairs, we project them to a new space and use the data from the overlapping modality B to aligning the two MCRs in the new space. Meanwhile, since the modality pairs (A, B) and (B, C) are already aligned within each MCR, the connection learned by overlapping modality can also be transferred to non-overlapping modality pair (A, C). To unleash the potential of C-MCR, we further introduce a semantic-enhanced inter- and intra-MCR connection method. We first enhance the semantic consistency and completion of embeddings across different modalities for more robust alignment. Then we utilize the inter-MCR alignment to establish the connection, and employ the intra-MCR alignment to better maintain the connection for inputs from non-overlapping modalities. To demonstrate the effectiveness of C-MCR, we connect CLIP and CLAP via texts to derive audio-visual representations, and integrate CLIP and ULIP via images for 3D-language representations. Remarkably, without using any paired data, C-MCR for audio-visual achieves state-of-the-art performance on audio-image retrieval, audio-visual source localization, and counterfactual audio-image recognition tasks. Furthermore, C-MCR for 3D-language also attains advanced zero-shot 3D point cloud classification accuracy on ModelNet40.