Papers with Multimodal learning
UniS-MMC: Multimodal Classification via Unimodality-supervised Multimodal Contrastive Learning (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing multimodal fusion methods ignore inter-modality relationship, treat each modality equally, suffer sensor noise, and thus reduce multimodal learning performance. |
| Approach: | They propose a multimodal contrastive method to explore more reliable multimodal representations under the weak supervision of unimodal predicting. |
| Outcome: | The proposed method outperforms current state-of-the-art multimodal learning methods on image-text classification benchmarks UPMC-Food-101 and N24News. |
LRMM: Learning to Recommend with Missing Modalities (D18-1)
Copied to clipboard
| Challenge: | Existing methods for content-based recommendation with missing or corrupted modalities are lacking in learning multimodal models. |
| Approach: | They propose a multimodal multimodal autoencoder that learns multimodal representations for complementing and imputing missing modalities. |
| Outcome: | The proposed framework achieves state-of-the-art performance on rating prediction tasks and is more robust to previous methods in alleviating data-sparsity and the cold-start problem. |
T2DR: A Two-Tier Deficiency-Resistant Framework for Incomplete Multimodal Learning (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing incomplete multimodal learning frameworks are inadequate for integrating multimodal data. |
| Approach: | They propose a framework for incomplete multimodal learning that is deficiency-resistant and provides two modules to address fine-grained deficiencies. |
| Outcome: | The proposed framework outperforms the SOTA models on two well-known multimodal benchmarks. |
Adversarial Alignment with Anchor Dragging Drift (A3D2): Multimodal Domain Adaptation with Partially Shifted Modalities (2025.acl-long)
Copied to clipboard
| Challenge: | Domain adaptation is underexplored in multimodal learning environments due to expensive data collection and annotation. |
| Approach: | They propose a bi-alignment scheme to perform drift-drift and anchor-driving matching with partially shifting anchors. |
| Outcome: | The proposed approach achieves superior performance compared with state-of-the-art approaches. |
SCOPE: Preserving Modality-Specific Cues to Mitigate Modality Laziness in Multimodal Learning (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to learning multimodal representations emphasize shared semantics and overlook modality-specific cues. |
| Approach: | They propose a framework for learning complete multimodal representations using shared and practical cues. |
| Outcome: | SCOPE outperforms SOTA benchmarks on four datasets and achieves 27.10% accuracy improvement. |
Word-Aware Modality Stimulation for Multimodal Fusion (2024.lrec-main)
Copied to clipboard
| Challenge: | Multimodal learning is expected to make more accurate predictions than text-only analysis. |
| Approach: | They propose a method for fusing multimodal inputs with text-based fusion methods . they propose fusion that integrates non-verbal modalities with text . |
| Outcome: | The proposed method improves sentiment prediction by using non-verbal modalities with text . the proposed method is unsuitable for applying attention to text modality in the fusion phase . |