{"total":31,"rows":[{"id":"2302.03084","title":"Pic2Word: Mapping Pictures to Words for Zero-shot Composed Image Retrieval","created":"2023-02-06","cited_by_count":156,"area":null},{"id":"2302.10035","title":"Large-scale Multi-Modal Pre-trained Models: A Comprehensive Survey","created":"2023-02-20","cited_by_count":153,"area":null},{"id":"2212.05051","title":"VindLU: A Recipe for Effective Video-and-Language Pretraining","created":"2022-12-09","cited_by_count":87,"area":null},{"id":"2304.01008","title":"Self-Supervised Multimodal Learning: A Survey","created":"2023-03-31","cited_by_count":58,"area":null},{"id":"2303.02982","title":"CLIP-guided Prototype Modulating for Few-shot Action Recognition","created":"2023-03-06","cited_by_count":41,"area":null},{"id":"2212.10888","title":"A Survey of Mix-based Data Augmentation: Taxonomy, Methods, Applications, and Explainability","created":"2022-12-21","cited_by_count":31,"area":null},{"id":"2305.11965","title":"Not All Semantics are Created Equal: Contrastive Self-supervised Learning with Automatic Temperature Individualization","created":"2023-05-19","cited_by_count":25,"area":null},{"id":"2409.05202","title":"A Survey on Mixup Augmentations and Beyond","created":"2024-09-08","cited_by_count":20,"area":null},{"id":"2402.09649","title":"ProtChatGPT: Towards Understanding Proteins with Large Language Models","created":"2024-02-15","cited_by_count":18,"area":null},{"id":"2305.12964","title":"Text-based Person Search without Parallel Image-Text Data","created":"2023-05-22","cited_by_count":17,"area":null},{"id":"2602.23169","title":"Learning Continuous Wasserstein Barycenter Space for Generalized All-in-One Image Restoration","created":"2026-02-26","cited_by_count":15,"area":null},{"id":"2303.05309","title":"MixSpeech: Cross-Modality Self-Learning with Audio-Visual Stream Mixup for Visual Speech Translation and Recognition","created":"2023-03-09","cited_by_count":14,"area":null},{"id":"2411.06518","title":"Causal Representation Learning from Multimodal Biomedical Observations","created":"2024-11-10","cited_by_count":13,"area":null},{"id":"2407.00603","title":"Hierarchical Memory for Long Video QA","created":"2024-06-30","cited_by_count":9,"area":null},{"id":"2507.03304","title":"Bridging Domain Generalization to Multimodal Domain Generalization via Unified Representations","created":"2025-07-04","cited_by_count":9,"area":null},{"id":"2305.15483","title":"Weakly Supervised Vision-and-Language Pre-training with Relative Representations","created":"2023-05-24","cited_by_count":5,"area":null},{"id":"2406.09003","title":"Enhancing Cross-Modal Fine-Tuning with Gradually Intermediate Modality Generation","created":"2024-06-13","cited_by_count":5,"area":null},{"id":"2410.02086","title":"Anchors Aweigh! Sail for Optimal Unified Multi-Modal Representations","created":"2024-10-02","cited_by_count":5,"area":null},{"id":"2507.14935","title":"Open-set Cross Modal Generalization via Multimodal Unified Representation","created":"2025-07-20","cited_by_count":4,"area":null},{"id":"2505.21637","title":"BaryIR: Learning Multi-Source Unified Representation in Continuous Barycenter Space for Generalizable All-in-One Image Restoration","created":"2025-05-27","cited_by_count":3,"area":null},{"id":"2509.25831","title":"MIDAS: Misalignment-based Data Augmentation Strategy for Imbalanced Multimodal Learning","created":"2025-09-30","cited_by_count":2,"area":null},{"id":"2511.12150","title":"Breaking the Modality Wall: Time-step Mixup for Efficient Spiking Knowledge Transfer from Static to Event Domain","created":"2025-11-15","cited_by_count":2,"area":null},{"id":"2312.12334","title":"PowMix: A Versatile Regularizer for Multimodal Sentiment Analysis","created":"2023-12-19","cited_by_count":1,"area":null},{"id":"2504.00561","title":"Continual Cross-Modal Generalization","created":"2025-04-01","cited_by_count":0,"area":null},{"id":"2509.11362","title":"PersonaX: Multimodal Datasets with LLM-Inferred Behavior Traits","created":"2025-09-14","cited_by_count":0,"area":null},{"id":"2509.12959","title":"Time-step Mixup for Efficient Spiking Knowledge Transfer from Appearance to Event Domain","created":"2025-09-16","cited_by_count":0,"area":null},{"id":"2510.11579","title":"MS-Mix: Sentiment-Guided Adaptive Augmentation for Multimodal Sentiment Analysis","created":"2025-10-13","cited_by_count":0,"area":null},{"id":"2511.00831","title":"Enhancing Adversarial Transferability in Visual-Language Pre-training Models via Local Shuffle and Sample-based Attack","created":"2025-11-02","cited_by_count":0,"area":null},{"id":"2602.03570","title":"Asymmetric Hierarchical Anchoring for Robust Audio-Visual Cross-Modal Generalization","created":"2026-02-03","cited_by_count":0,"area":null},{"id":"2605.12145","title":"Cross-Modal-Domain Generalization Through Semantically Aligned Discrete Representations","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2609.12965","title":"Generative Retrieval for Unsupervised Text-Based Person Search","created":"2026-09-11","cited_by_count":0,"area":null}],"next_cursor":null}