MiMIC: Mitigating Visual Modality Collapse in Universal Multimodal Retrieval While Avoiding Semantic Misalignment

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Li, Juan, Ding, Chuanghao, Zhang, Xujie, Nguyen, Cam-Tu
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

SynthDoc: Bilingual Documents Synthesis for Visual Document Understanding
by: Ding, Chuanghao, et al.
Published: (2024)

Mitigating Semantic Collapse in Partially Relevant Video Retrieval
by: Moon, WonJun, et al.
Published: (2025)

MiMIC: Multi-Modal Indian Earnings Calls Dataset to Predict Stock Prices
by: Ghosh, Sohom, et al.
Published: (2025)

Beyond Artificial Misalignment: Detecting and Grounding Semantic-Coordinated Multimodal Manipulations
by: Shen, Jinjie, et al.
Published: (2025)

A Closer Look at Multimodal Representation Collapse
by: Chaudhuri, Abhra, et al.
Published: (2025)

Federated Cross-Modal Retrieval with Missing Modalities via Semantic Routing and Adapter Personalization
by: Zhou, Hefeng, et al.
Published: (2026)

MissBench: Benchmarking Multimodal Affective Analysis under Imbalanced Missing Modalities
by: Pham, Tien Anh, et al.
Published: (2026)

Beyond Semantic Priors: Mitigating Optimization Collapse for Generalizable Visual Forensics
by: Liu, Jipeng, et al.
Published: (2026)

StitchFusion: Weaving Any Visual Modalities to Enhance Multimodal Semantic Segmentation
by: Li, Bingyu, et al.
Published: (2024)

Knowledge-based Visual Question Answer with Multimodal Processing, Retrieval and Filtering
by: Hong, Yuyang, et al.
Published: (2025)

Multimodal Contextualized Support for Enhancing Video Retrieval System
by: Nguyen-Le, Quoc-Bao, et al.
Published: (2024)

LLandMark: A Multi-Agent Framework for Landmark-Aware Multimodal Interactive Video Retrieval
by: Phung, Minh-Chi, et al.
Published: (2026)

Modelling Visual Semantics via Image Captioning to extract Enhanced Multi-Level Cross-Modal Semantic Incongruity Representation with Attention for Multimodal Sarcasm Detection
by: Aggarwal, Sajal, et al.
Published: (2024)

Combating Visual Neglect and Semantic Drift in Large Multimodal Models for Enhanced Cross-Modal Retrieval
by: Zhang, Guosheng, et al.
Published: (2026)

Explaining and Mitigating the Modality Gap in Contrastive Multimodal Learning
by: Yaras, Can, et al.
Published: (2024)

The Role of Visual Modality in Multimodal Mathematical Reasoning: Challenges and Insights
by: Liu, Yufang, et al.
Published: (2025)

Preserving Cross-Modal Stability for Visual Unlearning in Multimodal Scenarios
by: Li, Jinghan Xu Yuyang Zhang Qixuan Cai Jiancheng Chen Keqiu
Published: (2025)

Leveraging Retrieval Augment Approach for Multimodal Emotion Recognition Under Missing Modalities
by: Fan, Qi, et al.
Published: (2024)

Mitigating Visual Hallucinations via Semantic Curriculum Preference Optimization in MLLMs
by: Li, Yuanshuai, et al.
Published: (2025)

HV-Attack: Hierarchical Visual Attack for Multimodal Retrieval Augmented Generation
by: Luo, Linyin, et al.
Published: (2025)

AlignZeg: Mitigating Objective Misalignment for Zero-shot Semantic Segmentation
by: Ge, Jiannan, et al.
Published: (2024)

Semantic-Consistent Bidirectional Contrastive Hashing for Noisy Multi-Label Cross-Modal Retrieval
by: Peng, Likang, et al.
Published: (2025)

VideoSEAL: Mitigating Evidence Misalignment in Agentic Long Video Understanding by Decoupling Answer Authority
by: Qiu, Chenhao, et al.
Published: (2026)

Diagnosing and Mitigating Modality Interference in Multimodal Large Language Models
by: Cai, Rui, et al.
Published: (2025)

Leveraging Hierarchical Image-Text Misalignment for Universal Fake Image Detection
by: Zhang, Daichi, et al.
Published: (2025)

On the Value of Cross-Modal Misalignment in Multimodal Representation Learning
by: Cai, Yichao, et al.
Published: (2025)

Rethinking Visual Token Reduction in LVLMs Under Cross-Modal Misalignment
by: Xu, Rui, et al.
Published: (2025)

Uni-X: Mitigating Modality Conflict with a Two-End-Separated Architecture for Unified Multimodal Models
by: Hao, Jitai, et al.
Published: (2025)

Projecting Gaussian Ellipsoids While Avoiding Affine Projection Approximation
by: Qi, Han, et al.
Published: (2024)

Rad-VLSM: A Cross-Modal Framework with Semantics-Assisted Prompting for Medical Segmentation and Diagnosis
by: Zhang, Fengyi, et al.
Published: (2026)

IDMR: Towards Instance-Driven Precise Visual Correspondence in Multimodal Retrieval
by: Liu, Bangwei, et al.
Published: (2025)

Unifying Visual and Semantic Feature Spaces with Diffusion Models for Enhanced Cross-Modal Alignment
by: Zheng, Yuze, et al.
Published: (2024)

OMGM: Orchestrate Multiple Granularities and Modalities for Efficient Multimodal Retrieval
by: Yang, Wei, et al.
Published: (2025)

StableAnimator++: Overcoming Pose Misalignment and Face Distortion for Human Image Animation
by: Tu, Shuyuan, et al.
Published: (2025)

STSA: Spatial-Temporal Semantic Alignment for Visual Dubbing
by: Ding, Zijun, et al.
Published: (2025)

Thinking Before Looking: Improving Multimodal LLM Reasoning via Mitigating Visual Hallucination
by: Zheng, Haojie, et al.
Published: (2024)

Robustness Evaluation of OCR-based Visual Document Understanding under Multi-Modal Adversarial Attacks
by: Tien, Dong Nguyen, et al.
Published: (2025)

Cross the Gap: Exposing the Intra-modal Misalignment in CLIP via Modality Inversion
by: Mistretta, Marco, et al.
Published: (2025)

Adaptive Video Distillation: Mitigating Oversaturation and Temporal Collapse in Few-Step Generation
by: You, Yuyang, et al.
Published: (2026)

Multimodal Foundation Model for Cross-Modal Retrieval and Activity Recognition Tasks
by: Matsuishi, Koki, et al.
Published: (2025)