mlsanityData to 7 Oct 2026

FlexiReID: Adaptive Mixture of Expert for Multi-Modal Person Re-Identification

arXiv 2510.15595 ↗First posted 17 Oct 2025cs.CVcited by 3

Not on the map. Why?

Abstract (arXiv)

Multimodal person re-identification (Re-ID) aims to match pedestrian images across different modalities. However, most existing methods focus on limited cross-modal settings and fail to support arbitrary query-retrieval combinations, hindering practical deployment. We propose FlexiReID, a flexible framework that supports seven retrieval modes across four modalities: rgb, infrared, sketches, and text. FlexiReID introduces an adaptive mixture-of-experts (MoE) mechanism to dynamically integrate diverse modality features and a cross-modal query fusion module to enhance multimodal feature extraction. To facilitate comprehensive evaluation, we construct CIRS-PEDES, a unified dataset extending four popular Re-ID datasets to include all four modalities. Extensive experiments demonstrate that FlexiReID achieves state-of-the-art performance and offers strong generalization in complex scenarios.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 50 of its 73 references that are in the map. First posted on arXiv 17 Oct 2025.

Builds on

50 of 73 references.

References · 50

  1. 2017Attention Is All You Needcited by 59,932
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,539
  5. 2021Zero-Shot Text-to-Image Generationcited by 4,276
  6. 2021Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervisioncited by 3,848
  7. 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Modelscited by 3,595
  8. 2017Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layercited by 3,413
  9. 2021Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsitycited by 3,014
  10. 2021Learning to Prompt for Vision-Language Modelscited by 2,269
  11. 2019ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Taskscited by 2,219
  12. 2021Align before Fuse: Vision and Language Representation Learning with Momentum Distillationcited by 1,612
38 more
  1. 2020GShard: Scaling Giant Models with Conditional Computation and Automatic Shardingcited by 1,601
  2. 2019LXMERT: Learning Cross-Modality Encoder Representations from Transformerscited by 1,548
  3. 2021Alias-Free Generative Adversarial Networkscited by 1,181
  4. 2021CLIP-Adapter: Better Vision-Language Models with Feature Adapterscited by 1,021
  5. 2021StyleCLIP: Text-Driven Manipulation of StyleGAN Imagerycited by 990
  6. 2019VL-BERT: Pre-training of Generic Visual-Linguistic Representationscited by 954
  7. 2021Scaling Vision with Sparse Mixture of Expertscited by 740
  8. 2022AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognitioncited by 714
  9. 2021LiT: Zero-Shot Transfer with Locked-image text Tuningcited by 572
  10. 2020Deep Learning for Person Re-identification: A Survey and Outlookcited by 547
  11. 2021Unifying Vision-and-Language Tasks via Text Generationcited by 411
  12. 2021ActionCLIP: A New Paradigm for Video Action Recognitioncited by 317
  13. 2013Learning Factored Representations in a Deep Mixture of Expertscited by 275
  14. 2017Person Search with Natural Language Descriptioncited by 149
  15. 2023Cross-Modal Implicit Relation Reasoning and Aligning for Text-to-Image Person Retrievalcited by 131
  16. 2022Task Residual for Tuning Vision-Language Modelscited by 122
  17. 2020Dynamic Dual-Attentive Aggregation Learning for Visible-Infrared Person Re-Identificationcited by 111
  18. 2021Semantically Self-Aligned Network for Text-to-Image Part-aware Person Re-identificationcited by 108
  19. 2021DSSL: Deep Surroundings-person Separation Learning for Text-based Person Retrievalcited by 102
  20. 2020Cross-modality Person re-identification with Shared-Specific Feature Transfercited by 80
  21. 2022CLIP-Driven Fine-grained Text-Image Person Re-identificationcited by 79
  22. 2020ViTAA: Visual-Textual Attributes Alignment in Person Search by Natural Languagecited by 78
  23. 2022See Finer, See More: Implicit Modality Alignment for Text-based Person Retrievalcited by 65
  24. 2019Improving Description-based Person Re-identification by Multi-granularity Image-text Alignmentscited by 64
  25. 2022Learning Granularity-Unified Representations for Text-to-Image Person Re-identificationcited by 62
  26. 2021Contextual Non-Local Alignment over Full-Scale Representation for Text-Based Person Searchcited by 60
  27. 2021TIPCB: A Simple but Effective Part-based Convolutional Baseline for Text-based Person Searchcited by 57
  28. 2021Text-Based Person Search with Limited Datacited by 53
  29. 2021Farewell to Mutual Information: Variational Distillation for Cross-Modal Person Re-Identificationcited by 50
  30. 2021Learning Semantic-Aligned Feature Representation for Text-based Person Searchcited by 40
  31. 2022CAIBC: Capturing All-round Information Beyond Color for Text-based Person Retrievalcited by 39
  32. 2022Look Before You Leap: Improving Text-based Person Retrieval by Learning A Consistent Cross-modal Common Manifoldcited by 38
  33. 2021AXM-Net: Implicit Cross-Modal Feature Alignment for Person Re-identificationcited by 34
  34. 2023EVE: Efficient Vision-Language Pre-training with Masked Prediction and Modality-Aware MoEcited by 24
  35. 2020Dual Gaussian-based Variational Subspace Disentanglement for Visible-Infrared Person Re-Identificationcited by 23
  36. 2023CLIP-based Synergistic Knowledge Transfer for Text-based Person Retrievalcited by 10
  37. 2024Exploring Semantic Consistency and Style Diversity for Domain Generalized Semantic Segmentationcited by 7
  38. 2022Instance-level Heterogeneous Domain Adaptation for Limited-labeled Sketch-to-Photo Retrievalcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026DRFormer: A Dual-Regularized Bidirectional Transformer for Person Re-identificationcited by 0
  2. 2026Unleashing MLLMs on the Edge: A Unified Framework for Cross-Modal ReID via Adaptive SVD Distillationcited by 0
  3. 2026FUSE: Frequency-domain Unification and Spectral Energy Alignment for Multi-modal Object Re-Identificationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025ChatReID: Open-ended Interactive Person Retrieval via Hierarchical Progressive Tuning for Vision Language Models
  2. 2025ReID5o: Achieving Omni Multi-modal Person Re-identification in a Single Model
  3. 2025What really matters for person re-identification? A Mixture-of-Experts Framework for Semantic Attribute Importance
  4. 2025Attribute Guidance With Inherent Pseudo-label For Occluded Person Re-identification
  5. 2025Following the Clues: Experiments on Person Re-ID using Cross-Modal Intelligence
  6. 2025ShapeSpeak: Body Shape-Aware Textual Alignment for Visible-Infrared Person Re-Identification
  7. 2026A Generative AI Integrated Multimodal Framework for Low-Latency Multi-Camera Person Re-Identification
  8. 2025Human-centered Interactive Learning via MLLMs for Text-to-Image Person Re-identification