{"ID":2854086,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.15595","arxiv_id":"2510.15595","title":"FlexiReID: Adaptive Mixture of Expert for Multi-Modal Person Re-Identification","abstract":"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.","short_abstract":"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 suppor...","url_abs":"https://arxiv.org/abs/2510.15595","url_pdf":"https://arxiv.org/pdf/2510.15595v1","authors":"[\"Zhen Sun\",\"Lei Tan\",\"Yunhang Shen\",\"Chengmao Cai\",\"Xing Sun\",\"Pingyang Dai\",\"Liujuan Cao\",\"Rongrong Ji\"]","published":"2025-10-17T12:41:05Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false}