{"ID":2881800,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.11218","arxiv_id":"2508.11218","title":"A CLIP-based Uncertainty Modal Modeling (UMM) Framework for Pedestrian Re-Identification in Autonomous Driving","abstract":"Re-Identification (ReID) is a critical technology in intelligent perception systems, especially within autonomous driving, where onboard cameras must identify pedestrians across views and time in real-time to support safe navigation and trajectory prediction. However, the presence of uncertain or missing input modalities--such as RGB, infrared, sketches, or textual descriptions--poses significant challenges to conventional ReID approaches. While large-scale pre-trained models offer strong multimodal semantic modeling capabilities, their computational overhead limits practical deployment in resource-constrained environments. To address these challenges, we propose a lightweight Uncertainty Modal Modeling (UMM) framework, which integrates a multimodal token mapper, synthetic modality augmentation strategy, and cross-modal cue interactive learner. Together, these components enable unified feature representation, mitigate the impact of missing modalities, and extract complementary information across different data types. Additionally, UMM leverages CLIP's vision-language alignment ability to fuse multimodal inputs efficiently without extensive finetuning. Experimental results demonstrate that UMM achieves strong robustness, generalization, and computational efficiency under uncertain modality conditions, offering a scalable and practical solution for pedestrian re-identification in autonomous driving scenarios.","short_abstract":"Re-Identification (ReID) is a critical technology in intelligent perception systems, especially within autonomous driving, where onboard cameras must identify pedestrians across views and time in real-time to support safe navigation and trajectory prediction. However, the presence of uncertain or missing input modaliti...","url_abs":"https://arxiv.org/abs/2508.11218","url_pdf":"https://arxiv.org/pdf/2508.11218v1","authors":"[\"Jialin Li\",\"Shuqi Wu\",\"Ning Wang\"]","published":"2025-08-15T04:50:27Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.LG\"]","methods":"[]","has_code":false}