{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T19:58:48Z","timestamp":1790279928175,"version":"4.1.0"},"publisher-location":"Cham","reference-count":58,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032369833","type":"print"},{"value":"9783032369840","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-36984-0_31","type":"book-chapter","created":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T19:01:54Z","timestamp":1790276514000},"page":"567-584","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Incentive Noise and\u00a0Structural Prior Infusion for\u00a0Multi-modal Object Re-Identification"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-8625-5720","authenticated-orcid":false,"given":"Weixiang","family":"Zhou","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-7906-0329","authenticated-orcid":false,"given":"Yuhao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-8286-7367","authenticated-orcid":false,"given":"Xingguo","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-3624-0318","authenticated-orcid":false,"given":"Weizhen","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6093-8266","authenticated-orcid":false,"given":"Zhixun","family":"Su","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0304-9507","authenticated-orcid":false,"given":"Jinshan","family":"Pan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6068-0103","authenticated-orcid":false,"given":"Cong","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,25]]},"reference":[{"key":"31_CR1","unstructured":"Crawford, J., Yin, H., McDermott, L., Cummings, D.: UniCat: crafting a stronger fusion baseline for multimodal re-identification. arXiv:2310.18812 (2023)"},{"key":"31_CR2","doi-asserted-by":"crossref","unstructured":"Dong, W., Yang, X., Cheng, D., Wang, N., Gao, X.: Escaping modal interactions: an efficient desanet for multi-modal object re-identification. TIP (2025)","DOI":"10.1109\/TIP.2025.3592575"},{"key":"31_CR3","unstructured":"Dosovitskiy, A., et al.: An image is worth 16$$\\times $$16 words: transformers for image recognition at scale. arXiv:2010.11929 (2020)"},{"key":"31_CR4","doi-asserted-by":"crossref","unstructured":"Feng, Y., Li, J., Hu, J., Zhang, Y., Tan, L., Ji, J.: MDReID: modality-decoupled learning for any-to-any multi-modal object re-identification. In: NeurIPS (2025)","DOI":"10.52202\/085713-1418"},{"key":"31_CR5","unstructured":"Feng, Y., Li, J., Xie, C., Tan, L., Ji, J.: Multi-modal object re-identification via sparse mixture-of-experts. In: ICML (2025)"},{"key":"31_CR6","unstructured":"Gao, Y., Li, S., Liu, Z., Zheng, A., Li, C., Tang, J.: Chain-of-thought guided multi-modal object re-identification. In: CVPR (2026)"},{"key":"31_CR7","doi-asserted-by":"crossref","unstructured":"Guo, J., Zhang, X., Liu, Z., Wang, Y.: Generative and attentive fusion for multi-spectral vehicle re-identification. In: ICSP (2022)","DOI":"10.1109\/ICSP54964.2022.9778769"},{"key":"31_CR8","doi-asserted-by":"crossref","unstructured":"He, Q., Lu, Z., Wang, Z., Hu, H.: Graph-based progressive fusion network for multi-modality vehicle re-identification. T-ITS (2023)","DOI":"10.1109\/TITS.2023.3285758"},{"key":"31_CR9","doi-asserted-by":"crossref","unstructured":"He, S., Luo, H., Wang, P., Wang, F., Li, H., Jiang, W.: TransReID: transformer-based object re-identification. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01474"},{"key":"31_CR10","unstructured":"Hermans, A., Beyer, L., Leibe, B.: defense of the triplet loss for person re-identification. arXiv:1703.07737 (2017)"},{"key":"31_CR11","doi-asserted-by":"crossref","unstructured":"Huang, S., Zhang, H., Li, X.: Enhance vision-language alignment with noise. In: AAAI (2025)","DOI":"10.1609\/aaai.v39i16.33918"},{"key":"31_CR12","doi-asserted-by":"crossref","unstructured":"Jiang, K., Shi, Z., Zhang, D., Zhang, H., Li, X.: Mixture of noise for pre-trained model-based class-incremental learning. arXiv preprint arXiv:2509.16738 (2025)","DOI":"10.52202\/085713-1491"},{"key":"31_CR13","doi-asserted-by":"crossref","unstructured":"Li, H., Li, C., Zhu, X., Zheng, A., Luo, B.: Multi-spectral vehicle re-identification: a challenge. In: AAAI (2020)","DOI":"10.1609\/aaai.v34i07.6796"},{"key":"31_CR14","doi-asserted-by":"crossref","unstructured":"Li, H., Liu, G., Wang, X., Liang, B., Luo, Y.: PEFT-BoA: parameter-efficient fine-tuning with bag-of-adapters for multi-modal object re-identification. In: AAAI (2026)","DOI":"10.1609\/aaai.v40i8.37537"},{"key":"31_CR15","doi-asserted-by":"crossref","unstructured":"Li, S., Li, C., Zheng, A., Lu, A., Tang, J., Ma, J.: Next: multi-grained mixture of experts via text-modulation for multi-modal object Re-ID. arXiv:2505.20001 (2025)","DOI":"10.1109\/TIFS.2026.3729508"},{"key":"31_CR16","doi-asserted-by":"crossref","unstructured":"Li, S., Li, C., Zheng, A., Tang, J., Luo, B.: ICPL-ReID: identity-conditional prompt learning for multi-spectral object re-identification. arXiv:2505.17821 (2025)","DOI":"10.1109\/TMM.2025.3623556"},{"key":"31_CR17","doi-asserted-by":"crossref","unstructured":"Li, S., Leng, J., Gan, J., Mo, M., Gao, X.: Shape-centered representation learning for visible-infrared person re-identification. Pattern Recognit. (2025)","DOI":"10.1016\/j.patcog.2025.111756"},{"key":"31_CR18","doi-asserted-by":"crossref","unstructured":"Li, S., Leng, J., Kuang, C., Tan, M., Gao, X.: Video-level language-driven video-based visible-infrared person re-identification. TIFS (2025)","DOI":"10.1109\/TIFS.2025.3573672"},{"key":"31_CR19","doi-asserted-by":"crossref","unstructured":"Li, S., Leng, J., Kuang, C., Tan, M., Yuan, Y., Gao, X.: Causal bootstrapped alignment for unsupervised video-based visible-infrared person re-identification. arXiv:2604.15631 (2026)","DOI":"10.1109\/TIFS.2026.3707442"},{"key":"31_CR20","unstructured":"Li, X.: Positive-incentive noise. TNNLS (2022)"},{"key":"31_CR21","doi-asserted-by":"crossref","unstructured":"Lin, M., et al.: DMPT: decoupled modality-aware prompt tuning for multi-modal object re-identification. In: WACV (2025)","DOI":"10.1109\/WACV61041.2025.00211"},{"key":"31_CR22","unstructured":"Liu, Y., Wang, Y., Zhang, P.: Signal: selective interaction and global-local alignment for multi-modal object re-identification. arXiv:2511.17965 (2025)"},{"key":"31_CR23","doi-asserted-by":"crossref","unstructured":"Liu, Y., Wang, Y., Zhang, P.: Signal: selective interaction and global-local alignment for multi-modal object re-identification. In: AAAI (2026)","DOI":"10.1609\/aaai.v40i9.37674"},{"key":"31_CR24","unstructured":"Van\u00a0der Maaten, L., Hinton, G.: Visualizing data using t-SNE. JMLR (2008)"},{"key":"31_CR25","doi-asserted-by":"crossref","unstructured":"Pan, W., Huang, L., Liang, J., Hong, L., Zhu, J.: Progressively hybrid transformer for multi-modal vehicle re-identification. Sensors (2023)","DOI":"10.3390\/s23094206"},{"key":"31_CR26","doi-asserted-by":"crossref","unstructured":"Qiu, Z., et\u00a0al.: Gated attention for large language models: non-linearity, sparsity, and attention-sink-free. arXiv:2505.06708 (2025)","DOI":"10.52202\/085713-3345"},{"key":"31_CR27","doi-asserted-by":"crossref","unstructured":"Radenovi\u0107, F., Tolias, G., Chum, O.: Fine-tuning CNN image retrieval with no human annotation. TPAMI (2018)","DOI":"10.1109\/TPAMI.2018.2846566"},{"key":"31_CR28","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: ICML (2021)"},{"key":"31_CR29","doi-asserted-by":"crossref","unstructured":"Rao, Y., Chen, G., Lu, J., Zhou, J.: Counterfactual attention learning for fine-grained visual categorization and re-identification. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00106"},{"key":"31_CR30","unstructured":"Shazeer, N., et al.: Outrageously large neural networks: the sparsely-gated mixture-of-experts layer. arXiv:1701.06538 (2017)"},{"key":"31_CR31","unstructured":"Sim\u00e9oni, O., et\u00a0al.: DINOv3. arXiv:2508.10104 (2025)"},{"key":"31_CR32","doi-asserted-by":"crossref","unstructured":"Somers, V., Alahi, A., Vleeschouwer, C.D.: Keypoint promptable re-identification. In: ECCV (2024)","DOI":"10.1007\/978-3-031-72986-7_13"},{"key":"31_CR33","doi-asserted-by":"crossref","unstructured":"Sun, Y., Zheng, L., Yang, Y., Tian, Q., Wang, S.: Beyond part models: person retrieval with refined part pooling (and a strong convolutional baseline). In: ECCV (2018)","DOI":"10.1007\/978-3-030-01225-0_30"},{"key":"31_CR34","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.308"},{"key":"31_CR35","doi-asserted-by":"crossref","unstructured":"Wan, X., Zheng, A., Wang, Z., Jiang, B., Tang, J., Ma, J.: Reliable multi-modal object re-identification via modality-aware graph reasoning. arXiv:2504.14847 (2025)","DOI":"10.1109\/TIFS.2026.3696569"},{"key":"31_CR36","doi-asserted-by":"crossref","unstructured":"Wan, X., Zheng, A., Wang, Z., Jiang, B., Tang, J., Ma, J.: Reliable multi-modal object re-identification via modality-aware graph reasoning. TIFS (2026)","DOI":"10.1109\/TIFS.2026.3696569"},{"key":"31_CR37","doi-asserted-by":"crossref","unstructured":"Wang, Y., et al.: MambaPro: multi-modal object re-identification with mamba aggregation and synergistic prompt. In: AAAI (2025)","DOI":"10.1609\/aaai.v39i8.32879"},{"key":"31_CR38","doi-asserted-by":"crossref","unstructured":"Wang, Y., Liu, X., Zhang, P., Lu, H., Tu, Z., Lu, H.: Top-ReID: multi-spectral object re-identification with token permutation. In: AAAI (2024)","DOI":"10.1609\/aaai.v38i6.28388"},{"key":"31_CR39","doi-asserted-by":"crossref","unstructured":"Wang, Y., Liu, Y., Zheng, A., Zhang, P.: Decoupled feature-based mixture of experts for multi-modal object re-identification. In: AAAI (2025)","DOI":"10.1609\/aaai.v39i8.32878"},{"key":"31_CR40","doi-asserted-by":"crossref","unstructured":"Wang, Y., Lv, Y., Zhang, P., Lu, H.: IDEA: inverted text with cooperative deformable aggregation for multi-modal object re-identification. In: CVPR (2025)","DOI":"10.1109\/CVPR52734.2025.02765"},{"key":"31_CR41","doi-asserted-by":"crossref","unstructured":"Wang, Z., Huang, H., Zheng, A., He, R.: Heterogeneous test-time training for multi-modal person re-identification. In: AAAI (2024)","DOI":"10.1609\/aaai.v38i6.28398"},{"key":"31_CR42","doi-asserted-by":"crossref","unstructured":"Wang, Z., Li, C., Zheng, A., He, R., Tang, J.: Interact, embed, and enlarge: boosting modality-specific representations for multi-modal person re-identification. In: AAAI (2022)","DOI":"10.1609\/aaai.v36i3.20165"},{"key":"31_CR43","doi-asserted-by":"crossref","unstructured":"Wu, D., Liu, Z., Chen, Z., Gan, S., Tan, K., Wan, Q., Wang, Y.: LRMM: Low rank multi-scale multi-modal fusion for person re-identification based on RGB-NI-TI. ESWA (2025)","DOI":"10.1016\/j.eswa.2024.125716"},{"key":"31_CR44","doi-asserted-by":"crossref","unstructured":"Xu, X., et al.: STMI: segmentation-guided token modulation with cross-modal hypergraph interaction for multi-modal object re-identification. In: AAAI (2026)","DOI":"10.1609\/aaai.v40i14.38125"},{"key":"31_CR45","doi-asserted-by":"crossref","unstructured":"Yang, Y., Li, S., Ye, J., Dong, N., Li, F., Li, H.: DINOv2 driven gait representation learning for video-based visible-infrared person re-identification. In: ACM MM (2025)","DOI":"10.1145\/3746027.3755413"},{"key":"31_CR46","unstructured":"Yin, H., Li, J., Schiller, E., McDermott, L., Cummings, D.: GraFT: gradual fusion transformer for multimodal re-identification. arXiv:2310.16856 (2023)"},{"key":"31_CR47","unstructured":"Yu, Z., et al.: Representation selective coupling via token sparsification for multi-spectral object re-identification. TCSVT (2024)"},{"key":"31_CR48","doi-asserted-by":"crossref","unstructured":"Yu, Z., Huang, Z., Hou, M., Yan, Y., Liu, Y.: WTSF-ReID: depth-driven window-oriented token selection and fusion for multi-modality vehicle re-identification with knowledge consistency constraint. ESWA (2025)","DOI":"10.1016\/j.eswa.2025.126921"},{"key":"31_CR49","doi-asserted-by":"crossref","unstructured":"Zhang, H., Huang, S., Guo, Y., Li, X.: Variational positive-incentive noise: how noise benefits models. TPAMI (2025)","DOI":"10.1109\/TPAMI.2025.3575295"},{"key":"31_CR50","doi-asserted-by":"crossref","unstructured":"Zhang, P., Wang, Y., Liu, Y., Tu, Z., Lu, H.: Magic tokens: select diverse tokens for multi-modal object re-identification. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.01620"},{"key":"31_CR51","doi-asserted-by":"crossref","unstructured":"Zhang, S., et al.: Prompt-based modality alignment for effective multi-modal object re-identification. TIP (2025)","DOI":"10.1109\/TIP.2025.3556531"},{"key":"31_CR52","doi-asserted-by":"crossref","unstructured":"Zheng, A., He, Z., Wang, Z., Li, C., Tang, J.: Dynamic enhancement network for partial multi-modality person re-identification. arXiv:2305.15762 (2023)","DOI":"10.3724\/SP.J.1089.2023.19280"},{"key":"31_CR53","doi-asserted-by":"crossref","unstructured":"Zheng, A., Ma, Z., Sun, Y., Wang, Z., Li, C., Tang, J.: Flare-aware cross-modal enhancement network for multi-spectral vehicle re-identification. Inf. Fusion (2025)","DOI":"10.1016\/j.inffus.2024.102800"},{"key":"31_CR54","doi-asserted-by":"crossref","unstructured":"Zheng, A., Wang, Z., Chen, Z., Li, C., Tang, J.: Robust multi-modality person re-identification. In: AAAI (2021)","DOI":"10.1609\/aaai.v35i4.16467"},{"key":"31_CR55","doi-asserted-by":"crossref","unstructured":"Zheng, A., Zhu, X., Ma, Z., Li, C., Tang, J., Ma, J.: Cross-directional consistency network with adaptive layer normalization for multi-spectral vehicle re-identification and a high-quality benchmark. Inf. Fusion (2023)","DOI":"10.1016\/j.inffus.2023.101901"},{"key":"31_CR56","doi-asserted-by":"crossref","unstructured":"Zhong, Z., Zheng, L., Kang, G., Li, S., Yang, Y.: Random erasing data augmentation. In: AAAI (2020)","DOI":"10.1609\/aaai.v34i07.7000"},{"key":"31_CR57","doi-asserted-by":"crossref","unstructured":"Zhou, K., Yang, Y., Cavallaro, A., Xiang, T.: Omni-scale feature learning for person re-identification. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00380"},{"key":"31_CR58","doi-asserted-by":"crossref","unstructured":"Zhu, K., Guo, H., Liu, Z., Tang, M., Wang, J.: Identity-guided human semantic parsing for person re-identification. In: ECCV (2020)","DOI":"10.1007\/978-3-030-58580-8_21"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-36984-0_31","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T19:02:16Z","timestamp":1790276536000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-36984-0_31"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032369833","9783032369840"],"references-count":58,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-36984-0_31","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"25 September 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Malm\u00f6","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sweden","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}