{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T14:28:39Z","timestamp":1785421719300,"version":"3.56.0"},"reference-count":35,"publisher":"MDPI AG","issue":"13","license":[{"start":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T00:00:00Z","timestamp":1783382400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"The National Natural Science Foundation of China under Grant","award":["62502349"],"award-info":[{"award-number":["62502349"]}]},{"award":["62502349"],"award-info":[{"award-number":["62502349"]}],"id":[{"id":"https:\/\/ror.org\/01h0zpd94","id-type":"ROR","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Existing image\u2013text retrieval methods often compute cross-modal similarity using global single-vector representations. Although efficient for coarse semantic alignment, such compressed representations are limited when textual queries involve fine-grained semantics, including objects, attributes, relations, and their compositional structures. This paper focuses on fine-grained text-to-image retrieval and proposes Q-GrAM, a retrieval-oriented adaptation of the BLIP-2 Q-Former. Instead of treating Q-Former queries as a homogeneous set, Q-GrAM partitions a fixed query budget into semantically differentiated groups. A text-guided router assigns token-level semantic demands to query groups, while query conditional initialization modulates each group according to group-level textual summaries. The resulting grouped visual query features are matched with text tokens through a group-aware late interaction scorer, and auxiliary routing balance and inter-group diversity regularization are introduced to stabilize semantic specialization. Experiments on MS-COCO 5K, Flickr30K, and Flickr30K-CFQ show that Q-GrAM achieves strong text-to-image retrieval performance against both global embedding baselines and representative fine-grained image\u2013text matching methods, while maintaining competitive bidirectional retrieval performance. These results demonstrate the effectiveness of structured, text-conditioned Q-Former query specialization for fine-grained text-driven image search.<\/jats:p>","DOI":"10.3390\/s26134313","type":"journal-article","created":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T16:16:18Z","timestamp":1783527378000},"page":"4313","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Q-GrAM: Fine-Grained Image\u2013Text Retrieval via Grouped Query Routing and Conditional Query Modulation"],"prefix":"10.3390","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-2456-7629","authenticated-orcid":false,"given":"Guihe","family":"Gu","sequence":"first","affiliation":[{"name":"School of Computer Science, Wuhan University, Wuhan 430072, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-1798-9934","authenticated-orcid":false,"given":"Huawei","family":"Li","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Wuhan University, Wuhan 430072, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7220-5246","authenticated-orcid":false,"given":"Hong","family":"Qin","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Wuhan University, Wuhan 430072, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,7,7]]},"reference":[{"key":"ref_1","unstructured":"Yao, L., Huang, R., Hou, L., Lu, G., Niu, M., Xu, H., Liang, X., Li, Z., Jiang, X., and Xu, C. (2022, January 25\u201329). FILIP: Fine-grained Interactive Language-Image Pre-Training. Proceedings of the International Conference on Learning Representations, Virtual."},{"key":"ref_2","first-page":"3974","article-title":"Improving fine-grained understanding in image-text pre-training","volume":"Volume 235","author":"Bica","year":"2024","journal-title":"Proceedings of the International Conference on Machine Learning, Vienna, Austria, 21\u201327 July 2024"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Gu, G., Xue, Y., Wu, Z., Song, L., and Liang, C. (2025). InstructSee: Instruction-Aware and Feedback-Driven Multimodal Retrieval with Dynamic Query Generation. Sensors, 25.","DOI":"10.3390\/s25165195"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Zhu, H., Huang, J.H., Rudinac, S., and Kanoulas, E. (2024). Enhancing Interactive Image Retrieval with Query Rewriting Using Large Language Models and Vision Language Models. Proceedings of the International Conference on Multimedia Retrieval, Phuket, Thailand, 10\u201314 June 2024, ACM.","DOI":"10.1145\/3652583.3658032"},{"key":"ref_5","first-page":"387","article-title":"TalkSee: Interactive Video Retrieval Engine Using Large Language Model","volume":"Volume 14557","author":"Gu","year":"2024","journal-title":"Proceedings of the 30th International Conference on Multimedia Modeling, Amsterdam, The Netherlands, 29 January\u20132 February 2024"},{"key":"ref_6","first-page":"302","article-title":"Interactive Video Search with Multi-modal LLM Video Captioning","volume":"Volume 15524","author":"Cheng","year":"2025","journal-title":"Proceedings of the 31st International Conference on Multimedia Modeling, Nara, Japan, 8\u201310 January 2025"},{"key":"ref_7","first-page":"380","article-title":"Leveraging LLMs and Generative Models for Interactive Known-Item Video Search","volume":"Volume 14557","author":"Ma","year":"2024","journal-title":"Proceedings of the 30th International Conference on Multimedia Modeling, Amsterdam, The Netherlands, 29 January\u20132 February 2024"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Khattab, O., and Zaharia, M. (2020). ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over bert. Proceedings of the International ACM SIGIR Conference on Research and Development in Information Retrieval, Virtual, 25\u201330 July 2020, ACM.","DOI":"10.1145\/3397271.3401075"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Pan, Z., Wu, F., and Zhang, B. (2023, January 18\u201322). Fine-grained image-text matching by cross-modal hard aligning network. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Vancouver, BC, Canada.","DOI":"10.1109\/CVPR52729.2023.01847"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Fu, Z., Mao, Z., Song, Y., and Zhang, Y. (2023, January 18\u201322). Learning Semantic Relationship Among Instances for Image-Text Matching. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Vancouver, BC, Canada.","DOI":"10.1109\/CVPR52729.2023.01455"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Pham, K., Huynh, C., Lim, S.N., and Shrivastava, A. (2024). Composing Object Relations and Attributes for Image-Text Matching. arXiv.","DOI":"10.1109\/CVPR52733.2024.01361"},{"key":"ref_12","first-page":"19730","article-title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","volume":"Volume 202","author":"Li","year":"2023","journal-title":"Proceedings of the International Conference on Machine Learning, Honolulu, HI, USA, 23\u201329 July 2023"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Dai, W., Li, J., Li, D., Tiong, A.M.H., Zhao, J., Wang, W., Li, B., Fung, P., and Hoi, S.C.H. (2023, January 10\u201316). InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning. Proceedings of the Advances in Neural Information Processing Systems, New Orleans, LA, USA.","DOI":"10.52202\/075280-2142"},{"key":"ref_14","first-page":"8748","article-title":"Learning Transferable Visual Models from Natural Language Supervision","volume":"Volume 139","author":"Radford","year":"2021","journal-title":"Proceedings of the International Conference on Machine Learning, Virtual, 18\u201324 July 2021"},{"key":"ref_15","unstructured":"Jia, C., Yang, Y., Xia, Y., Chen, Y.T., Parekh, Z., Pham, H., Le, Q.V., Sung, Y., Li, Z., and Duerig, T. (2021, January 18\u201324). Scaling Up Visual and Vision-Language Representation Learning with Noisy Text Supervision. Proceedings of the International Conference on Machine Learning, Virtual."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Chen, Y.C., Li, L., Yu, L., El Kholy, A., Ahmed, F., Gan, Z., Cheng, Y., and Liu, J. (2020). UNITER: UNiversal Image-TExt Representation Learning. Proceedings of the European Conference on Computer Vision, Glasgow, UK, 23\u201328 August 2020, Springer.","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Li, X., Yin, X., Li, C., Zhang, P., Hu, X., Zhang, L., Wang, L., Hu, H., Dong, L., and Wei, F. (2020). Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks. Proceedings of the European Conference on Computer Vision, Glasgow, UK, 23\u201328 August 2020, Springer.","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"ref_18","unstructured":"Li, J., Selvaraju, R.R., Gotmare, A.D., Joty, S., Xiong, C., and Hoi, S. (2021). Align before Fuse: Vision and Language Representation Learning with Momentum Distillation. arXiv."},{"key":"ref_19","first-page":"12888","article-title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation","volume":"Volume 162","author":"Li","year":"2022","journal-title":"Proceedings of the International Conference on Machine Learning, Baltimore, MD, USA, 17\u201323 July 2022"},{"key":"ref_20","unstructured":"Lu, J., Batra, D., Parikh, D., and Lee, S. (2019, January 8\u201314). ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks. Proceedings of the Advances in Neural Information Processing Systems, Vancouver, BC, Canada."},{"key":"ref_21","first-page":"5583","article-title":"ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision","volume":"Volume 139","author":"Kim","year":"2021","journal-title":"Proceedings of the International Conference on Machine Learning, Virtual, 18\u201324 July 2021"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Zhai, X., Mustafa, B., Kolesnikov, A., and Beyer, L. (2023). Sigmoid Loss for Language Image Pre-Training. arXiv.","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Patashnik, O., Wu, Z., Shechtman, E., Cohen-Or, D., and Lischinski, D. (2021, January 11\u201317). Styleclip: Text-driven manipulation of stylegan imagery. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Montreal, QC, Canada.","DOI":"10.1109\/ICCV48922.2021.00209"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"4267","DOI":"10.52202\/079017-0139","article-title":"Clipceil: Domain generalization through clip via channel refinement and image-text alignment","volume":"37","author":"Yu","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Lee, K.H., Chen, X., Hua, G., Hu, H., and He, X. (2018). Stacked Cross Attention for Image-Text Matching. Proceedings of the European Conference on Computer Vision, Munich, Germany, 8\u201314 September 2018, Springer.","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Chen, H., Ding, G., Liu, X., Lin, Z., Liu, J., and Han, J. (2020, January 14\u201319). Imram: Iterative matching with recurrent attention memory for cross-modal image-text retrieval. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.01267"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Liu, C., Mao, Z., Liu, A.A., Zhang, T., Wang, B., and Zhang, Y. (2019). Focus Your Attention: A Bidirectional Focal Attention Network for Image-Text Matching. arXiv.","DOI":"10.1145\/3343031.3350869"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Diao, H., Zhang, Y., Ma, L., and Lu, H. (2021, January 2\u20139). Similarity reasoning and filtration for image-text matching. Proceedings of the AAAI Conference on Artificial Intelligence, Virtual.","DOI":"10.1609\/aaai.v35i2.16209"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Zhang, K., Mao, Z., Wang, Q., and Zhang, Y. (2022, January 18\u201324). Negative-aware attention framework for image-text matching. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA.","DOI":"10.1109\/CVPR52688.2022.01521"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Li, K., Zhang, Y., Li, K., Li, Y., and Fu, Y. (2019). Visual Semantic Reasoning for Image-Text Matching. arXiv.","DOI":"10.1109\/ICCV.2019.00475"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Wang, Z., Liu, X., Li, H., Sheng, L., Yan, J., Wang, X., and Shao, J. (2019). CAMP: Cross-Modal Adaptive Message Passing for Text-Image Retrieval. arXiv.","DOI":"10.1109\/ICCV.2019.00586"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Liu, C., Mao, Z., Zhang, T., Xie, H., Wang, B., and Zhang, Y. (2020). Graph Structured Network for Image-Text Matching. arXiv.","DOI":"10.1109\/CVPR42600.2020.01093"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Bi, Q., Yu, Q., Zheng, T., Zhu, W., Zhang, Y., Chen, Y., and Jiang, Y.G. (2023, January 1\u20136). VL-Match: Enhancing Vision-Language Pretraining with Token-Level and Instance-Level Matching. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Paris, France.","DOI":"10.1109\/ICCV51070.2023.00244"},{"key":"ref_34","first-page":"1","article-title":"Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity","volume":"23","author":"Fedus","year":"2022","journal-title":"J. Mach. Learn. Res."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Liu, H., Song, Y., Wang, X., Xiangru, Z., Li, Z., Song, W., and Li, T. (2024). Flickr30K-CFQ: A Compact and Fragmented Query Dataset for Text-image Retrieval. arXiv.","DOI":"10.1007\/978-981-97-5555-4_30"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/13\/4313\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T04:15:11Z","timestamp":1783656911000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/13\/4313"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,7]]},"references-count":35,"journal-issue":{"issue":"13","published-online":{"date-parts":[[2026,7]]}},"alternative-id":["s26134313"],"URL":"https:\/\/doi.org\/10.3390\/s26134313","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,7]]}}}