{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T08:44:48Z","timestamp":1769849088858,"version":"3.49.0"},"reference-count":41,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,9,18]],"date-time":"2024-09-18T00:00:00Z","timestamp":1726617600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,9,18]],"date-time":"2024-09-18T00:00:00Z","timestamp":1726617600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,9,18]]},"DOI":"10.1109\/rtsi61910.2024.10761839","type":"proceedings-article","created":{"date-parts":[[2024,11,26]],"date-time":"2024-11-26T18:45:38Z","timestamp":1732646738000},"page":"97-102","source":"Crossref","is-referenced-by-count":1,"title":["Exploring Fine-Grained Retail Product Discrimination with Zero-Shot Object Classification Using Vision-Language Models"],"prefix":"10.1109","author":[{"given":"Anil Osman","family":"Tur","sequence":"first","affiliation":[{"name":"University of Trento,DISI,Trento,Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alessandro","family":"Conti","sequence":"additional","affiliation":[{"name":"University of Trento,DISI,Trento,Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cigdem","family":"Beyan","sequence":"additional","affiliation":[{"name":"University of Verona,Dep. of Computer Science,Verona,Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Davide","family":"Boscaini","sequence":"additional","affiliation":[{"name":"Technologies of Vision, Fondazione Bruno Kessler,Trento,Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Roberto","family":"Larcher","sequence":"additional","affiliation":[{"name":"Spindox Labs, Spindox SpA,Trento,Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stefano","family":"Messelodi","sequence":"additional","affiliation":[{"name":"Technologies of Vision, Fondazione Bruno Kessler,Trento,Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fabio","family":"Poiesi","sequence":"additional","affiliation":[{"name":"Technologies of Vision, Fondazione Bruno Kessler,Trento,Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Elisa","family":"Ricci","sequence":"additional","affiliation":[{"name":"University of Trento, Fondazione Bruno Kessler,Trento,Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Share & trends analysis report by solution","volume":"2030","author":"Size","year":"2023","journal-title":"By Technol-ogy (Deep Learning, Machine Learning), By End-use, By Region, And Segment Forecasts"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICIRCA.2018.8597403"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.3390\/app13052871"},{"key":"ref4","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"ICML","author":"Radford","year":"2021"},{"key":"ref5","first-page":"12888","article-title":"Blip: Bootstrapping language-image pretraining for unified vision-language understanding and generation","author":"Li","year":"2022","journal-title":"ICML"},{"key":"ref6","article-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2023","journal-title":"arXiv preprint:2304.07193"},{"key":"ref7","article-title":"Retailklip: Finetuning openclip backbone using metric learning on a single gpu for zero-shot retail product image classification","author":"Srivastava","year":"2023","journal-title":"arXiv preprint"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ASYU56188.2022.9925453"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1002\/tee.23051"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCE56470.2023.10043466"},{"key":"ref11","first-page":"19730","article-title":"Blip-2: Bootstrapping language-image pretraining with frozen image encoders and large language models","author":"Li","year":"2023","journal-title":"ICML"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/5326.661099"},{"key":"ref13","first-page":"645","article-title":"Pattern recognition and machine learning","volume":"2","author":"Bishop","year":"2006","journal-title":"Springer google schola"},{"key":"ref14","journal-title":"MIMEX Micro Market Experience"},{"key":"ref15","first-page":"18583","article-title":"Measuring robustness to natural distribution shifts in image classification","volume":"33","author":"Taori","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.23915\/distill.00030"},{"key":"ref17","article-title":"Simvlm: Simple visual language model pretraining with weak supervision","author":"Wang","year":"2022","journal-title":"ICLR"},{"key":"ref18","article-title":"Multi-grained vision language pretraining: Aligning texts with visual concepts","author":"Zeng","year":"2022","journal-title":"ICML"},{"key":"ref19","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","author":"Li","year":"2021","journal-title":"NeurIPS"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01519"},{"key":"ref21","article-title":"LAION-5b: An open large-scale dataset for training next generation image-text models","volume-title":"Thirty-sixth Conference on Neural Information Processing Systems Datasets and Benchmarks Track","author":"Schuhmann"},{"key":"ref22","author":"Ilharco","year":"2021","journal-title":"Open CLIP. Zenodo"},{"key":"ref23","article-title":"Open-vocabulary object detection via vision and language knowledge distillation","author":"Gu","year":"2021","journal-title":"ICLR"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19818-2_42"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_40"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01755"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01629"},{"key":"ref29","article-title":"Marinedet: Towards open-marine object detection","author":"Haixin","year":"2023","journal-title":"arXiv preprint"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01857"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00271"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1155\/2020\/8875910"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICPECA56706.2023.10075978"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/s521-001-8051-z"},{"key":"ref39","article-title":"Opt: Open pretrained transformer language models","volume-title":"arXiv preprint","author":"Zhang","year":"2022"},{"key":"ref40","article-title":"Imagenet-21k pretraining for the masses","author":"Ridnik","year":"2021","journal-title":"arXiv preprint"},{"key":"ref41","article-title":"Umap: Uniform manifold approximation and projection for dimension reduction","author":"McInnes","year":"2018","journal-title":"arXiv preprint"}],"event":{"name":"2024 IEEE 8th Forum on Research and Technologies for Society and Industry Innovation (RTSI)","location":"Milano, Italy","start":{"date-parts":[[2024,9,18]]},"end":{"date-parts":[[2024,9,20]]}},"container-title":["2024 IEEE 8th Forum on Research and Technologies for Society and Industry Innovation (RTSI)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10761112\/10761063\/10761839.pdf?arnumber=10761839","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T19:17:50Z","timestamp":1732735070000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10761839\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,18]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/rtsi61910.2024.10761839","relation":{},"subject":[],"published":{"date-parts":[[2024,9,18]]}}}