{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T08:38:23Z","timestamp":1771922303658,"version":"3.50.1"},"reference-count":41,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"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":[[2025,10,19]]},"DOI":"10.1109\/iccvw69036.2025.00419","type":"proceedings-article","created":{"date-parts":[[2026,2,23]],"date-time":"2026-02-23T20:44:02Z","timestamp":1771879442000},"page":"4032-4041","source":"Crossref","is-referenced-by-count":0,"title":["Probabilistic Dynamic Quantization for Memory Constrained Devices"],"prefix":"10.1109","author":[{"given":"Gabriele","family":"Santini","sequence":"first","affiliation":[{"name":"Fondazione Bruno Kessler"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Francesco","family":"Paissan","sequence":"additional","affiliation":[{"name":"Fondazione Bruno Kessler"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Elisabetta","family":"Farella","sequence":"additional","affiliation":[{"name":"Fondazione Bruno Kessler"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"22300","article-title":"Revisiting neural scaling laws in language and vision","volume":"35","author":"Ibrahim","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01556"},{"key":"ref3","article-title":"Efficient and effective methods for mixed precision neural network quantization for faster, energy-efficient inference","author":"Bablani","year":"2023","journal-title":"arXiv preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2311878121"},{"key":"ref5","article-title":"Token merging: Your vit but faster","author":"Bolya","year":"2022","journal-title":"ArXiv, abs\/2210.09461"},{"key":"ref6","article-title":"Flashattention-2: Faster attention with better parallelism and work partitioning","volume-title":"The Twelfth International Conference on Learning Representations","author":"Dao"},{"key":"ref7","first-page":"800","article-title":"Tensorflow lite micro: Embedded machine learning for tinyml systems","volume-title":"Proceedings of Machine Learning and Systems","volume":"3","author":"David"},{"key":"ref8","article-title":"Differentiable model compression via pseudo quantization noise","author":"Defossez","journal-title":"Transactions on Machine Learning Research"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00038"},{"key":"ref11","first-page":"18518","article-title":"Hawq-v2: Hessian aware trace-weighted quantization of neural networks","volume":"33","author":"Dong","year":"2020","journal-title":"Ad-vances in neural information processing systems"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref14","author":"Jocher","year":"2024","journal-title":"Ultralytics yolo11"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1806.08342"},{"key":"ref16","article-title":"Llm post-training: A deep dive into reasoning large language models","author":"Kumar","year":"2025","journal-title":"ar Xiv preprint"},{"key":"ref17","article-title":"Cmsisnn: Efficient neural network kernels for arm cortex-m cpus","author":"Lai","year":"2018","journal-title":"arXiv preprint"},{"key":"ref18","article-title":"Deep neural networks as gaussian processes","volume-title":"International Conference on Learning Representations","author":"Lee","year":"2018"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00052"},{"key":"ref20","first-page":"11711","article-title":"Mcunet: Tiny deep learning on iot devices","volume":"33","author":"Lin","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1405.0312"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01386"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413631"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01211"},{"key":"ref27","article-title":"A white paper on neural network quantization","author":"Nagel","year":"2021","journal-title":"Ar Xiv, abs\/2106.08295"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3510832"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-193"},{"key":"ref30","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref31","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"International Conference on Machine Learning","author":"Radford"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref34","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref36","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Neural Information Processing Systems"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2024.3409692"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00418"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1137\/1037125"},{"key":"ref40","article-title":"Coca: Contrastive captioners are image-text foundation models","author":"Yu","year":"2022","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref41","article-title":"Vision mamba: Efficient visual representation learning with bidirectional state space model","author":"Zhu","year":"2024","journal-title":"ArXiv, abs\/2401.09417"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision Workshops (ICCVW)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,20]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision Workshops (ICCVW)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11373940\/11374285\/11374540.pdf?arnumber=11374540","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T07:33:26Z","timestamp":1771918406000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11374540\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/iccvw69036.2025.00419","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}