{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:40:43Z","timestamp":1776886843017,"version":"3.51.2"},"reference-count":46,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100014013","name":"UK Research and Innovation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100014013","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1109\/ijcnn64981.2025.11229333","type":"proceedings-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T18:46:15Z","timestamp":1763145975000},"page":"1-10","source":"Crossref","is-referenced-by-count":2,"title":["Position Paper: Towards a Unified Representation Evaluation Framework Beyond Downstream Tasks"],"prefix":"10.1109","author":[{"given":"Christos","family":"Plachouras","sequence":"first","affiliation":[{"name":"Queen Mary University of London,School of Electronic Engineering and Computer Science,London,UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Julien","family":"Guinot","sequence":"additional","affiliation":[{"name":"Queen Mary University of London,School of Electronic Engineering and Computer Science,London,UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gy\u00f6rgy","family":"Fazekas","sequence":"additional","affiliation":[{"name":"Queen Mary University of London,School of Electronic Engineering and Computer Science,London,UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Elio","family":"Quinton","sequence":"additional","affiliation":[{"name":"Universal Music Group,Music & Audio Machine Learning Lab,London,UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Emmanouil","family":"Benetos","sequence":"additional","affiliation":[{"name":"Queen Mary University of London,School of Electronic Engineering and Computer Science,London,UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Johan","family":"Pauwels","sequence":"additional","affiliation":[{"name":"Queen Mary University of London,School of Electronic Engineering and Computer Science,London,UK"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3497510"},{"key":"ref2","article-title":"Masked autoencoders that listen","volume":"35","author":"Huang","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref3","article-title":"Self-Supervised Learning of Split Invariant Equivariant Representations","volume-title":"40th Int. Conf. on Machine Learning","author":"Garrido"},{"key":"ref4","article-title":"EquiMod: An Equivariance Module to Improve Visual Instance Discrimination","volume-title":"Int. Conf. on Learning Representations","author":"Devillers"},{"key":"ref5","article-title":"What Should Not Be Contrastive in Contrastive Learning","volume-title":"Int. Conf. on Learning Representations","author":"Xiao"},{"key":"ref6","article-title":"The Platonic Representation Hypothesis","volume-title":"41st Int. Conf. on Machine Learning","author":"Huh"},{"issue":"2","key":"ref7","article-title":"A Systematic Evaluation of Shallow Convolutional Neural Network on CIFAR Dataset","volume":"46","author":"Rachmadi","year":"2019","journal-title":"IAENG Int. Journal of Computer Science"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2211477"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s11229-023-04334-9"},{"key":"ref10","article-title":"Evaluating Disentangled Representations","author":"Sepliarskaia","year":"2019"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.108418"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-71704-9_65"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/DSAA.2018.00018"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref15","article-title":"Improving Language Understanding by Generative Pre-Training","author":"Radford","year":"2018","journal-title":"OpenAI Technical Report"},{"key":"ref16","article-title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"Journal of Machine Learning Research"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01499"},{"key":"ref19","article-title":"A Simple Framework For Contrastive Learning of Visual Representations","volume-title":"Int. Conf. on Machine Learning","author":"Chen"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref22","article-title":"wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations","volume":"33","author":"Baevski","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref23","article-title":"Auto-Encoding Variational Bayes","volume-title":"Int. Conf. on Learning Representations","author":"Kingma"},{"key":"ref24","article-title":"Denoising Diffusion Probabilistic Models","volume":"33","author":"Ho","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1775"},{"key":"ref26","article-title":"HEAR: Holistic Evaluation of Audio Representations","volume-title":"NeurIPS 2021 Competitions and Demonstrations Track","author":"Turian"},{"key":"ref27","article-title":"A Large-Scale Study of Representation Learning with the Visual Task Adaptation Benchmark","volume-title":"Int. Conf. on Learning Representations","author":"Zhai"},{"key":"ref28","article-title":"mir ref: A Representation Evaluation Framework for Music Information Retrieval Tasks","volume-title":"37th Conf. on Neural Information Processing Systems, Machine Learning for Audio Workshop","author":"Plachouras"},{"key":"ref29","article-title":"Group Equivariant Convolutional Networks","volume-title":"Int. Conf. on Machine Learning","author":"Cohen"},{"key":"ref30","article-title":"Color equivariant convolutional networks","volume":"36","author":"Lengyel","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref31","article-title":"Equivariant Contrastive Learning","volume-title":"Int. Conf. on Learning Representations","author":"Dangovski"},{"key":"ref32","article-title":"Theory and Evaluation Metrics for Learning Disentangled Representations","volume-title":"Int. Conf. on Learning Representations","author":"Do"},{"key":"ref33","article-title":"A Framework for the Quantitative Evaluation of Disentangled Representations","volume-title":"Int. Conf. on Learning Representations","author":"Eastwood"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref35","article-title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","volume-title":"Int. Conf. on Learning Representations","author":"Dosovitskiy"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref37","article-title":"DINOv2: Learning Robust Visual Features without Supervision","author":"Oquab","year":"2024","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref38","article-title":"Learning Transferable Visual Models From Natural Language Supervision","volume-title":"Int. Conf. on Machine Learning","author":"Radford"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3389636"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095889"},{"key":"ref41","article-title":"Robust Speech Recognition via Large-Scale Weak Supervision","volume-title":"Int. Conf. on Machine Learning","author":"Radford"},{"key":"ref42","article-title":"UniSpeech: Unified Speech Representation Learning with Labeled and Unlabeled Data","volume-title":"Int. Conf. on Machine Learning","author":"Wang"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref44","article-title":"iver56\/audiomentations: v0.38.0","author":"Jordal","year":"2024"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"}],"event":{"name":"2025 International Joint Conference on Neural Networks (IJCNN)","location":"Rome, Italy","start":{"date-parts":[[2025,6,30]]},"end":{"date-parts":[[2025,7,5]]}},"container-title":["2025 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11227166\/11227148\/11229333.pdf?arnumber=11229333","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:17:54Z","timestamp":1763191074000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11229333\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/ijcnn64981.2025.11229333","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}