{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:20:40Z","timestamp":1765308040063,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":54,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100002428","name":"Austrian Science Fund","doi-asserted-by":"publisher","award":["10.55776\/DFH37"],"award-info":[{"award-number":["10.55776\/DFH37"]}],"id":[{"id":"10.13039\/501100002428","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3758163","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T05:44:48Z","timestamp":1761371088000},"page":"12371-12380","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["A Matter of Time: Revealing the Structure of Time in Vision-Language Models"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-8679-4082","authenticated-orcid":false,"given":"Nidham","family":"Tekaya","sequence":"first","affiliation":[{"name":"St. P\u00f6lten University of Applied Sciences, St. P\u00f6lten, Austria and TU Wien, Vienna, Austria"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1387-5132","authenticated-orcid":false,"given":"Manuela","family":"Waldner","sequence":"additional","affiliation":[{"name":"TU Wien, Vienna, Austria"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0413-4746","authenticated-orcid":false,"given":"Matthias","family":"Zeppelzauer","sequence":"additional","affiliation":[{"name":"St. P\u00f6lten University of Applied Sciences, St. P\u00f6lten, Austria"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","unstructured":"A. Nicolson L. Schut J. A. Noble and Yarin Gal. 2024. Explaining explainability: understanding concept activation vectors. arXiv.org. doi:10.48550\/arxiv.2404.03713.","DOI":"10.48550\/arxiv.2404.03713"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.21203\/rs.3.rs-126052\/v1"},{"volume-title":"International Conference on Machine Learning.","author":"Alec","key":"e_1_3_2_1_3_1","unstructured":"Alec Radford et al. 2021. Learning transferable visual models from natural language supervision. International Conference on Machine Learning."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.48550\/arxiv.2310.06633"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-8396(99)00023-0"},{"key":"e_1_3_2_1_6_1","unstructured":"Xi Chen et al. 2023. Pali-3 vision language models: smaller faster stronger. arXiv preprint arXiv:2310.09199."},{"key":"e_1_3_2_1_7_1","unstructured":"Xi Chen et al. 2022. Pali: a jointly-scaled multilingual language-image model. arXiv preprint arXiv:2209.06794."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.48550\/arxiv.2408.14698"},{"key":"e_1_3_2_1_9_1","unstructured":"Christoph Schuhmann Richard Vencu Romain Beaumont R. Kaczmarczyk Clayton Mullis Aarush Katta Theo Coombes J. Jitsev and Aran Komatsuzaki. 2021. LAION-400m: open dataset of CLIP-filtered 400 million image-text pairs. arXiv.org."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"crossref","unstructured":"Duolikun Danier Mehmet Ayg\u00fcn Changjian Li Hakan Bilen and Oisin Mac Aodha. 2024. Depthcues: evaluating monocular depth perception in large vision models. arXiv preprint arXiv:2411.17385.","DOI":"10.1109\/CVPR52734.2025.01867"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14761"},{"key":"e_1_3_2_1_12_1","first-page":"9841","article-title":"GANSpace: discovering interpretable GAN controls","volume":"33","author":"H\u00e4rk\u00f6nen Erik","year":"2020","unstructured":"Erik H\u00e4rk\u00f6nen, Erik H\u00e4rk\u00f6nen, Aaron Hertzmann, Aaron Hertzmann, Jaakko Lehtinen, Jaakko Lehtinen, Sylvain Paris, and Sylvain Paris. 2020. GANSpace: discovering interpretable GAN controls. Neural Information Processing Systems, 33, 9841--9850.","journal-title":"Neural Information Processing Systems"},{"key":"e_1_3_2_1_13_1","volume-title":"Amit Jain, Ludwig Schmidt, Alexander Toshev, and Vaishaal Shankar.","author":"Fang Alex","year":"2023","unstructured":"Alex Fang, Albin Madappally Jose, Amit Jain, Ludwig Schmidt, Alexander Toshev, and Vaishaal Shankar. 2023. Data filtering networks. arXiv preprint arXiv:2309.17425."},{"key":"e_1_3_2_1_14_1","unstructured":"Wes Gurnee and Max Tegmark. 2023. Language models represent space and time. arXiv preprint arXiv:2310.02207."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"crossref","unstructured":"Benjamin Heinzerling and Kentaro Inui. 2024. Monotonic representation of numeric properties in language models. arXiv preprint arXiv:2403.10381.","DOI":"10.18653\/v1\/2024.acl-short.18"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.5143773"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/tvcg.2022.3209423"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","unstructured":"Jieneng Chen Qihang Yu Xiaohui Shen Alan L. Yuille and Liang-Chieh Chen. 2024. ViTamin: designing scalable vision models in the vision-language era. Computer Vision and Pattern Recognition. doi:10.1109\/cvpr52733.2024.01231.","DOI":"10.1109\/cvpr52733.2024.01231"},{"key":"e_1_3_2_1_19_1","first-page":"86","article-title":"Visualizing data using t-SNE","volume":"9","author":"van der Maaten Laurens","year":"2008","unstructured":"Laurens van der Maaten, Laurens van der Maaten, Geoffrey E. Hinton, and Geoffrey E. Hinton. 2008. Visualizing data using t-SNE. Journal of Machine Learning Research, 9, 86 (Jan. 1, 2008), 2579--2605.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_1_20_1","volume-title":"UMAP: uniform manifold approximation and projection for dimension reduction. arXiv: Machine Learning (Feb. 9","author":"McInnes Leland","year":"2018","unstructured":"Leland McInnes, Leland McInnes, John J. Healy, and John Healy. 2018. UMAP: uniform manifold approximation and projection for dimension reduction. arXiv: Machine Learning (Feb. 9, 2018)."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-56027-9_26"},{"key":"e_1_3_2_1_22_1","unstructured":"Martha Lewis Nihal V Nayak Peilin Yu Qinan Yu Jack Merullo Stephen H Bach and Ellie Pavlick. 2022. Does clip bind concepts? probing compositionality in large image models. arXiv preprint arXiv:2212.10537."},{"key":"e_1_3_2_1_23_1","first-page":"14200","article-title":"Datacomp-lm: in search of the next generation of training sets for language models","volume":"37","author":"Jeffrey Li","year":"2024","unstructured":"Jeffrey Li et al. 2024. Datacomp-lm: in search of the next generation of training sets for language models. Advances in Neural Information Processing Systems, 37, 14200--14282.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_24_1","volume-title":"International conference on machine learning. PMLR","author":"Li Junnan","year":"2023","unstructured":"Junnan Li, Dongxu Li, Silvio Savarese, and Steven Hoi. 2023. Blip-2: boot-strapping language-image pre-training with frozen image encoders and large language models. In International conference on machine learning. PMLR, 19730--19742."},{"key":"e_1_3_2_1_25_1","unstructured":"Xianhang Li Zeyu Wang and Cihang Xie. 2024. An inverse scaling law for clip training. Advances in Neural Information Processing Systems 36."},{"key":"e_1_3_2_1_26_1","article-title":"Clip-based grid features and masking for remote sensing image captioning","author":"Lin Qiaoling","year":"2024","unstructured":"Qiaoling Lin, Shuang Wang, Xiutiao Ye, Ruixuan Wang, Rui Yang, and Licheng Jiao. 2024. Clip-based grid features and masking for remote sensing image captioning. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.","journal-title":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing."},{"key":"e_1_3_2_1_27_1","unstructured":"Haotian Liu Chunyuan Li Qingyang Wu and Yong Jae Lee. 2023. Visual instruction tuning. Advances in neural information processing systems 36 34892--34916."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"crossref","unstructured":"Leland McInnes John Healy and James Melville. 2018. Umap: uniform manifold approximation and projection for dimension reduction. arXiv preprint arXiv:1802.03426.","DOI":"10.21105\/joss.00861"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.00276"},{"key":"e_1_3_2_1_30_1","unstructured":"Frederic P Miller Agnes F Vandome and John McBrewster. 2009. Levenshtein distance: information theory computer science string (computer science) string metric damerau? levenshtein distance spell checker hamming distance. (2009)."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.48550\/arxiv.2303.15389"},{"key":"e_1_3_2_1_32_1","unstructured":"Qizhou Wang Yong Lin Yongqiang Chen Ludwig Schmidt Bo Han and Tong Zhang. 2024. A sober look at the robustness of CLIPs to spurious features."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","unstructured":"Quan Sun Jinsheng Wang Qiying Yu Yufeng Cui Fan Zhang Xiaosong Zhang and Xinlong Wang. 2024. EVA-CLIP-18b: scaling CLIP to 18 billion parameters. arXiv.org. doi:10.48550\/arxiv.2402.04252.","DOI":"10.48550\/arxiv.2402.04252"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01457"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.48550\/arxiv.2210.08402"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.48550\/arxiv.2304.11127"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3463257"},{"key":"e_1_3_2_1_38_1","unstructured":"Alexei Stepanov. 2015. On the kendall correlation coefficient. arXiv preprint arXiv:1507.01427."},{"key":"e_1_3_2_1_39_1","unstructured":"Ben Vardi Oron Nir and Ariel Shamir. 2025. Clip-up: clip-based unanswerable problem detection for visual question answering. arXiv preprint arXiv:2501.01371."},{"key":"e_1_3_2_1_40_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 15963--15974","author":"Anasosalu Vasu Pavan Kumar","year":"2024","unstructured":"Pavan Kumar Anasosalu Vasu, Hadi Pouransari, Fartash Faghri, Raviteja Vemulapalli, and Oncel Tuzel. 2024. Mobileclip: fast image-text models through multi-modal reinforced training. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 15963--15974."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.48550\/arxiv.2207.12396"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","unstructured":"Weixian Lei Yixiao Ge Jianfeng Zhang Dylan Sun Kun Yi Ying Shan and Mike Zheng Shou. 2023. VIT-LENS: towards omni-modal representations. Computer Vision and Pattern Recognition. doi:10.1109\/cvpr52733.2024.02516.","DOI":"10.1109\/cvpr52733.2024.02516"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.5220\/0010288206010610"},{"key":"e_1_3_2_1_44_1","volume-title":"https:\/\/www.wikimedia.org","author":"Foundation Wikimedia","year":"2025","unstructured":"Wikimedia Foundation. 2025. Wikimedia Foundation. (2025). https:\/\/www.wikimedia.org."},{"key":"e_1_3_2_1_45_1","unstructured":"Wikimedia Foundation. 2025. Wikipedia - the free encyclopedia. (2025). https:\/\/www.wikipedia.org."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"crossref","unstructured":"Clark Wissler. 1905. The spearman correlation formula. Science 22 558 309--311.","DOI":"10.1126\/science.22.558.309"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"crossref","unstructured":"Xi Ding and Lei Wang. 2024. Do language models understand time?","DOI":"10.1145\/3701716.3717744"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.48550\/arxiv.2306.00813"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-96530-3"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01393"},{"key":"e_1_3_2_1_51_1","unstructured":"Jiahui Yu Zirui Wang Vijay Vasudevan Legg Yeung Mojtaba Seyedhosseini and Yonghui Wu. 2022. Coca: contrastive captioners are image-text foundation models. arXiv preprint arXiv:2205.01917."},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-38703-6_53"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr42600.2020.00282"}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Dublin Ireland","acronym":"MM '25"},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3758163","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:17:07Z","timestamp":1765307827000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3758163"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":54,"alternative-id":["10.1145\/3746027.3758163","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3758163","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}