{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T21:31:31Z","timestamp":1730237491645,"version":"3.28.0"},"reference-count":81,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"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":[[2023,10,1]]},"DOI":"10.1109\/iccv51070.2023.01102","type":"proceedings-article","created":{"date-parts":[[2024,1,15]],"date-time":"2024-01-15T15:55:59Z","timestamp":1705334159000},"page":"11964-11974","source":"Crossref","is-referenced-by-count":6,"title":["Equivariant Similarity for Vision-Language Foundation Models"],"prefix":"10.1109","author":[{"given":"Tan","family":"Wang","sequence":"first","affiliation":[{"name":"Nanyang Technological University"}]},{"given":"Kevin","family":"Lin","sequence":"additional","affiliation":[{"name":"Microsoft"}]},{"given":"Linjie","family":"Li","sequence":"additional","affiliation":[{"name":"Microsoft"}]},{"given":"Chung-Ching","family":"Lin","sequence":"additional","affiliation":[{"name":"Microsoft"}]},{"given":"Zhengyuan","family":"Yang","sequence":"additional","affiliation":[{"name":"Microsoft"}]},{"given":"Hanwang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Nanyang Technological University"}]},{"given":"Zicheng","family":"Liu","sequence":"additional","affiliation":[{"name":"Microsoft"}]},{"given":"Lijuan","family":"Wang","sequence":"additional","affiliation":[{"name":"Microsoft"}]}],"member":"263","reference":[{"article-title":"Flamingo: a visual language model for few-shot learning","year":"2022","author":"Alayrac","key":"ref1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/130385.130401"},{"article-title":"Geometric deep learning: Grids, groups, graphs, geodesics, and gauges","year":"2021","author":"Bronstein","key":"ref4"},{"key":"ref5","article-title":"Rubi: Reducing unimodal biases for visual question answering","volume":"32","author":"Cadene","year":"2019","journal-title":"NeurIPS"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p18-1241"},{"article-title":"Microsoft COCO Captions: Data collection and evaluation server","year":"2015","author":"Chen","key":"ref7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"article-title":"Dalleval: Probing the reasoning skills and social biases of text-to-image generative transformers","year":"2022","author":"Cho","key":"ref9"},{"key":"ref10","first-page":"2990","article-title":"Group equivariant convolutional networks","volume-title":"ICML","author":"Cohen","year":"2016"},{"article-title":"Spherical cnns","year":"2018","author":"Cohen","key":"ref11"},{"article-title":"Equivariant contrastive learning","year":"2021","author":"Dangovski","key":"ref12"},{"article-title":"Coarse-to-fine vision-language pre-training with fusion in the backbone","year":"2022","author":"Dou","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01763"},{"journal-title":"NeurIPS","article-title":"Large-scale adversarial training for vision-and-language representation learning","year":"2020","author":"Gan","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1561\/9781638281337"},{"article-title":"Cyclip: Cyclic contrastive language-image pretraining","year":"2022","author":"Goel","key":"ref17"},{"article-title":"Multimodal-gpt: A vision and language model for dialogue with humans","year":"2023","author":"Gong","key":"ref18"},{"journal-title":"ICLR","article-title":"Permutation equivariant models for compositional generalization in language","year":"2019","author":"Gordon","key":"ref19"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00373"},{"article-title":"Grit: General robust image task benchmark","year":"2022","author":"Gupta","key":"ref21"},{"key":"ref22","first-page":"5679","article-title":"Self-supervised co-training for video representation learning","volume":"33","author":"Han","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.318"},{"article-title":"Prompt-to-prompt image editing with cross attention control","year":"2022","author":"Hertz","key":"ref24"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00237"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01025"},{"journal-title":"ICML","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","year":"2021","author":"Jia","key":"ref27"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.443"},{"article-title":"The kinetics human action video dataset","year":"2017","author":"Kay","key":"ref29"},{"key":"ref30","first-page":"5583","article-title":"Vilt: Vision-and-language transformer without convolution or region supervision","volume-title":"ICML","author":"Kim","year":"2021"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.241"},{"article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","year":"2023","author":"Li","key":"ref33"},{"article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","year":"2022","author":"Li","key":"ref34"},{"journal-title":"NeurIPS","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","year":"2021","author":"Li","key":"ref35"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00205"},{"article-title":"VisualBERT: A simple and performant baseline for vision and language","year":"2019","author":"Li","key":"ref37"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"article-title":"Visual instruction tuning","year":"2023","author":"Liu","key":"ref40"},{"journal-title":"NeurIPS","article-title":"ViL-BERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","year":"2019","author":"Lu","key":"ref41"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01251"},{"journal-title":"NeurIPS","article-title":"Im2Text: Describing images using 1 million captioned photographs","year":"2011","author":"Ordonez","key":"ref43"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.567"},{"article-title":"Support-set bottlenecks for video-text representation learning","year":"2020","author":"Patrick","key":"ref45"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3029801"},{"key":"ref48","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"ICML","author":"Radford","year":"2021"},{"article-title":"Hierarchical text-conditional image generation with clip latents","year":"2022","author":"Ramesh","key":"ref49"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"volume":"32","volume-title":"Real analysis","year":"1988","author":"Royden","key":"ref52"},{"article-title":"Photorealistic text-to-image diffusion models with deep language understanding","year":"2022","author":"Saharia","key":"ref53"},{"article-title":"Laion-400m: Open dataset of clip-filtered 400 million image-text pairs","year":"2021","author":"Schuhmann","key":"ref54"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1024"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00797"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01519"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01519"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00377"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00517"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4757-3264-1"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"article-title":"Unifying architectures, tasks, and modalities through a simple sequence-to-sequence learning framework","year":"2022","author":"Wang","key":"ref65"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01077"},{"key":"ref67","first-page":"18225","article-title":"Self-supervised learning disentangled group representation as feature","volume":"34","author":"Wang","year":"2021","journal-title":"NeurIPS"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01838"},{"article-title":"VLMo: Unified vision-language pre-training with mixture-of-modality-experts","year":"2021","author":"Wang","key":"ref69"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_41"},{"journal-title":"ICLR","article-title":"SimVLM: Simple visual language model pretraining with weak supervision","year":"2022","author":"Wang","key":"ref71"},{"key":"ref72","article-title":"General e (2)-equivariant steerable cnns","volume":"32","author":"Weiler","year":"2019","journal-title":"NeurIPS"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00456"},{"article-title":"CoCa: Contrastive captioners are image-text foundation models","year":"2022","author":"Yu","key":"ref74"},{"article-title":"Scaling autoregressive models for content-rich text-to-image generation","year":"2022","author":"Yu","key":"ref75"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00688"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00553"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-demos.4"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12342"},{"article-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","year":"2023","author":"Zhu","key":"ref81"}],"event":{"name":"2023 IEEE\/CVF International Conference on Computer Vision (ICCV)","start":{"date-parts":[[2023,10,1]]},"location":"Paris, France","end":{"date-parts":[[2023,10,6]]}},"container-title":["2023 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10376473\/10376477\/10376552.pdf?arnumber=10376552","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,17]],"date-time":"2024-01-17T19:59:12Z","timestamp":1705521552000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10376552\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,1]]},"references-count":81,"URL":"https:\/\/doi.org\/10.1109\/iccv51070.2023.01102","relation":{},"subject":[],"published":{"date-parts":[[2023,10,1]]}}}