{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,9]],"date-time":"2026-10-09T17:27:04Z","timestamp":1791566824156,"version":"4.3.4"},"reference-count":60,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,6,16]],"date-time":"2024-06-16T00:00:00Z","timestamp":1718496000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,16]],"date-time":"2024-06-16T00:00:00Z","timestamp":1718496000000},"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":[[2024,6,16]]},"DOI":"10.1109\/cvpr52733.2024.01290","type":"proceedings-article","created":{"date-parts":[[2024,9,16]],"date-time":"2024-09-16T13:34:53Z","timestamp":1726493693000},"page":"13592-13602","source":"Crossref","is-referenced-by-count":9,"title":["Generating Enhanced Negatives for Training Language-Based Object Detectors"],"prefix":"10.1109","author":[{"given":"Shiyu","family":"Zhao","sequence":"first","affiliation":[{"name":"Rutgers University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Long","family":"Zhao","sequence":"additional","affiliation":[{"name":"Google Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vijay Kumar","family":"B G","sequence":"additional","affiliation":[{"name":"NEC Laboratories America"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yumin","family":"Suh","sequence":"additional","affiliation":[{"name":"NEC Laboratories America"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dimitris N.","family":"Metaxas","sequence":"additional","affiliation":[{"name":"Rutgers University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Manmohan","family":"Chandraker","sequence":"additional","affiliation":[{"name":"NEC Laboratories America"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Samuel","family":"Schulter","sequence":"additional","affiliation":[{"name":"NEC Laboratories America"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref2","first-page":"2","article-title":"BERT: Pre-training of deep bidirectional trans-formers for language understanding","author":"Devlin","year":"2019","journal-title":"NAACL"},{"key":"ref3","first-page":"1","article-title":"Coarse-to-Fine Vision-Language Pre-training with Fusion in the Backbone","author":"Dou","year":"2022","journal-title":"NeurIPS"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00261"},{"key":"ref5","first-page":"1","article-title":"Open-vocabulary Object Detection via Vision and Language Knowledge Distillation","author":"Gu","year":"2022","journal-title":"ICLR"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00550"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1281"},{"key":"ref8","first-page":"2","article-title":"Sugarcrepe: Fixing hack-able benchmarks for vision-language compositionality","author":"Hsieh","year":"2023","journal-title":"NeurIPS"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00147"},{"key":"ref10","first-page":"2","article-title":"Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision","author":"Jia","year":"2021","journal-title":"ICML"},{"key":"ref11","first-page":"1","article-title":"MDETR - Mod-ulated Detection for End-to-End Multi-Modal Understanding","author":"Kamath","year":"2021","journal-title":"ICCV"},{"key":"ref12","first-page":"1","article-title":"TRICD: Testing Robust Image Under-standing Through Contextual Phrase Detection","author":"Kamath","year":"2023","journal-title":"Technical report"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_42"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref15","first-page":"1","article-title":"F-vlm: Open-vocabulary object detection upon frozen vision and language models","author":"Kuo","year":"2023","journal-title":"ICLR"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01316-z"},{"key":"ref17","first-page":"1","article-title":"ELE-VATER: A Benchmark and Toolkit for Evaluating Language-Augmented Visual Models","author":"Li","year":"2022","journal-title":"NeurIPS"},{"key":"ref18","first-page":"2","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","author":"Li","year":"2021","journal-title":"NeurIPS"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"ref20","first-page":"2","article-title":"DesCo: Learning Object Recognition with Rich Language Descriptions","author":"Li","year":"2023","journal-title":"NeurIPS"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02156"},{"key":"ref22","first-page":"1","article-title":"Learning object-language alignments for open-vocabulary object detection","author":"Lin","year":"2023","journal-title":"ICLR"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02259"},{"key":"ref26","first-page":"6","article-title":"Grounding dino: Marrying dino with grounded pre-training for open-set object detection","author":"Liu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref27","first-page":"2","volume-title":"Roberta: A robustly optimized bert pretraining approach","author":"Liu","year":"2019"},{"key":"ref28","first-page":"2","article-title":"ViL-BERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks","author":"Lu","year":"2019","journal-title":"NeurIPS"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01050"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.9"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/219717.219748"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02050"},{"key":"ref33","first-page":"1","article-title":"Simple Open-Vocabulary Object Detection with Vision Transformers","author":"Minderer","year":"2022","journal-title":"ECCV"},{"key":"ref34","first-page":"1","article-title":"Scaling Open-Vocabulary Object Detection","author":"Minderer","year":"2023","journal-title":"NeurIPS"},{"key":"ref35","first-page":"2","volume-title":"Gpt-3.5.","year":"2022"},{"key":"ref36","first-page":"2641","article-title":"Flickr30k Entities: Collecting region-to-phrase corre-spondences for richer image-to-sentence models","author":"Bryan","year":"2015","journal-title":"ICCV"},{"key":"ref37","first-page":"2","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"ICML"},{"key":"ref38","first-page":"1","article-title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","author":"Ren","year":"2015","journal-title":"NeurIPS"},{"key":"ref39","first-page":"1","article-title":"Contrastive Learning with Hard Negative Samples","author":"Robinson","year":"2021","journal-title":"ICLR"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01098"},{"key":"ref42","first-page":"1","article-title":"Objects 365: A Large-scale, High-quality Dataset for Object Detection","author":"Shao","year":"2019","journal-title":"ICCV"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1024"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.89"},{"key":"ref45","first-page":"1","article-title":"ReCLIP: A Strong Zero-Shot Baseline for Referring Expression Com-prehension","author":"Subramanian","year":"2022","journal-title":"ACL"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00517"},{"key":"ref47","first-page":"2","volume-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"issue":"86","key":"ref48","first-page":"2579","article-title":"Visualizing data using t-sne","volume":"9","author":"van der Maaten","year":"2008","journal-title":"Journal of Machine Learning Research"},{"key":"ref49","first-page":"6","article-title":"OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework","author":"Wang","year":"2022","journal-title":"ICML"},{"key":"ref50","first-page":"1","article-title":"PhraseCut: Language-based Image Seg-mentation in the Wild","author":"Wu","year":"2020","journal-title":"CVPR"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00677"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00679"},{"key":"ref53","first-page":"1","article-title":"Described Object Detection: Liberating Ob-ject Detection with Flexible Expressions","author":"Xie","journal-title":"NeurIPS, 2023."},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"ref55","first-page":"2","article-title":"When and why vision-language models behave like bags-of-words, and what to do about it?","author":"Yuksekgonul","year":"2023","journal-title":"ICLR"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01416"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_10"},{"key":"ref58","first-page":"2","volume-title":"Improving pseudo labels for open-vocabulary object detection","author":"Zhao","year":"2023"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01629"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_21"}],"event":{"name":"2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","location":"Seattle, WA, USA","start":{"date-parts":[[2024,6,16]]},"end":{"date-parts":[[2024,6,22]]}},"container-title":["2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10654794\/10654797\/10658507.pdf?arnumber=10658507","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,20]],"date-time":"2024-09-20T01:32:01Z","timestamp":1726795921000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10658507\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,16]]},"references-count":60,"URL":"https:\/\/doi.org\/10.1109\/cvpr52733.2024.01290","relation":{},"subject":[],"published":{"date-parts":[[2024,6,16]]}}}