{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,4]],"date-time":"2025-09-04T14:29:51Z","timestamp":1756996191495,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":61,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,10,26]],"date-time":"2023-10-26T00:00:00Z","timestamp":1698278400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3611721","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:27:40Z","timestamp":1698391660000},"page":"17-26","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["Suspected Objects Matter: Rethinking Model's Prediction for One-stage Visual Grounding"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8679-2242","authenticated-orcid":false,"given":"Yang","family":"Jiao","sequence":"first","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3038-5891","authenticated-orcid":false,"given":"Zequn","family":"Jie","sequence":"additional","affiliation":[{"name":"Meituan, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6234-1124","authenticated-orcid":false,"given":"Jingjing","family":"Chen","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3970-6548","authenticated-orcid":false,"given":"Lin","family":"Ma","sequence":"additional","affiliation":[{"name":"Meituan, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8781-6955","authenticated-orcid":false,"given":"Yu-Gang","family":"Jiang","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16188"},{"key":"e_1_3_2_1_2_1","volume-title":"Real-Time Referring Expression Comprehension by Single-Stage Grounding Network. CoRR","author":"Chen Xinpeng","year":"2018","unstructured":"Xinpeng Chen, Lin Ma, Jingyuan Chen, Zequn Jie, Wei Liu, and Jiebo Luo. 2018. Real-Time Referring Expression Comprehension by Single-Stage Grounding Network. CoRR, Vol. abs\/1812.03426 (2018). [arXiv]1812.03426"},{"key":"e_1_3_2_1_3_1","volume-title":"Revisiting Visual Grounding. CoRR","author":"Conser Erik","year":"2019","unstructured":"Erik Conser, Kennedy Hahn, Chandler M. Watson, and Melanie Mitchell. 2019. Revisiting Visual Grounding. CoRR, Vol. abs\/1904.02225 (2019). [arXiv]1904.02225"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.89"},{"key":"e_1_3_2_1_5_1","volume-title":"TransVG: End-to-End Visual Grounding with Transformers. arXiv preprint arXiv:2104.08541","author":"Deng Jiajun","year":"2021","unstructured":"Jiajun Deng, Zhengyuan Yang, Tianlang Chen, Wengang Zhou, and Houqiang Li. 2021. TransVG: End-to-End Visual Grounding with Transformers. arXiv preprint arXiv:2104.08541 (2021)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n19-1423"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2009.03.008"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"e_1_3_2_1_9_1","volume-title":"Long short-term memory. Neural computation","author":"Hochreiter Sepp","year":"1997","unstructured":"Sepp Hochreiter and J\u00fcrgen Schmidhuber. 1997. Long short-term memory. Neural computation, Vol. 9, 8 (1997), 1735--1780."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.470"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.493"},{"key":"e_1_3_2_1_12_1","volume-title":"Look Before You Leap: Learning Landmark Features for One-Stage Visual Grounding. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR).","author":"Huang Binbin","year":"2021","unstructured":"Binbin Huang, Dongze Lian, Weixin Luo, and Shenghua Gao. 2021. Look Before You Leap: Learning Landmark Features for One-Stage Visual Grounding. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_31"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475222"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/d14--1086"},{"key":"e_1_3_2_1_16_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma Diederik P","year":"2014","unstructured":"Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"key":"e_1_3_2_1_17_1","volume-title":"Kipf and Max Welling","author":"Thomas","year":"2017","unstructured":"Thomas N. Kipf and Max Welling. 2017. Semi-Supervised Classification with Graph Convolutional Networks. In 5th International Conference on Learning Representations, ICLR 2017, Toulon, France, April 24-26, 2017, Conference Track Proceedings. OpenReview.net."},{"key":"e_1_3_2_1_18_1","first-page":"19652","article-title":"Referring transformer: A one-step approach to multi-task visual grounding","volume":"34","author":"Li Muchen","year":"2021","unstructured":"Muchen Li and Leonid Sigal. 2021. Referring transformer: A one-step approach to multi-task visual grounding. Advances in Neural Information Processing Systems, Vol. 34 (2021), 19652--19664.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_19_1","volume-title":"2023 a. LMEye: An Interactive Perception Network for Large Language Models. arXiv preprint arXiv:2305.03701","author":"Li Yunxin","year":"2023","unstructured":"Yunxin Li, Baotian Hu, Xinyu Chen, Lin Ma, and Min Zhang. 2023 a. LMEye: An Interactive Perception Network for Large Language Models. arXiv preprint arXiv:2305.03701 (2023)."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.909"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.601"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01089"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3181516"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00477"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"e_1_3_2_1_28_1","volume-title":"Improving Referring Expression Grounding With Cross-Modal Attention-Guided Erasing. In IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2019","author":"Liu Xihui","year":"2019","unstructured":"Xihui Liu, Zihao Wang, Jing Shao, Xiaogang Wang, and Hongsheng Li. 2019a. Improving Referring Expression Grounding With Cross-Modal Attention-Guided Erasing. In IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2019, Long Beach, CA, USA, June 16-20, 2019. Computer Vision Foundation \/ IEEE, 1950--1959."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6833"},{"key":"e_1_3_2_1_30_1","volume-title":"SGDR: Stochastic Gradient Descent with Warm Restarts. In 5th International Conference on Learning Representations, ICLR","author":"Loshchilov Ilya","year":"2017","unstructured":"Ilya Loshchilov and Frank Hutter. 2017. SGDR: Stochastic Gradient Descent with Warm Restarts. In 5th International Conference on Learning Representations, ICLR 2017, Toulon, France, April 24-26, 2017, Conference Track Proceedings. OpenReview.net."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.9"},{"key":"e_1_3_2_1_32_1","volume-title":"Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, (AAAI-18)","author":"Perez Ethan","year":"2019","unstructured":"Ethan Perez, Florian Strub, Harm de Vries, Vincent Dumoulin, and Aaron C. Courville. 2018. FiLM: Visual Reasoning with a General Conditioning Layer. In Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, (AAAI-18), the 30th innovative Applications of Artificial Intelligence (IAAI-18), and the 8th AAAI Symposium on Educational Advances in Artificial Intelligence (EAAI-18), New Orleans, Louisiana, USA, February 2-7, 2019, Sheila A. McIlraith and Kilian Q. Weinberger (Eds.). AAAI Press, 3942--3951."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01258-8_16"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00371-006-0051-1"},{"volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 9982--9991","author":"Qi Yuankai","key":"e_1_3_2_1_35_1","unstructured":"Yuankai Qi, Qi Wu, Peter Anderson, Xin Wang, William Yang Wang, Chunhua Shen, and Anton van den Hengel. 2020. Reverie: Remote embodied visual referring expression in real indoor environments. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 9982--9991."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3042066"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"e_1_3_2_1_38_1","volume-title":"Faster r-cnn: Towards real-time object detection with region proposal networks. Advances in neural information processing systems","author":"Ren Shaoqing","year":"2015","unstructured":"Shaoqing Ren, Kaiming He, Ross Girshick, and Jian Sun. 2015. Faster r-cnn: Towards real-time object detection with region proposal networks. Advances in neural information processing systems, Vol. 28 (2015), 91--99."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00479"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3090595"},{"key":"e_1_3_2_1_41_1","volume-title":"Si Liu, and John Y Goulermas.","author":"Sun Mingjie","year":"2021","unstructured":"Mingjie Sun, Jimin Xiao, Eng Gee Lim, Si Liu, and John Y Goulermas. 2021. Discriminative triad matching and reconstruction for weakly referring expression grounding. IEEE transactions on pattern analysis and machine intelligence, Vol. 43, 11 (2021), 4189--4195."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00972"},{"key":"e_1_3_2_1_43_1","volume-title":"Attention is all you need. Advances in neural information processing systems","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_1_44_1","volume-title":"Graph Attention Networks. CoRR","author":"Velickovic Petar","year":"2017","unstructured":"Petar Velickovic, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Li\u00f2, and Yoshua Bengio. 2017. Graph Attention Networks. CoRR, Vol. abs\/1710.10903 (2017). showeprint[arXiv]1710.10903"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2797921"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00206"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"e_1_3_2_1_48_1","volume-title":"HuggingFace's Transformers: State-of-the-art Natural Language Processing. CoRR","author":"Wolf Thomas","year":"2019","unstructured":"Thomas Wolf, Lysandre Debut, Victor Sanh, Julien Chaumond, Clement Delangue, Anthony Moi, Pierric Cistac, Tim Rault, R\u00e9mi Louf, Morgan Funtowicz, and Jamie Brew. 2019. HuggingFace's Transformers: State-of-the-art Natural Language Processing. CoRR, Vol. abs\/1910.03771 (2019). [arXiv]1910.03771"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00474"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00997"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"crossref","unstructured":"Zhengyuan Yang Tianlang Chen Liwei Wang and Jiebo Luo. 2020a. Improving One-stage Visual Grounding by Recursive Sub-query Construction. In ECCV.","DOI":"10.1007\/978-3-030-58568-6_23"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"crossref","unstructured":"Zhengyuan Yang Boqing Gong Liwei Wang Wenbing Huang Dong Yu and Jiebo Luo. 2019a. A Fast and Accurate One-Stage Approach to Visual Grounding. In ICCV.","DOI":"10.1109\/ICCV.2019.00478"},{"key":"e_1_3_2_1_53_1","volume-title":"4th International Conference on Learning Representations, ICLR 2016, San Juan, Puerto Rico, May 2-4, 2016, Conference Track Proceedings, Yoshua Bengio and Yann LeCun (Eds.).","author":"Yu Fisher","year":"2016","unstructured":"Fisher Yu and Vladlen Koltun. 2016. Multi-Scale Context Aggregation by Dilated Convolutions. In 4th International Conference on Learning Representations, ICLR 2016, San Juan, Puerto Rico, May 2-4, 2016, Conference Track Proceedings, Yoshua Bengio and Yann LeCun (Eds.)."},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00142"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.375"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/155"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00437"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01174"},{"key":"e_1_3_2_1_60_1","volume-title":"Tel Aviv","author":"Zhu Chaoyang","year":"2022","unstructured":"Chaoyang Zhu, Yiyi Zhou, Yunhang Shen, Gen Luo, Xingjia Pan, Mingbao Lin, Chao Chen, Liujuan Cao, Xiaoshuai Sun, and Rongrong Ji. 2022. Seqtr: A simple yet universal network for visual grounding. In Computer Vision-ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23-27, 2022, Proceedings, Part XXXV. Springer, 598--615."},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00447"}],"event":{"name":"MM '23: The 31st ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Ottawa ON Canada","acronym":"MM '23"},"container-title":["Proceedings of the 31st ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3611721","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3611721","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:06:49Z","timestamp":1755821209000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3611721"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":61,"alternative-id":["10.1145\/3581783.3611721","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3611721","relation":{},"subject":[],"published":{"date-parts":[[2023,10,26]]},"assertion":[{"value":"2023-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}