@article{suo2023text, title={Text Augmented Spatial-aware Zero-shot Referring Image Segmentation}, author={Suo, Yucheng and Zhu, Linchao and Yang, Yi}, journal={arXiv preprint arXiv:2310.18049}, year={2023} }
@inproceedings{shi2023unsupervised, title={Unsupervised Domain Adaptation for Referring Semantic Segmentation}, author={Shi, Haonan and Pan, Wenwen and Zhao, Zhou and Zhang, Mingmin and Wu, Fei}, booktitle={Proceedings of the 31st ACM International Conference on Multimedia}, pages={5807--5818}, year={2023} }
@inproceedings{liu2023caris, title={CARIS: Context-Aware Referring Image Segmentation}, author={Liu, Sun-Ao and Zhang, Yiheng and Qiu, Zhaofan and Xie, Hongtao and Zhang, Yongdong and Yao, Ting}, booktitle={Proceedings of the 31st ACM International Conference on Multimedia}, pages={779--788}, year={2023} }
@inproceedings{kim2023shatter, title={Shatter and Gather: Learning Referring Image Segmentation with Text Supervision}, author={Kim, Dongwon and Kim, Namyup and Lan, Cuiling and Kwak, Suha}, booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision}, pages={15547--15557}, year={2023} }
@inproceedings{wu2023advancing, title={Advancing referring expression segmentation beyond single image}, author={Wu, Yixuan and Zhang, Zhao and Xie, Chi and Zhu, Feng and Zhao, Rui}, booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision}, pages={2628--2638}, year={2023} }
@inproceedings{xu2023bridging, title={Bridging vision and language encoders: Parameter-efficient tuning for referring image segmentation}, author={Xu, Zunnan and Chen, Zhihong and Zhang, Yong and Song, Yibing and Wan, Xiang and Li, Guanbin}, booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision}, pages={17503--17512}, year={2023} }
@inproceedings{liu2023referring, title={Referring image segmentation using text supervision}, author={Liu, Fang and Liu, Yuhao and Kong, Yuqiu and Xu, Ke and Zhang, Lihe and Yin, Baocai and Hancke, Gerhard and Lau, Rynson}, booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision}, pages={22124--22134}, year={2023} }
@inproceedings{hu2023beyond, title={Beyond One-to-One: Rethinking the Referring Image Segmentation}, author={Hu, Yutao and Wang, Qixiong and Shao, Wenqi and Xie, Enze and Li, Zhenguo and Han, Jungong and Luo, Ping}, booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision}, pages={4067--4077}, year={2023} }
@article{ding2023bilateral, title={Bilateral Knowledge Interaction Network for Referring Image Segmentation}, author={Ding, Haixin and Zhang, Shengchuan and Wu, Qiong and Yu, Songlin and Hu, Jie and Cao, Liujuan and Ji, Rongrong}, journal={IEEE Transactions on Multimedia}, year={2023}, publisher={IEEE} }
@inproceedings{ouyang23slvit, title={Slvit: Scale-wise language-guided vision transformer for referring image segmentation}, author={Ouyang, Shuyi and Wang, Hongyi and Xie, Shiao and Niu, Ziwei and Tong, Ruofeng and Chen, Yen-Wei and Lin, Lanfen}, booktitle={Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence, IJCAI-23}, pages={1294--1302} }
@article{cheng2023wico, title={WiCo: Win-win Cooperation of Bottom-up and Top-down Referring Image Segmentation}, author={Cheng, Zesen and Jin, Peng and Li, Hao and Li, Kehan and Li, Siheng and Ji, Xiangyang and Liu, Chang and Chen, Jie}, journal={arXiv preprint arXiv:2306.10750}, year={2023} }
@article{wang2023cm, title={CM-MaskSD: Cross-Modality Masked Self-Distillation for Referring Image Segmentation}, author={Wang, Wenxuan and Liu, Jing and He, Xingjian and Zhang, Yisi and Chen, Chen and Shen, Jiachen and Zhang, Yan and Li, Jiangyun}, journal={arXiv preprint arXiv:2305.11481}, year={2023} }
@inproceedings{tang2023contrastive, title={Contrastive Grouping with Transformer for Referring Image Segmentation}, author={Tang, Jiajin and Zheng, Ge and Shi, Cheng and Yang, Sibei}, booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition}, pages={23570--23580}, year={2023} }
@inproceedings{qu2023learning, title={Learning to Segment Every Referring Object Point by Point}, author={Qu, Mengxue and Wu, Yu and Wei, Yunchao and Liu, Wu and Liang, Xiaodan and Zhao, Yao}, booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition}, pages={3021--3030}, year={2023} }
@inproceedings{yu2023zero, title={Zero-shot Referring Image Segmentation with Global-Local Context Features}, author={Yu, Seonghoon and Seo, Paul Hongsuck and Son, Jeany}, booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition}, pages={19456--19465}, year={2023} }
@inproceedings{xu2023meta, title={Meta compositional referring expression segmentation}, author={Xu, Li and Huang, Mark He and Shang, Xindi and Yuan, Zehuan and Sun, Ying and Liu, Jun}, booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition}, pages={19478--19487}, year={2023} }
@inproceedings{liu2023polyformer, title={PolyFormer: Referring image segmentation as sequential polygon generation}, author={Liu, Jiang and Ding, Hui and Cai, Zhaowei and Zhang, Yuting and Satzoda, Ravi Kumar and Mahadevan, Vijay and Manmatha, R}, booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition}, pages={18653--18663}, year={2023} }
@inproceedings{liu2023gres, title={GRES: Generalized referring expression segmentation}, author={Liu, Chang and Ding, Henghui and Jiang, Xudong}, booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition}, pages={23592--23601}, year={2023} }
@article{yang2023semantics, title={Semantics-Aware Dynamic Localization and Refinement for Referring Image Segmentation}, author={Yang, Zhao and Wang, Jiaqi and Tang, Yansong and Chen, Kai and Zhao, Hengshuang and Torr, Philip HS}, journal={arXiv preprint arXiv:2303.06345}, year={2023} }
@article{chen2022position, title={Position-aware contrastive alignment for referring image segmentation}, author={Chen, Bo and Hu, Zhiwei and Ji, Zhilong and Bai, Jinfeng and Zuo, Wangmeng}, journal={arXiv preprint arXiv:2212.13419}, year={2022} }
@article{zhang2022coupalign, title={Coupalign: Coupling word-pixel with sentence-mask alignments for referring image segmentation}, author={Zhang, Zicheng and Zhu, Yi and Liu, Jianzhuang and Liang, Xiaodan and Ke, Wei}, journal={Advances in Neural Information Processing Systems}, volume={35}, pages={14729--14742}, year={2022} }
@article{shang2022cross, title={Cross-Modal Recurrent Semantic Comprehension for Referring Image Segmentation}, author={Shang, Chao and Li, Hongliang and Qiu, Heqian and Wu, Qingbo and Meng, Fanman and Zhao, Taijin and Ngan, King Ngi}, journal={IEEE Transactions on Circuits and Systems for Video Technology}, year={2022}, publisher={IEEE} }
@article{liu2023local, title={Local-global coordination with transformers for referring image segmentation}, author={Liu, Fang and Kong, Yuqiu and Zhang, Lihe and Feng, Guang and Yin, Baocai}, journal={Neurocomputing}, volume={522}, pages={39--52}, year={2023}, publisher={Elsevier} }
@article{huang2022unified, title={A unified mutual supervision framework for referring expression segmentation and generation}, author={Huang, Shijia and Li, Feng and Zhang, Hao and Liu, Shilong and Zhang, Lei and Wang, Liwei}, journal={arXiv preprint arXiv:2211.07919}, year={2022} }
@article{ding2022vlt, title={Vlt: Vision-language transformer and query generation for referring segmentation}, author={Ding, Henghui and Liu, Chang and Wang, Suchen and Jiang, Xudong}, journal={IEEE Transactions on Pattern Analysis and Machine Intelligence}, year={2022}, publisher={IEEE} }
@article{feng2022learning, title={Learning from box annotations for referring image segmentation}, author={Feng, Guang and Zhang, Lihe and Hu, Zhiwei and Lu, Huchuan}, journal={IEEE Transactions on Neural Networks and Learning Systems}, year={2022}, publisher={IEEE} }
@article{liu2022instance, title={Instance-specific feature propagation for referring segmentation}, author={Liu, Chang and Jiang, Xudong and Ding, Henghui}, journal={IEEE Transactions on Multimedia}, year={2022}, publisher={IEEE} }
@inproceedings{zhu2022seqtr, title={Seqtr: A simple yet universal network for visual grounding}, author={Zhu, Chaoyang and Zhou, Yiyi and Shen, Yunhang and Luo, Gen and Pan, Xingjia and Lin, Mingbao and Chen, Chao and Cao, Liujuan and Sun, Xiaoshuai and Ji, Rongrong}, booktitle={European Conference on Computer Vision}, pages={598--615}, year={2022}, organization={Springer} }
@inproceedings{yang2022lavt, title={Lavt: Language-aware vision transformer for referring image segmentation}, author={Yang, Zhao and Wang, Jiaqi and Tang, Yansong and Chen, Kai and Zhao, Hengshuang and Torr, Philip HS}, booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition}, pages={18155--18165}, year={2022} }
@inproceedings{wang2022cris, title={Cris: Clip-driven referring image segmentation}, author={Wang, Zhaoqing and Lu, Yu and Li, Qiang and Tao, Xunqiang and Guo, Yandong and Gong, Mingming and Liu, Tongliang}, booktitle={Proceedings of the IEEE/CVF conference on computer vision and pattern recognition}, pages={11686--11695}, year={2022} }
@inproceedings{kim2022restr, title={Restr: Convolution-free referring image segmentation using transformers}, author={Kim, Namyup and Kim, Dongwon and Lan, Cuiling and Zeng, Wenjun and Kwak, Suha}, booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition}, pages={18145--18154}, year={2022} }
@article{feng2021bidirectional, title={Bidirectional relationship inferring network for referring image localization and segmentation}, author={Feng, Guang and Hu, Zhiwei and Zhang, Lihe and Sun, Jiayu and Lu, Huchuan}, journal={IEEE Transactions on Neural Networks and Learning Systems}, year={2021}, publisher={IEEE} }
@article{li2021referring, title={Referring transformer: A one-step approach to multi-task visual grounding}, author={Li, Muchen and Sigal, Leonid}, journal={Advances in neural information processing systems}, volume={34}, pages={19652--19664}, year={2021} }
@inproceedings{jiao2021two, title={Two-stage visual cues enhancement network for referring image segmentation}, author={Jiao, Yang and Jie, Zequn and Luo, Weixin and Chen, Jingjing and Jiang, Yu-Gang and Wei, Xiaolin and Ma, Lin}, booktitle={Proceedings of the 29th ACM International Conference on Multimedia}, pages={1331--1340}, year={2021} }
@inproceedings{ding2021vision, title={Vision-language transformer and query generation for referring segmentation}, author={Ding, Henghui and Liu, Chang and Wang, Suchen and Jiang, Xudong}, booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision}, pages={16321--16330}, year={2021} }
@inproceedings{kamath2021mdetr, title={Mdetr-modulated detection for end-to-end multi-modal understanding}, author={Kamath, Aishwarya and Singh, Mannat and LeCun, Yann and Synnaeve, Gabriel and Misra, Ishan and Carion, Nicolas}, booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision}, pages={1780--1790}, year={2021} }
@inproceedings{feng2021encoder, title={Encoder fusion network with co-attention embedding for referring image segmentation}, author={Feng, Guang and Hu, Zhiwei and Zhang, Lihe and Lu, Huchuan}, booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition}, pages={15506--15515}, year={2021} }
@inproceedings{yang2021bottom, title={Bottom-up shift and reasoning for referring image segmentation}, author={Yang, Sibei and Xia, Meng and Li, Guanbin and Zhou, Hong-Yu and Yu, Yizhou}, booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition}, pages={11266--11275}, year={2021} }
@inproceedings{jing2021locate, title={Locate then segment: A strong pipeline for referring image segmentation}, author={Jing, Ya and Kong, Tao and Wang, Wei and Wang, Liang and Li, Lei and Tan, Tieniu}, booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition}, pages={9858--9867}, year={2021} }
@inproceedings{luo2020cascade, title={Cascade grouped attention network for referring expression segmentation}, author={Luo, Gen and Zhou, Yiyi and Ji, Rongrong and Sun, Xiaoshuai and Su, Jinsong and Lin, Chia-Wen and Tian, Qi}, booktitle={Proceedings of the 28th ACM International Conference on Multimedia}, pages={1274--1282}, year={2020} }
@inproceedings{hui2020linguistic, title={Linguistic structure guided context modeling for referring image segmentation}, author={Hui, Tianrui and Liu, Si and Huang, Shaofei and Li, Guanbin and Yu, Sansi and Zhang, Faxi and Han, Jizhong}, booktitle={Computer Vision--ECCV 2020: 16th European Conference, Glasgow, UK, August 23--28, 2020, Proceedings, Part X 16}, pages={59--75}, year={2020}, organization={Springer} }
@inproceedings{huang2020referring, title={Referring image segmentation via cross-modal progressive comprehension}, author={Huang, Shaofei and Hui, Tianrui and Liu, Si and Li, Guanbin and Wei, Yunchao and Han, Jizhong and Liu, Luoqi and Li, Bo}, booktitle={Proceedings of the IEEE/CVF conference on computer vision and pattern recognition}, pages={10488--10497}, year={2020} }
@inproceedings{hu2020bi, title={Bi-directional relationship inferring network for referring image segmentation}, author={Hu, Zhiwei and Feng, Guang and Sun, Jiayu and Zhang, Lihe and Lu, Huchuan}, booktitle={Proceedings of the IEEE/CVF conference on computer vision and pattern recognition}, pages={4424--4433}, year={2020} }
@inproceedings{wu2020phrasecut, title={Phrasecut: Language-based image segmentation in the wild}, author={Wu, Chenyun and Lin, Zhe and Cohen, Scott and Bui, Trung and Maji, Subhransu}, booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition}, pages={10216--10225}, year={2020} }
@inproceedings{luo2020multi, title={Multi-task collaborative network for joint referring expression comprehension and segmentation}, author={Luo, Gen and Zhou, Yiyi and Sun, Xiaoshuai and Cao, Liujuan and Wu, Chenglin and Deng, Cheng and Ji, Rongrong}, booktitle={Proceedings of the IEEE/CVF Conference on computer vision and pattern recognition}, pages={10034--10043}, year={2020} }
@article{ye2020dual, title={Dual convolutional lstm network for referring image segmentation}, author={Ye, Linwei and Liu, Zhi and Wang, Yang}, journal={IEEE Transactions on Multimedia}, volume={22}, number={12}, pages={3224--3235}, year={2020}, publisher={IEEE} }
@article{chen2019referring, title={Referring expression object segmentation with caption-aware consistency}, author={Chen, Yi-Wen and Tsai, Yi-Hsuan and Wang, Tiantian and Lin, Yen-Yu and Yang, Ming-Hsuan}, journal={arXiv preprint arXiv:1910.04748}, year={2019} }
@inproceedings{chen2019see, title={See-through-text grouping for referring image segmentation}, author={Chen, Ding-Jie and Jia, Songhao and Lo, Yi-Chen and Chen, Hwann-Tzong and Liu, Tyng-Luh}, booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision}, pages={7454--7463}, year={2019} }
@inproceedings{ye2019cross, title={Cross-modal self-attention network for referring image segmentation}, author={Ye, Linwei and Rochan, Mrigank and Liu, Zhi and Wang, Yang}, booktitle={Proceedings of the IEEE/CVF conference on computer vision and pattern recognition}, pages={10502--10511}, year={2019} }
@inproceedings{shi2018key, title={Key-word-aware network for referring expression image segmentation}, author={Shi, Hengcan and Li, Hongliang and Meng, Fanman and Wu, Qingbo}, booktitle={Proceedings of the European Conference on Computer Vision (ECCV)}, pages={38--54}, year={2018} }
@inproceedings{margffoy2018dynamic, title={Dynamic multimodal instance segmentation guided by natural language queries}, author={Margffoy-Tuay, Edgar and P{'e}rez, Juan C and Botero, Emilio and Arbel{'a}ez, Pablo}, booktitle={Proceedings of the European Conference on Computer Vision (ECCV)}, pages={630--645}, year={2018} }
@inproceedings{li2018referring, title={Referring image segmentation via recurrent refinement networks}, author={Li, Ruiyu and Li, Kaican and Kuo, Yi-Chun and Shu, Michelle and Qi, Xiaojuan and Shen, Xiaoyong and Jia, Jiaya}, booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition}, pages={5745--5753}, year={2018} }
@inproceedings{yu2018mattnet, title={Mattnet: Modular attention network for referring expression comprehension}, author={Yu, Licheng and Lin, Zhe and Shen, Xiaohui and Yang, Jimei and Lu, Xin and Bansal, Mohit and Berg, Tamara L}, booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition}, pages={1307--1315}, year={2018} }
@inproceedings{liu2017recurrent, title={Recurrent multimodal interaction for referring image segmentation}, author={Liu, Chenxi and Lin, Zhe and Shen, Xiaohui and Yang, Jimei and Lu, Xin and Yuille, Alan}, booktitle={Proceedings of the IEEE international conference on computer vision}, pages={1271--1280}, year={2017} }
@inproceedings{hu2016segmentation, title={Segmentation from natural language expressions}, author={Hu, Ronghang and Rohrbach, Marcus and Darrell, Trevor}, booktitle={Computer Vision--ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11--14, 2016, Proceedings, Part I 14}, pages={108--124}, year={2016}, organization={Springer} }