Subscribe to this collection to receive daily e-mail notification of new additions

	Title	Author(s)	Issue Date	Views
	Real-time end-to-end video text spotter with contrastive representation learning Proceeding/Conference:Proceedings of the European Conference on Computer Vision (ECCV)	Wu, WLi, ZLi, JShen, CZhou, HGao, TWang, ZLuo, P	2022	5
	Restoreformer: High-quality blind face restoration from undegraded key-value pairs Proceeding/Conference:Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022	Wang, ZZhang, JChen, RWang, WLuo, P	2022	4
	Panoptic segformer: Delving deeper into panoptic segmentation with transformers Proceeding/Conference:Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022	Li, ZWang, WXie, EYu, ZAnandkumar, AAlvarez, JMLuo, PLu, T	2022
	Davit: Dual attention vision transformers	Ding, MXiao, BCodella, NLuo, PYuan, L	2022	5
	Towards ultra-resolution neural style transfer via thumbnail instance normalization Proceeding/Conference:Proceedings of the AAAI Conference on Artificial Intelligence (AAAI)	Chen, ZWang, WXie, ELuo, P	2022	2
	Cyclemlp: A MLP-like architecture for dense prediction Proceeding/Conference:International Conference on Learning Representation (ICLR), Oral	Chen, SXie, EGe, CLiang, DYLuo, P	2022	3
	Pyramid vision transformer: A versatile backbone for dense prediction without convolutions Proceeding/Conference:Proceedings: 2021 IEEE/CVF International Conference on Computer Vision: ICCV 2021, 11-17 October 2021, Virtual event	Wang, WXie, ELi, XFan, DPSong, KLiang, DLu, TLuo, PShao, L	2021	3
	Dynamic token normalization improves vision transformer Proceeding/Conference:Advances in Neural Information Processing Systems (NeurlPS)	Shao, WGe, YZhang, ZXu, XWang, XShan, YLuo, P	2022	2
	Bringing events into video deblurring with non-consecutively blurry frames Proceeding/Conference:Advances In Neural Information Processing Systems: 35th conference on neural information processing systems (NeurIPS 2021)	Shang, WRen, DZou, DRen, SLuo, PZuo, W	2021	3
	Compressed video contrastive learning Proceeding/Conference:Advances in Neural Information Processing Systems 34 (NeurIPS 2021)	Huo, YDing, MLu, HFei, NLu, ZWen, JLuo, P	2021	4
	Dynamic visual reasoning by learning differentiable physics models from video and language Proceeding/Conference:Advances In Neural Information Processing Systems: 35th conference on neural information processing systems (NeurIPS 2021)	Ding, MChen, ZDu, TLuo, PTenenbaum, JGan, C	2021	3
	Watch only once: An end-to-end video action detection framework Proceeding/Conference:Proceedings: 2021 IEEE/CVF International Conference on Computer Vision: ICCV 2021	Chen, SSun, PXie, EGe, CWu, JMa, LShen, JLuo, P	2021
	Not all tokens are equal: Human-centric visual analysis via token clustering transformer Proceeding/Conference:Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022	Zeng, WJin, SLiu, WQian, CLuo, POuyang, WWang, X	2022	3
	Rethinking the pruning criteria for convolutional neural network Proceeding/Conference:Advances In Neural Information Processing Systems: 35th conference on neural information processing systems (NeurIPS 2021)	Huang, ZShao, WWang, XLin, LLuo, P	2021	4
	Objects in semantic topology Proceeding/Conference:International Conference on Learning Representation (ICLR)	Yang, SSun, PJiang, YXia, XZhang , RYuan, ZWang, CLuo, PXu, M	2022
	PoseTrans: A Simple Yet Effective Pose Transformation Augmentation for Human Pose Estimation Proceeding/Conference:Proceedings of the European Conference on Computer Vision (ECCV), 2022	Jiang, WJin, SLiu, WQian, CLuo, PLiu, S	2022	17
	Segformer: Simple and efficient design for semantic segmentation with transformers Proceeding/Conference:Advances In Neural Information Processing Systems: 35th conference on neural information processing systems (NeurIPS 2021)	Xie, EWang, WYu, ZAnandkumar, AAlvarez, JMLuo, P	2021	6
	Don’t touch what matters: Task-aware lipschitz data augmentationfor visual reinforcement learning Proceeding/Conference:Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, Vienna, 23-29 July 2022	Yuan, ZMa, GMu, YXia, BYuan, BWang, XLuo, PXu, H	2022	3
	Miles: Visual bert pre-training with injected language semantics for video-text retrieval	Ge, YGe, YLiu, XWang, JAWu, JShan, YQie, XLuo, P	2022	3
	Bridging video-text retrieval with multiple choice questions Proceeding/Conference:Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022	Ge, YGe, YLiu, DLi, DShan, YQie, XLuo, P	2022