5th Workshop on Robot Visual Perception in Human Crowded Environments
GM-DETR: Generalized Muiltispectral DEtection TRansformer with Efficient Fusion Encoder for Visible-Infrared Detection-
[pdf]
[bibtex]@InProceedings{Xiao_2024_CVPR, author = {Xiao, Yiming and Meng, Fanman and Wu, Qingbo and Xu, Linfeng and He, Mingzhou and Li, Hongliang}, title = {GM-DETR: Generalized Muiltispectral DEtection TRansformer with Efficient Fusion Encoder for Visible-Infrared Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2024}, pages = {5541-5549} }
HumanFormer: Human-centric Prompting Multi-modal Perception Transformer for Referring Crowd Detection-
[pdf]
[bibtex]@InProceedings{Qiu_2024_CVPR, author = {Qiu, Heqian and Wang, Lanxiao and Zhao, Taijin and Meng, Fanman and Li, Hongliang}, title = {HumanFormer: Human-centric Prompting Multi-modal Perception Transformer for Referring Crowd Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2024}, pages = {5530-5540} }
Is Our Continual Learner Reliable? Investigating Its Decision Attribution Stability through SHAP Value Consistency-
[pdf]
[bibtex]@InProceedings{Cai_2024_CVPR, author = {Cai, Yusong and Ling, Shimou and Zhang, Liang and Pan, Lili and Li, Hongliang}, title = {Is Our Continual Learner Reliable? Investigating Its Decision Attribution Stability through SHAP Value Consistency}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2024}, pages = {5568-5575} }
Pre-trained Bidirectional Dynamic Memory Network For Long Video Question Answering-
[pdf]
[bibtex]@InProceedings{Wu_2024_CVPR, author = {Wu, Jinmeng and Shu, Pengcheng and Hong, Hanyu and Ma, Lei and Zhu, Ying and Wang, Lei}, title = {Pre-trained Bidirectional Dynamic Memory Network For Long Video Question Answering}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2024}, pages = {5550-5557} }
Must Unsupervised Continual Learning Relies on Previous Information?-
[pdf]
[bibtex]@InProceedings{Cheng_2024_CVPR, author = {Cheng, Haoyang and Wen, Haitao and Qiu, Heqian and Wang, Lanxiao and Zhang, Minjian and Li, Hongliang}, title = {Must Unsupervised Continual Learning Relies on Previous Information?}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2024}, pages = {5519-5529} }
DSTCFuse: A Method based on Dual-cycled Cross-awareness of Structure Tensor for Semantic Segmentation via Infrared and Visible Image Fusion-
[pdf]
[bibtex]@InProceedings{Li_2024_CVPR, author = {Li, Xuan and Chen, Rongfu and Wang, Jie and Ma, Lei and Cheng, Li and Yuan, Haiwen}, title = {DSTCFuse: A Method based on Dual-cycled Cross-awareness of Structure Tensor for Semantic Segmentation via Infrared and Visible Image Fusion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2024}, pages = {5558-5567} }
InViG: Benchmarking Open-Ended Interactive Visual Grounding with 500K Dialogues-
[pdf]
[bibtex]@InProceedings{Zhang_2024_CVPR, author = {Zhang, Hanbo and Xu, Jie and Mo, Yuchen and Kong, Tao}, title = {InViG: Benchmarking Open-Ended Interactive Visual Grounding with 500K Dialogues}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2024}, pages = {5508-5518} }