Human-Inspired Computer Vision
AttZoom: Attention Zoom for Better Visual Features-
[pdf]
[arXiv]
[bibtex]@InProceedings{DeAlcala_2025_ICCV, author = {DeAlcala, Daniel and Morales, Aythami and Fierrez, Julian and Tolosana, Ruben}, title = {AttZoom: Attention Zoom for Better Visual Features}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2025}, pages = {4834-4843} }
Co-VisiON: Co-Visibility ReasONing on Sparse Image Sets of Indoor Scenes-
[pdf]
[supp]
[bibtex]@InProceedings{Chen_2025_ICCV, author = {Chen, Chao and Dang, Nobel and Zhang, Juexiao and Sun, Wenkai and Zheng, Pengfei and He, Xuhang and Ye, Yimeng and Zhang, Jiasheng and Srinivas, Taarun and Feng, Chen}, title = {Co-VisiON: Co-Visibility ReasONing on Sparse Image Sets of Indoor Scenes}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2025}, pages = {4802-4812} }
Long-Tailed Data Classification by Increasing and Decreasing Neurons During Training-
[pdf]
[arXiv]
[bibtex]@InProceedings{Sakai_2025_ICCV, author = {Sakai, Taigo and Hotta, Kazuhiro}, title = {Long-Tailed Data Classification by Increasing and Decreasing Neurons During Training}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2025}, pages = {4752-4760} }
OscNet v1.5: Energy Efficient Hopfield Network on CMOS Oscillators for Image Classification-
[pdf]
[bibtex]@InProceedings{Cai_2025_ICCV, author = {Cai, Wenxiao and Li, Zongru and Wang, Iris and Wang, Yu-Neng and Lee, Thomas H}, title = {OscNet v1.5: Energy Efficient Hopfield Network on CMOS Oscillators for Image Classification}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2025}, pages = {4733-4741} }
Using Human Perception to Regularize Transfer Learning-
[pdf]
[supp]
[bibtex]@InProceedings{Cruz_2025_ICCV, author = {Cruz, Steve and Dulay, Justin and Scheirer, Walter}, title = {Using Human Perception to Regularize Transfer Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2025}, pages = {4781-4791} }
HiSS: Human-inspired Semantic Segmentation for Vehicle Interior Scene Understanding-
[pdf]
[supp]
[bibtex]@InProceedings{Kostuch_2025_ICCV, author = {Kostuch, Aleksander and Jaworek-Korjakowska, Joanna}, title = {HiSS: Human-inspired Semantic Segmentation for Vehicle Interior Scene Understanding}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2025}, pages = {4792-4801} }
From Neural Activity to Computation: Biological Reservoirs for Pattern Recognition in Digit Classification-
[pdf]
[arXiv]
[bibtex]@InProceedings{Iannello_2025_ICCV, author = {Iannello, Ludovico and Ciampi, Luca and Tonelli, Fabrizio and Lagani, Gabriele and Calcagnile, Lucio M. and Cremisi, Federico and Di Garbo, Angelo and Amato, Giuseppe}, title = {From Neural Activity to Computation: Biological Reservoirs for Pattern Recognition in Digit Classification}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2025}, pages = {4771-4780} }
Exploring Human-Model Alignment in Visual Social Attention During Help-and-Hinder Social Interaction Classification-
[pdf]
[bibtex]@InProceedings{Schiatti_2025_ICCV, author = {Schiatti, Lucia and Vallarino, Guido and Lopez, Sabrina Megan and Kuo, Yen-Ling and Moro, Matteo and Zhang, Mengmi and Gori, Monica and Del Bue, Alessio and Katz, Boris and Barbu, Andrei}, title = {Exploring Human-Model Alignment in Visual Social Attention During Help-and-Hinder Social Interaction Classification}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2025}, pages = {4854-4863} }
SeeEEG: Semantic-aware EEG-based Multi-Modal Retrieval-Augmented Generation for High-Fidelity Visual Brain Decoding-
[pdf]
[supp]
[bibtex]@InProceedings{Kim_2025_ICCV, author = {Kim, Jun-Mo and Choi, Woohyeok and Park, Sang-Jun and Heo, Keun-Soo and Son, Young-Han and Oh, Ji-Hye and Shin, Dong-Hee and Kam, Tae-Eui}, title = {SeeEEG: Semantic-aware EEG-based Multi-Modal Retrieval-Augmented Generation for High-Fidelity Visual Brain Decoding}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2025}, pages = {4824-4833} }
Human-Inspired Summarization: Cluster Scene Videos into Diverse Frames-
[pdf]
[supp]
[bibtex]@InProceedings{Chen_2025_ICCV, author = {Chen, Chao and Zhu, Mingzhi and Singh, Ankush Pratap and Yan, Yu and Juefei-Xu, Felix and Feng, Chen}, title = {Human-Inspired Summarization: Cluster Scene Videos into Diverse Frames}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2025}, pages = {4813-4823} }
Human Vision Constrained Super-Resolution-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Karpenko_2025_ICCV, author = {Karpenko, Volodymyr and Tariq, Taimoor and Condor, Jorge and Didyk, Piotr}, title = {Human Vision Constrained Super-Resolution}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2025}, pages = {4742-4751} }
Towards Human-Like Invariance: Self-Supervised Learning with Feature-Level Rotation Alignment-
[pdf]
[supp]
[bibtex]@InProceedings{Han_2025_ICCV, author = {Han, Sangjun and Cheong, Woojin and Song, Chang Hoon and Kang, Myungjoo}, title = {Towards Human-Like Invariance: Self-Supervised Learning with Feature-Level Rotation Alignment}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2025}, pages = {4761-4770} }
Who Walks With You Matters: Perceiving Social Interactions with Groups for Pedestrian Trajectory Prediction-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zou_2025_ICCV, author = {Zou, Ziqian and Wong, Conghao and Xia, Beihao and You, Xinge}, title = {Who Walks With You Matters: Perceiving Social Interactions with Groups for Pedestrian Trajectory Prediction}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2025}, pages = {4844-4853} }