2024-05-04.md

[UPDATED!] 2024-05-04 (Publish Time)

生成模型

Publish Date	Title	Title_CN	Authors	PDF	Code
2024-05-04	Towards a Scalable Identification of Novel Modes in Generative Models	迈向生成模型中新模式的可扩展识别	Jingwei Zhang, Mohammad Jalali, Cheuk Ting Li, Farzan Farnia	http://arxiv.org/pdf/2405.02700v1	null
2024-05-04	Vision-based 3D occupancy prediction in autonomous driving: a review and outlook	自动驾驶中基于视觉的 3D 占用预测：回顾与展望	Yanan Zhang, Jinqing Zhang, Zengran Wang, Junhao Xu, Di Huang	http://arxiv.org/pdf/2405.02595v1	link

多模态

Publish Date	Title	Title_CN	Authors	PDF	Code
2024-05-04	MMEarth: Exploring Multi-Modal Pretext Tasks For Geospatial Representation Learning	MMEarth：探索地理空间表示学习的多模态借口任务	Vishal Nedungadi, Ankit Kariryaa, Stefan Oehmcke, Serge Belongie, Christian Igel, Nico Lang	http://arxiv.org/pdf/2405.02771v1	null
2024-05-04	Beyond Unimodal Learning: The Importance of Integrating Multiple Modalities for Lifelong Learning	超越单模态学习：整合多种模态对于终身学习的重要性	Fahad Sarfraz, Bahram Zonooz, Elahe Arani	http://arxiv.org/pdf/2405.02766v1	null
2024-05-04	AFter: Attention-based Fusion Router for RGBT Tracking	AFter：用于 RGBT 跟踪的基于注意力的融合路由器	Andong Lu, Wanyu Wang, Chenglong Li, Jin Tang, Bin Luo	http://arxiv.org/pdf/2405.02717v1	link

Nerf

Publish Date	Title	Title_CN	Authors	PDF	Code
2024-05-04	TK-Planes: Tiered K-Planes with High Dimensional Feature Vectors for Dynamic UAV-based Scenes	TK-Planes：用于动态无人机场景的具有高维特征向量的分层 K 平面	Christopher Maxey, Jaehoon Choi, Yonghan Lee, Hyungtae Lee, Dinesh Manocha, Heesung Kwon	http://arxiv.org/pdf/2405.02762v1	null
2024-05-04	ActiveNeuS: Active 3D Reconstruction using Neural Implicit Surface Uncertainty	ActiveNeuS：使用神经隐式表面不确定性进行主动 3D 重建	Hyunseo Kim, Hyeonseo Yang, Taekyung Kim, YoonSung Kim, Jin-Hwa Kim, Byoung-Tak Zhang	http://arxiv.org/pdf/2405.02568v1	null

分类/检测/识别/分割/...

Publish Date	Title	Title_CN	Authors	PDF	Code
2024-05-04	Deep Image Restoration For Image Anti-Forensics	图像反取证的深度图像恢复	Eren Tahir, Mert Bal	http://arxiv.org/pdf/2405.02751v1	link
2024-05-04	Stable Diffusion Dataset Generation for Downstream Classification Tasks	用于下游分类任务的稳定扩散数据集生成	Eugenio Lomurno, Matteo D'Oria, Matteo Matteucci	http://arxiv.org/pdf/2405.02698v1	null
2024-05-04	Boosting 3D Neuron Segmentation with 2D Vision Transformer Pre-trained on Natural Images	使用在自然图像上预训练的 2D Vision Transformer 增强 3D 神经元分割	Yik San Cheng, Runkai Zhao, Heng Wang, Hanchuan Peng, Weidong Cai	http://arxiv.org/pdf/2405.02686v1	null
2024-05-04	Position Paper: Quo Vadis, Unsupervised Time Series Anomaly Detection?	立场文件：Quo Vadis，无监督时间序列异常检测？	M. Saquib Sarfraz, Mei-Yen Chen, Lukas Layer, Kunyu Peng, Marios Koulakis	http://arxiv.org/pdf/2405.02678v1	null
2024-05-04	A Conformal Prediction Score that is Robust to Label Noise	对噪声标签具有鲁棒性的保形预测分数	Coby Penso, Jacob Goldberger	http://arxiv.org/pdf/2405.02648v1	null
2024-05-04	UnSAMFlow: Unsupervised Optical Flow Guided by Segment Anything Model	UnSAMFlow：由分段任意模型引导的无监督光流	Shuai Yuan, Lei Luo, Zhuo Hui, Can Pu, Xiaoyu Xiang, Rakesh Ranjan, Denis Demandolx	http://arxiv.org/pdf/2405.02608v1	link
2024-05-04	Better YOLO with Attention-Augmented Network and Enhanced Generalization Performance for Safety Helmet Detection	具有注意力增强网络和增强安全头盔检测泛化性能的更好 YOLO	Shuqi Shen, Junjie Yang	http://arxiv.org/pdf/2405.02591v1	null
2024-05-04	Leveraging the Human Ventral Visual Stream to Improve Neural Network Robustness	利用人类腹侧视觉流提高神经网络的鲁棒性	Zhenan Shao, Linjian Ma, Bo Li, Diane M. Beck	http://arxiv.org/pdf/2405.02564v1	null
2024-05-04	Few-Shot Fruit Segmentation via Transfer Learning	通过迁移学习进行少样本水果分割	Jordan A. James, Heather K. Manching, Amanda M. Hulse-Kemp, William J. Beksi	http://arxiv.org/pdf/2405.02556v1	null
2024-05-04	AdaFPP: Adapt-Focused Bi-Propagating Prototype Learning for Panoramic Activity Recognition	AdaFPP：用于全景活动识别的以适应为中心的双向传播原型学习	Meiqi Cao, Rui Yan, Xiangbo Shu, Guangzhao Dai, Yazhou Yao, Guo-Sen Xie	http://arxiv.org/pdf/2405.02538v1	null

Transformer

Publish Date	Title	Title_CN	Authors	PDF	Code
2024-05-04	U-DiTs: Downsample Tokens in U-Shaped Diffusion Transformers	U-DiTs：U 形扩散变压器中的下采样令牌	Yuchuan Tian, Zhijun Tu, Hanting Chen, Jie Hu, Chao Xu, Yunhe Wang	http://arxiv.org/pdf/2405.02730v1	null
2024-05-04	Diffeomorphic Transformer-based Abdomen MRI-CT Deformable Image Registration	基于微分同形变压器的腹部 MRI-CT 变形图像配准	Yang Lei, Luke A. Matkovic, Justin Roper, Tonghe Wang, Jun Zhou, Beth Ghavidel, Mark McDonald, Pretesh Patel, Xiaofeng Yang	http://arxiv.org/pdf/2405.02692v1	null
2024-05-04	ViTALS: Vision Transformer for Action Localization in Surgical Nephrectomy	ViTALS：用于肾切除手术中动作定位的视觉转换器	Soumyadeep Chandra, Sayeed Shafayet Chowdhury, Courtney Yong, Chandru P. Sundaram, Kaushik Roy	http://arxiv.org/pdf/2405.02571v1	null

各类学习方式

Publish Date	Title	Title_CN	Authors	PDF	Code
2024-05-04	Generalizing CLIP to Unseen Domain via Text-Guided Diverse Novel Feature Synthesis	通过文本引导的多样化新颖特征合成将 CLIP 推广到看不见的领域	Siyuan Yan, Cheng Luo, Zhen Yu, Zongyuan Ge	http://arxiv.org/pdf/2405.02586v1	null

其他

Publish Date	Title	Title_CN	Authors	PDF	Code
2024-05-04	Hand-Object Interaction Controller (HOIC): Deep Reinforcement Learning for Reconstructing Interactions with Physics	手-物体交互控制器（HOIC）：用于重建物理交互的深度强化学习	Haoyu Hu, Xinyu Yi, Zhe Cao, Jun-Hai Yong, Feng Xu	http://arxiv.org/pdf/2405.02676v1	link
2024-05-04	Deep Pulse-Signal Magnification for remote Heart Rate Estimation in Compressed Videos	用于压缩视频中远程心率估计的深度脉冲信号放大	Joaquim Comas, Adria Ruiz, Federico Sukno	http://arxiv.org/pdf/2405.02652v1	null
2024-05-04	Stationary Representations: Optimally Approximating Compatibility and Implications for Improved Model Replacements	平稳表示：最佳近似兼容性和改进模型替换的含义	Niccolò Biondi, Federico Pernici, Simone Ricci, Alberto Del Bimbo	http://arxiv.org/pdf/2405.02581v1	link