Balancing privacy and performance in AI through innovative unlearning techniques.
Dasol Choi, Dongbin Na
― 6 min read
Computer Science - Computer Vision and Pattern Recognition
RSSEVA combines audio and visual signals for better speech recognition accuracy.
Yihan Wu, Yifan Peng, Yichen Lu
― 4 min read
PPNG offers a compact way to capture and share 3D visuals easily.
Jae Yong Lee, Yuqun Wu, Chuhang Zou
― 6 min read
New datasets and models improve pest and disease detection in trees and crops.
Mingle Zhou, Rui Xing, Delong Han
― 7 min read
New methods enhance the accuracy of identifying blood vessels in medical images.
Amine Sadikine, Bogdan Badic, Enzo Ferrante
― 5 min read
This article discusses the effectiveness of Structure from Motion for accurate 3D modeling.
Francisco Roza de Moraes, Irineu da Silva
― 5 min read
A new method improves how robots explore structured indoor spaces.
Cherie Ho, Seungchan Kim, Brady Moon
― 5 min read
An automated model enhances the creation of multi-organ pathology reports.
Jing Wei Tan, SeungKyu Kim, Eunsu Kim
― 5 min read
A new method enhances liver vessel segmentation in medical imaging.
Amine Sadikine, Bogdan Badic, Jean-Pierre Tasu
― 5 min read
A new method speeds up diffusion models while maintaining image quality.
Alireza Ganjdanesh, Yan Kang, Yuchen Liu
― 6 min read
A new approach combines LiDAR and cameras for better detection accuracy.
Vanshika Vats, Marzia Binta Nizam, James Davis
― 6 min read
New methods enhance object location tracking in dense urban areas.
Tavis Shore, Oscar Mendez, Simon Hadfield
― 6 min read
This study examines how people differentiate between real and AI-generated faces.
Jin Huang, Subhadra Gopalakrishnan, Trisha Mittal
― 5 min read
Llama-AVSR merges audio and visual inputs for enhanced speech recognition accuracy.
Umberto Cappellazzo, Minsu Kim, Honglie Chen
― 6 min read
A system enabling robots to explore and update indoor maps autonomously.
Sai Haneesh Allu, Itay Kadosh, Tyler Summers
― 6 min read
Introducing adjustable kernels for improved 3D shape reconstruction from limited data.
Maximilian Weiherer, Bernhard Egger
― 5 min read
A novel model combining VAE and QWGAN improves image quality and variety.
Aaron Mark Thomas, Sharu Theresa Jose
― 5 min read
New method improves the accuracy of medical image analysis.
Sebastian Doerrich, Francesco Di Salvo, Christian Ledig
― 5 min read
A new tool evaluates large language models' performance across multiple data types.
Yizhi Li, Ge Zhang, Yinghao Ma
― 5 min read
Using AI to improve lesion detection in cancer imaging.
Shadab Ahamed
― 5 min read
A new method improves 3D reconstruction of people in loose garments.
Chen Guo, Tianjian Jiang, Manuel Kaufmann
― 5 min read
This article examines methods to improve UDA performance in image classification tasks.
Tarun Kalluri, Sreyas Ravichandran, Manmohan Chandraker
― 6 min read
ZeroSCD detects changes in images without requiring prior training or labeled data.
Shyam Sundar Kannan, Byung-Cheol Min
― 6 min read
Robot dogs may transform construction site monitoring and data collection.
Miguel Arturo Vega Torres, Fabian Pfitzner
― 5 min read
New methods using language models enhance data processing in Earth observation systems.
Hong-fu Chou, Vu Nguyen Ha, Prabhu Thiruvasagam
― 6 min read
Researchers improve tumor segmentation in PET/CT images using automated methods.
Hamza Kalisch, Fabian Hörst, Ken Herrmann
― 5 min read
A new dataset and framework for generating engaging comments on Chinese videos.
Yuyan Chen, Yiwen Qian, Songzhou Yan
― 6 min read
New imaging system improves solar energy forecasting by tracking cloud movements.
Leron Julian, Haejoon Lee, Soummya Kar
― 7 min read
A new method improves accuracy in segmenting RGB-D images with depth errors.
Minh Bui, Kostas Alexis
― 6 min read
A new database and technique improve drone tracking without manual labeling.
Yu-Hsi Chen
― 4 min read
An event to improve image segmentation models for safer self-driving cars.
Tuan-Hung Vu, Eduardo Valle, Andrei Bursuc
― 5 min read
Learn about new methods for improving microscopy image clarity using AI.
Harshith Bachimanchi, Giovanni Volpe
― 7 min read
Region Mixup enhances training data diversity for better model performance.
Saptarshi Saha, Utpal Garain
― 5 min read
A new method improves change detection using labeled and unlabeled data.
Yan Xing, Qi'ao Xu, Jingcheng Zeng
― 5 min read
This study enhances key information extraction using a new model for unstructured documents.
Furkan Pala, Mehmet Yasin Akpınar, Onur Deniz
― 9 min read
New method improves depth map accuracy using multiple viewpoints.
Jungeon Kim, Soongjin Kim, Jaesik Park
― 6 min read
A new system for creating dance camera movements synchronized with music.
Zixuan Wang, Jiayi Li, Xiaoyu Qin
― 4 min read
Improving traffic sign detection for safer autonomous vehicles with few-shot learning methods.
Md. Atiqur Rahman, Nahian Ibn Asad, Md. Mushfiqul Haque Omi
― 6 min read
Adaptive attention techniques boost performance and reduce resource demands in LVLMs.
Junyang Zhang, Mu Yuan, Ruiguang Zhong
― 5 min read
Learn about deep learning techniques for automatically blurring faces in video recordings.
Roman Plaud, Jose-Luis Lisani
― 6 min read