LATEC offers a robust evaluation of XAI methods for better AI transparency.
Lukas Klein, Carsten T. Lüth, Udo Schlegel
― 7 min read
Computer Science - Computer Vision and Pattern Recognition
RSSDiscover what makes certain images captivating and appealing across different audiences.
Fitim Abdullahu, Helmut Grabner
― 6 min read
New approaches in HAR improve activity recognition using smartphone data.
Ning Sun, Yufei Wang, Yuwei Zhang
― 5 min read
Introducing CLIPFit, a method for efficient fine-tuning of Vision-Language Models.
Ming Li, Jike Zhong, Chenxin Li
― 6 min read
Skyeyes generates detailed ground views from aerial images for various applications.
Zhiyuan Gao, Wenbin Teng, Gonglin Chen
― 6 min read
Introducing a new method to improve deep learning models by reducing overfitting.
Bum Jun Kim, Sang Woo Kim
― 5 min read
New methods improve low-light image quality using semi-supervised learning.
Guanlin Li, Ke Zhang, Ting Wang
― 7 min read
Discover how DoSSR improves image quality efficiently and effectively.
Qinpeng Cui, Yixuan Liu, Xinyi Zhang
― 4 min read
DeBaRA helps create realistic room layouts using advanced technology.
Léopold Maillard, Nicolas Sereyjol-Garros, Tom Durand
― 4 min read
A3 framework enhances machine learning models for adapting to new data environments.
Chrisantus Eze, Christopher Crick
― 6 min read
New method improves MRI image quality and speed.
Chinmay Rao, Matthias van Osch, Nicola Pezzotti
― 7 min read
A new method enhances texture quality and consistency for 3D models using text prompts.
Jiawei Lu, Yingpeng Zhang, Zengjun Zhao
― 5 min read
YOSS uses audio to improve object identification in images.
Wenhao Yang, Jianguo Wei, Wenhuan Lu
― 4 min read
MultiClimate dataset reveals public stances on climate change through videos.
Jiawen Wang, Longfei Zuo, Siyao Peng
― 6 min read
A new method simplifies autonomous driving systems for real-world applications.
Peidong Li, Dixiao Cui
― 6 min read
FeDETR uses federated learning for improved coronary stenosis evaluation.
Raffaele Mineo, Amelia Sorrenti, Federica Proietto Salanitri
― 6 min read
An overview of various methods for merging models to enhance machine learning performance.
Derek Tam, Yash Kant, Brian Lester
― 8 min read
Introducing Wavelet-CLIP for improved detection of deepfake images.
Lalith Bharadwaj Baru, Shilhora Akshay Patel, Rohit Boddeda
― 5 min read
SOAR improves action recognition accuracy in drone footage analysis.
Ruiqi Xian, Xiyang Wu, Tianrui Guan
― 5 min read
New methods improve MRI image quality and reduce scanning time.
Qi Chen, Xiaohan Xing, Zhen Chen
― 6 min read
Introducing AdaGauss to enhance learning without retaining older data.
Grzegorz Rypeść, Sebastian Cygert, Tomasz Trzciński
― 5 min read
Omni6D dataset enhances object pose estimation with diverse categories and realistic scenarios.
Mengchen Zhang, Tong Wu, Tai Wang
― 6 min read
A new approach improves AI's ability to handle unusual data.
Debargha Ganguly, Debayan Gupta, Vipin Chaudhary
― 6 min read
A new training strategy improves 3D vision systems’ resistance to misleading inputs.
Nastaran Darabi, Dinithi Jayasuriya, Devashri Naik
― 5 min read
A new framework enhances motion tracking using wearables and egocentric videos.
Fangzhou Hong, Vladimir Guzov, Hyo Jin Kim
― 7 min read
LLaVA-3D combines 2D and 3D insights for deeper spatial reasoning.
Chenming Zhu, Tai Wang, Wenwei Zhang
― 6 min read
New method helps robots learn tasks by watching human demonstrations.
Justin Kerr, Chung Min Kim, Mingxuan Wu
― 5 min read
A new benchmark pushes boundaries in video understanding by focusing on event-level tasks.
Ye Liu, Zongyang Ma, Zhongang Qi
― 4 min read
A new method tracks rhinos using their waste locations to combat poaching.
Lucia Gordon, Nikhil Behari, Samuel Collier
― 7 min read
MALPOLON provides accessible species distribution modeling for researchers and ecologists.
Theo Larcher, Lukas Picek, Benjamin Deneu
― 5 min read
Combining AI and AR enhances satellite assembly, boosting accuracy and efficiency.
Alvaro Patricio, Joao Valente, Atabak Dehban
― 6 min read
Study examines self-supervised learning methods to enhance cardiovascular imaging.
Rob A. J. de Mooij, Josien P. W. Pluim, Cian M. Scannell
― 5 min read
Introducing EfficientCrackNet for safer infrastructure through accurate crack detection.
Abid Hasan Zim, Aquib Iqbal, Zaid Al-Huda
― 5 min read
Innovative methods enhance understanding of surroundings for self-driving vehicles.
Helin Cao, Sven Behnke
― 6 min read
ECHO framework improves sound classification accuracy using structured labels and a two-stage learning process.
Pranav Gupta, Raunak Sharma, Rashmi Kumari
― 5 min read
A framework to identify and reduce biases in visual data for AI models.
Rwiddhi Chakraborty, Yinong Wang, Jialu Gao
― 7 min read
EMOVA enhances human-computer interaction through emotional expression.
Kai Chen, Yunhao Gou, Runhui Huang
― 5 min read
A new model improves early detection of lung nodules.
Guohui Cai, Ying Cai, Zeyu Zhang
― 4 min read
Exploring the use of synthetic data to enhance DRL in real-world applications.
Jacopo Dapueto, Nicoletta Noceti, Francesca Odone
― 8 min read
InterNet enhances homography estimation by learning from images without labeled data.
Junchen Yu, Si-Yuan Cao, Runmin Zhang
― 4 min read