Discover how deep learning helps robots organize everyday items on tables.
Sanjuksha Nirgude, Kevin DuCharme, Namrita Madhusoodanan
― 6 min read
Computer Science - Computer Vision and Pattern Recognition
RSSAutomated models show promise in accurately segmenting soft tissue tumors from MRI images.
Tahsin Reasat, Stephen Chenard, Akhil Rekulapelli
― 5 min read
FIP enhances model training to prevent harmful data manipulation.
Nazmul Karim, Abdullah Al Arafat, Adnan Siraj Rakin
― 6 min read
New framework enhances machines' ability to understand 3D environments from 2D images.
Anas Mahmoud, Ali Harakeh, Steven Waslander
― 5 min read
Discovering new methods for creating 3D shapes from cross-sections.
Aradhya N. Mathur, Apoorv Khattar, Ojaswa Sharma
― 6 min read
A study on classifying weather conditions in images for better machine recognition.
Eden Ship, Eitan Spivak, Shubham Agarwal
― 7 min read
This article explores how visual features influence our decision-making.
Maytus Piriyajitakonkij, Sirawaj Itthipuripat, Ian Ballard
― 5 min read
A new method enhances fingerprint classification accuracy using fuzzy logic.
Ravi Prakash, Sinnu Susan Thomas
― 5 min read
A fresh model for anticipating indoor human trajectories using geometric and visual data.
Luigi Capogrosso, Andrea Toaiari, Andrea Avogaro
― 5 min read
A new method improves author identification in historical documents using Vision Transformers.
Tim Raven, Arthur Matei, Gernot A. Fink
― 5 min read
A new method for adapting deep learning models to unlabeled data while ensuring privacy.
Andrea Maracani, Lorenzo Rosasco, Lorenzo Natale
― 5 min read
AI helps improve identification of craniofacial anomalies in fetal ultrasounds.
Antonia Alomar, Ricardo Rubio, Laura Salort
― 5 min read
HAR systems improve safety by detecting unusual behaviors in real-time.
Shahriar Jahan, Roknuzzaman, Md Robiul Islam
― 4 min read
A novel reference-free metric improves object removal assessment in image editing.
Aditya Chandrasekar, Goirik Chakrabarty, Jai Bardhan
― 6 min read
New method improves accuracy in remote sensing scene classification using contextual relationships.
Karim El Khoury, Maxime Zanella, Benoît Gérin
― 6 min read
A look at how AI can forget private data during image restoration.
Xin Su, Zhuoran Zheng
― 5 min read
A new approach enhances the merging of satellite images for better analysis.
Ivan Pereira-Sánchez, Eloi Sans, Julia Navarro
― 7 min read
Research aims to improve safety at roundabouts by predicting dilemma zones.
Manthan Chelenahalli Satish, Duo Lu, Bharatesh Chakravarthi
― 6 min read
A look at traditional and deep learning methods for blending image styles.
Xinhe Xu, Zhuoer Wang, Yihan Zhang
― 5 min read
A new system improves accuracy in vehicle digital displays.
Cornelius Bürkle, Fabian Oboril, Kay-Ulrich Scholl
― 7 min read
This study evaluates how well VLMs can understand visual perspectives.
Gracjan Góral, Alicja Ziarko, Michal Nauman
― 5 min read
Research highlights methods to enhance machine learning in autonomous vehicles using video data.
Shawan Mohammed, Alp Argun, Nicolas Bonnotte
― 6 min read
A new framework enhances learning efficiency in visual reinforcement learning.
Jiarui Sun, M. Ugur Akcal, Wei Zhang
― 5 min read
Using advanced machine learning to improve sewer defect detection efficiently.
Daniel Otero, Rafael Mateus
― 6 min read
New methods enhance video transmission by predicting missing data effectively.
John Li, Shehab Sarar Ahmed, Deepak Nair
― 5 min read
EvoChart aims to improve chart understanding for machine learning models.
Muye Huang, Lai Han, Xinyu Zhang
― 5 min read
A novel approach enhances recognition of occluded fruits in farming.
Liang Geng
― 4 min read
Introducing LSSF-Net, a lightweight model for accurate skin lesion segmentation.
Hamza Farooq, Zuhair Zafar, Ahsan Saadat
― 6 min read
This study evaluates how well AI categorizes images compared to humans.
Bin Fu, Qiyang Wan, Jialin Li
― 7 min read
Learn how watermarking secures AI models and supports creators' rights.
Erjin Bao, Ching-Chun Chang, Hanrui Wang
― 4 min read
This study improves sign language video translation through innovative methods.
David Vinicius da Silva, Valter Estevam, David Menotti
― 6 min read
A new method combines 2D and 3D for realistic human videos.
Zhangsihao Yang, Mengyi Shan, Mohammad Farazi
― 6 min read
A novel approach improves image segmentation using limited supervision techniques.
Xuanrui Zeng
― 5 min read
FinePseudo enhances fine-grained action recognition using fewer labeled examples.
Ishan Rajendrakumar Dave, Mamshad Nayeem Rizve, Mubarak Shah
― 6 min read
A new approach enhances video alignment across large datasets.
Ishan Rajendrakumar Dave, Fabian Caba Heilbron, Mubarak Shah
― 9 min read
New regularization method improves heart electrical activity reconstructions from body surface measurements.
Manuel Haas, Thomas Grandits, Thomas Pinetz
― 5 min read
A new dataset aims to track coastal changes in Ireland accurately.
Conor O'Sullivan, Ambrish Kashyap, Seamus Coveney
― 8 min read
This article examines how intrinsic dimension influences neural network performance across image types.
Nicholas Konz, Maciej A. Mazurowski
― 5 min read
A model that improves segmentation of parts and objects in images.
Yunfei Xie, Cihang Xie, Alan Yuille
― 5 min read
A new AI method simplifies chip layout creation with fewer resources.
Guanglei Zhou, Bhargav Korrapati, Gaurav Rajavendra Reddy
― 5 min read