A new method enhances the detection of road hazards for advanced driving systems.
Pang-Yuan Pao, Shu-Wei Lu, Ze-Yan Lu
― 5 min read
Computer Science - Computer Vision and Pattern Recognition
RSSA new method combining models to improve unsupervised domain adaptation in segmentation tasks.
Roberto Alcover-Couso, Juan C. SanMiguel, Marcos Escudero-Viñolo
― 5 min read
This study highlights the importance of object detection in construction zones for self-driving cars.
Abu Shad Ahammed, Md Shahi Amran Hossain, Roman Obermaisser
― 5 min read
DALNet improves image segmentation accuracy using both visual and textual features.
Soojin Jang, Jungmin Yun, Junehyoung Kwon
― 6 min read
This article focuses on identifying data misuse in text-to-image models.
Likun Zhang, Hao Wu, Lingcui Zhang
― 7 min read
LaPose improves object positioning using standard RGB images, addressing key challenges.
Ruida Zhang, Ziqin Huang, Gu Wang
― 5 min read
New models enhance CNN performance against corrupted images using human visual processing methods.
Lucas Piper, Arlindo L. Oliveira, Tiago Marques
― 6 min read
MemFusionMap improves real-time HD mapping using past frame information.
Jingyu Song, Xudong Chen, Liupei Lu
― 7 min read
SCOMatch improves learning from both labeled and unlabeled data in OSSL.
Zerun Wang, Liuyu Xiang, Lang Huang
― 5 min read
A new method enhances diffusion models for better image quality and speed.
Yuchen Liang, Yuchuan Tian, Lei Yu
― 5 min read
D2UE framework improves detection of anomalies in medical images using diverse model approaches.
Yi Gu, Yi Lin, Kwang-Ting Cheng
― 5 min read
TFS-NeRF offers a new method for 3D modeling from videos.
Sandika Biswas, Qianyi Wu, Biplab Banerjee
― 7 min read
Assessing AI performance using survival analysis for reliability against challenges.
Charles Meyers, Mohammad Reza Saleh Sedghpour, Tommy Löfstedt
― 7 min read
AgRegNet offers efficient solutions for estimating flower and fruit counts, enhancing farming practices.
Uddhav Bhattarai, Santosh Bhusal, Qin Zhang
― 5 min read
SGDrop helps CNNs learn better from limited data by broadening their focus.
David Bertoin, Eduardo Hugo Sanchez, Mehdi Zouitine
― 6 min read
A new model enhances wind data analysis for better renewable energy projects.
Alif Bin Abdul Qayyum, Xihaier Luo, Nathan M. Urban
― 5 min read
Harnessing multi-temporal data transforms satellite image analysis for better segmentation.
Kartik Jindgar, Grace W. Lindsay
― 7 min read
A system analyzes worker behavior on assembly lines to improve safety and efficiency.
Konstantinos Papoutsakis, Nikolaos Bakalos, Konstantinos Fragkoulis
― 5 min read
A new algorithm reduces energy consumption in computer vision applications.
Md Abdullah-Al Kaiser, Sreetama Sarkar, Peter A. Beerel
― 6 min read
A new approach to handle data with outliers efficiently.
Lakshmi Jayalal, Gokularam Muthukrishnan, Sheetal Kalyani
― 5 min read
Disco4D generates realistic 3D human figures from a single image.
Hui En Pang, Shuai Liu, Zhongang Cai
― 7 min read
Walker offers efficient object tracking with minimal data labeling.
Mattia Segu, Luigi Piccinelli, Siyuan Li
― 5 min read
A method for creating HDR images from a single photo using intrinsic images.
Sebastian Dille, Chris Careaga, Yağız Aksoy
― 5 min read
AACLiteNet improves detection of abdominal aortic calcification for better heart health.
Zaid Ilyas, Afsah Saleem, David Suter
― 4 min read
A new technique boosts the performance of models combining text and images.
Runpeng Yu, Weihao Yu, Xinchao Wang
― 9 min read
A new model creates audio that matches video, enhancing media experiences.
Ilpo Viertola, Vladimir Iashin, Esa Rahtu
― 4 min read
A method to reveal what deep neural networks learn and how it aligns with existing knowledge.
Mert Keser, Gesina Schwalbe, Niki Amini-Naieni
― 6 min read
Text2CAD uses AI to simplify CAD design through text prompts.
Mohammad Sadil Khan, Sankalp Sinha, Talha Uddin Sheikh
― 6 min read
New method improves recognition of text from images, aiding in handwritten and printed formats.
Raphael Baena, Syrine Kalleli, Mathieu Aubry
― 6 min read
A new approach for clearer visualization and understanding of deep learning models.
Athanasios Karagounis
― 4 min read
Evaluating VLMs on spatial tasks using visual and unclear text.
Bowen Zhao, Leo Parker Dirac, Paulina Varshavskaya
― 6 min read
This study benchmarks DG algorithms to tackle domain shift in medical image analysis.
Neda Zamanitajeddin, Mostafa Jahanifar, Kesi Xu
― 7 min read
A new method reduces false positives in medical imaging segmentations.
Alexander Jaus, Simon Reiß, Jens Kleesiek
― 5 min read
Learn how new methods enhance HDR video from event cameras.
Yunhao Zou, Ying Fu, Tsuyoshi Takatani
― 7 min read
New model creates diverse brain MRI images using physics and machine learning.
Sven Lüpke, Yousef Yeganeh, Ehsan Adeli
― 4 min read
A new framework improves event recognition using event cameras.
Jiazhou Zhou, Kanghao Chen, Lei Zhang
― 6 min read
A new dataset improves how drones find their location without GPS.
Yuxiang Ji, Boyong He, Zhuoyue Tan
― 5 min read
Introducing Hyperbolic Vision Transformers for advanced image classification and analysis.
Jacob Fein-Ashley, Ethan Feng, Minh Pham
― 5 min read
A new method enhances understanding of CNN features and decision-making.
Maren H. Wehrheim, Pamela Osuna-Vargas, Matthias Kaschube
― 8 min read
Researchers develop CHOIR to improve hand-object interaction accuracy.
Théo Morales, Omid Taheri, Gerard Lacey
― 6 min read