Results 31 to 40 of about 228 (66)
Some of the next articles are maybe not open access.
Journal of Imaging
Accurate segmentation and classification of kidney pathologies from medical images remain a major challenge in computer-aided diagnosis due to complex morphological variations, small lesion sizes, and severe class imbalance.
H. Tekin, Şafak Kılıç, Yahya Doğan
semanticscholar +1 more source
Accurate segmentation and classification of kidney pathologies from medical images remain a major challenge in computer-aided diagnosis due to complex morphological variations, small lesion sizes, and severe class imbalance.
H. Tekin, Şafak Kılıç, Yahya Doğan
semanticscholar +1 more source
HOIGPT: Learning Long-Sequence Hand-Object Interaction with Language Models
Computer Vision and Pattern RecognitionWe introduce HOIGPT, a token-based generative method that unifies 3D hand-object interactions (HOI) perception and generation, offering the first comprehensive solution for captioning and generating high-quality 3D HOI sequences from a diverse range of ...
Mingzhen Huang +12 more
semanticscholar +1 more source
The Energy Impact of Domain Model Design in Classical Planning
arXiv.orgAI research has traditionally prioritised algorithmic performance, such as optimising accuracy in machine learning or runtime in automated planning.
Ilche Georgievski +2 more
semanticscholar +1 more source
Vector Optimization with Gaussian Process Bandits
Machine-mediated learningWe study black-box vector optimization with Gaussian process bandits, where there is an incomplete order relation on objective vectors described by a polyhedral convex cone.
Ilter Onat Korkmaz +3 more
semanticscholar +1 more source
Encounters with the Posthuman and the Environment
With the advent of posthumanism, many scholars in the humanities have started to explore a transforming conception of the “human,” recognizing the limits of “anthropocentricism” both within and between disciplines.
İ. Tekin, Z. Turner
semanticscholar +1 more source
Memory-efficient Streaming VideoLLMs for Real-time Procedural Video Understanding
arXiv.orgWe introduce ProVideLLM, an end-to-end framework for real-time procedural video understanding. ProVideLLM integrates a multimodal cache configured to store two types of tokens - verbalized text tokens, which provide compressed textual summaries of long ...
Dibyadip Chatterjee +11 more
semanticscholar +1 more source
HuMoCon: Concept Discovery for Human Motion Understanding
Computer Vision and Pattern RecognitionWe present HuMoCon, a novel motion-video understanding framework designed for advanced human behavior analysis. The core of our method is a human motion concept discovery framework that efficiently trains multi-modal encoders to extract semantically ...
Qihang Fang +4 more
semanticscholar +1 more source
Genetics in Medicine
Purpose The Undiagnosed Diseases Network (UDN) is a National Institutes of Health funded research study that aims to solve a broad clinical spectrum of challenging rare disease cases.
S. Fazal +19 more
semanticscholar +1 more source
Purpose The Undiagnosed Diseases Network (UDN) is a National Institutes of Health funded research study that aims to solve a broad clinical spectrum of challenging rare disease cases.
S. Fazal +19 more
semanticscholar +1 more source
Gene42: Long-Range Genomic Foundation Model With Dense Attention
arXiv.orgWe introduce Gene42, a novel family of Genomic Foundation Models (GFMs) designed to manage context lengths of up to 192,000 base pairs (bp) at a single-nucleotide resolution.
Kirill Vishniakov +14 more
semanticscholar +1 more source
Robust Few-Shot Ensemble Learning with Focal Diversity-Based Pruning
ACM Transactions on Intelligent Systems and TechnologyThis article presents FusionShot, a focal diversity-optimized few-shot ensemble learning approach for boosting the robustness and generalization performance of pre-trained few-shot models. The article makes three original contributions. First, we explore
S. Tekin +6 more
semanticscholar +1 more source