7 papers
Utilising physics-guided deep learning to overcome data scarcity
Jinshuai Bai, Laith Alzubaidi, Qingxia Wang +3
Deep learning (DL) relies heavily on data, and the quality of data influences its performance significantly. However, obtaining high-quality, well-annotated datasets can be challen…
HOPE: A Memory-Based and Composition-Aware Framework for Zero-Shot Learning with Hopfield Network and Soft Mixture of Experts
Do Huu Dat, Po Yuan Mao, Tien Hoang Nguyen +2
Compositional Zero-Shot Learning (CZSL) has emerged as an essential paradigm in machine learning, aiming to overcome the constraints of traditional zero-shot learning by incorporat…
Dynamic Neural Surfaces for Elastic 4D Shape Representation and Analysis
Awais Nizamani, Hamid Laga, Guanjin Wang +3
We propose a novel framework for the statistical analysis of genus-zero 4D surfaces, i.e., 3D surfaces that deform and evolve over time. This problem is particularly challenging du…
Generalized Closed-form Formulae for Feature-based Subpixel Alignment in Patch-based Matching
Laurent Valentin Jospin, Farid Boussaid, Hamid Laga +1
Cost-based image patch matching is at the core of various techniques in computer vision, photogrammetry and remote sensing. When the subpixel disparity between the reference patch…
UIFormer: A Unified Transformer-based Framework for Incremental Few-Shot Object Detection and Instance Segmentation
Chengyuan Zhang, Yilin Zhang, Lei Zhu +6
This paper introduces a novel framework for unified incremental few-shot object detection (iFSOD) and instance segmentation (iFSIS) using the Transformer architecture. Our goal is…
Referring Human Pose and Mask Estimation in the Wild
Bo Miao, Mingtao Feng, Zijie Wu +3
We introduce Referring Human Pose and Mask Estimation (R-HPM) in the wild, where either a text or positional prompt specifies the person of interest in an image. This new task hold…