Results 61 to 70 of about 2,605 (177)

Splattalk: 3D VQA with Gaussian Splatting

open access: yes2025 IEEE/CVF International Conference on Computer Vision (ICCV)
Language-guided 3D scene understanding is important for advancing applications in robotics, AR/VR, and human-computer interaction, enabling models to comprehend and interact with 3D environments through natural language. While 2D vision-language models (VLMs) have achieved remarkable success in 2D VQA tasks, progress in the 3D domain has been ...
Anh Thai   +4 more
openaire   +2 more sources

Efficient Few‐Shot Learning in Remote Sensing: Fusing Vision and Vision‐Language Models

open access: yesApplied AI Letters, Volume 7, Issue 1, February 2026.
ABSTRACT Remote sensing has become a vital tool across sectors such as urban planning, environmental monitoring, and disaster response. Although the volume of data generated has increased significantly, traditional vision models are often constrained by the requirement for extensive domain‐specific labelled data and their limited ability to understand ...
Jia Yun Chua   +2 more
wiley   +1 more source

Curriculum learning effectively improves low data VQA [PDF]

open access: yes, 2021
Visual question answering (VQA) models, in particular modular ones, are commonly trained on large-scale datasets to achieve state of the art performance. However, such datasets are sometimes not available.
Askarian, Narjes   +4 more
core  

Proton stereotactic body radiotherapy for early‐stage non‐small cell lung cancer: Influence of case‐specific characteristics on dosimetric robustness

open access: yesJournal of Applied Clinical Medical Physics, Volume 27, Issue 1, January 2026.
Abstract Background and purpose Proton stereotactic body radiotherapy (SBRT) offers superior dose conformity. However, its clinical application remains limited due to uncertainties from setup errors and respiratory motion. This study quantified the dosimetric robustness of proton SBRT for early‐stage non‐small cell lung cancer under combined setup and ...
Akihiro Yamano   +9 more
wiley   +1 more source

Analysing human vs. neural attention in VQA [PDF]

open access: yes
Visual Question Answering (VQA) has drawn substantial interest in both academic and industrial research fields in recent years. Driven by Vision Transformers (ViT) and the vision-text co-attention mechanism, these models have shown notable performance ...
Ma, Yingpeng
core   +1 more source

Zero-Shot Transfer VQA Dataset

open access: yesCoRR, 2018
Acquiring a large vocabulary is an important aspect of human intelligence. Onecommon approach for human to populating vocabulary is to learn words duringreading or listening, and then use them in writing or speaking. This ability totransfer from input to output is natural for human, but it is difficult for machines.Human spontaneously performs this ...
Yuanpeng Li 0001   +3 more
openaire   +2 more sources

Multi‐Channel Convolutional Neural Quantum Embedding

open access: yesAdvanced Quantum Technologies, Volume 9, Issue 1, January 2026.
This study presents convolutional neural quantum embedding (CNQE), a framework for optimizing quantum data embeddings for multi‐channel data classification, grounded in quantum state discrimination and Fourier analysis of quantum circuits. CNQE is validated through proof‐of‐principle demonstrations on CIFAR‐10 and Tiny ImageNet, showing improved ...
Yujin Kim   +4 more
wiley   +1 more source

Adaptive Control of a PV‐Integrated Unified Power Quality Conditioner for Remote Low‐Voltage Distribution Networks

open access: yesIET Renewable Power Generation, Volume 20, Issue 1, January/December 2026.
An adaptive VLLMS‐based control strategy is developed for a PV‐powered UPQC, enabling simultaneous PQ mitigation and distributed power management. Filterless extraction and decoupling of non‐ideal voltage and current components provide fast convergence, improved dynamic response and stable DC‐link voltage under PV power fluctuations.
Pragnyashree Ray   +6 more
wiley   +1 more source

Optimizing feature pooling and prediction models of VQA algorithms

open access: yes, 2014
International audienceIn this paper, we propose a strategy to optimize feature pooling and prediction models of video quality assessment (VQA) algorithms with a much smaller number of parameters than methods based on machine learning, such as neural ...
Le Callet, Patrick   +4 more
core   +1 more source

Enhanced VQA : numerical quantification

open access: yes, 2019
May 2019School of ScienceWhile it is plausible to hold that artificial intelligence, AI, has made steady progress since its modern inception in 1956, it seems that over the last 10 years, AI has innovated at a particularly rapid pace.
Wang, Max
core  

Home - About - Disclaimer - Privacy