Modal-aware visual prompting for incomplete multi-modal brain tumor segmentation

Y Qiu, Z Zhao, H Yao, D Chen, Z Wang - Proceedings of the 31st ACM …, 2023 - dl.acm.org
In the realm of medical imaging, distinct magnetic resonance imaging (MRI) modalities can
provide complementary medical insights. However, it is not uncommon for one or more …

Implicit-zoo: A large-scale dataset of neural implicit functions for 2d images and 3d scenes

Q Ma, DP Paudel, E Konukoglu, L Van Gool - arXiv preprint arXiv …, 2024 - arxiv.org
Neural implicit functions have demonstrated significant importance in various areas such as
computer vision, graphics. Their advantages include the ability to represent complex shapes …

Strait: Non-autoregressive generation with stratified image transformer

S Qian, H Chang, Y Li, Z Zhang, J Jia… - arXiv preprint arXiv …, 2023 - arxiv.org
We propose Stratified Image Transformer (StraIT), a pure non-autoregressive (NAR)
generative model that demonstrates superiority in high-quality image synthesis over existing …

Towards efficient task-driven model reprogramming with foundation models

S Xu, J Yao, R Luo, S Zhang, Z Lian, M Tan… - arXiv preprint arXiv …, 2023 - arxiv.org
Vision foundation models exhibit impressive power, benefiting from the extremely large
model capacity and broad training data. However, in practice, downstream scenarios may …

The power of empathy and positive emotions in enhancing the communication of environmental issues: a case study of 'wandering elephant in Yunnan'on twitter

K Xue, S Li, AM Wen - Environmental Research Communications, 2023 - iopscience.iop.org
Media narratives in environmental communication often broadcast scientific and complex
information from the perspective of professional experts, and while focusing on emotions …

Homogeneous Tokenizer Matters: Homogeneous Visual Tokenizer for Remote Sensing Image Understanding

R Shao, Z Zhang, C Tao, Y Zhang, C Peng… - arXiv preprint arXiv …, 2024 - arxiv.org
The tokenizer, as one of the fundamental components of large models, has long been
overlooked or even misunderstood in visual tasks. One key factor of the great …

ReBotNet: Fast Real-time Video Enhancement

JMJ Valanarasu, R Garg, A Toor, X Tong, W Xi… - arXiv preprint arXiv …, 2023 - arxiv.org
Most video restoration networks are slow, have high computational load, and can't be used
for real-time video enhancement. In this work, we design an efficient and fast framework to …

TTCR: Accurate TCR-Epitope Binding Affinity Prediction Using Transformers

M Dai, Y Wu, J Zhou, Z Wu, M Man… - … IEEE Conference on …, 2024 - ieeexplore.ieee.org
Predicting the binding affinity between a T cell receptor (TCR) and an epitope is essential in
cancer immunotherapy. The existing predictor epiTCR employs Random Forest to …

Deep Skin Cancer Lesions Classification Scheme

GC Amaizu, LAC Ahakonye, DS Kim… - 2023 14th International …, 2023 - ieeexplore.ieee.org
Skin cancer has risen to be one of the significant forms of cancer worldwide. However, the
traditional means of skin cancer detection requires manual examination by an expert, which …

Towards Efficient and Effective Representation Learning for Image and Video Understanding

T Yang - 2023 - stars.library.ucf.edu
Deep learning has achieved tremendous success on various computer vision tasks.
However, deep learning methods and models are usually computationally expensive …