2 citations · 6 across the 11 of their papers we have counts for
11 papers
MR-IQA: A Unified Margin View of Regression and Ranking for Blind Image Quality Assessment
Yuan Li, Youyuan Lin, Zitang Sun +4
Blind image quality assessment (BIQA) is commonly built on two basic learning paradigms: regression and ranking. Regression calibrates absolute scores, whereas ranking recovers qua…
Structuring Open-Ended NAS: Semi-Automated Design Knowledge Structuring with LLMs for Efficient Neural Architecture Search
Yuiko Sakuma, Masakazu Yoshimura, Marcel Gröpl +4
Current neural architecture search (NAS) methods are often limited by their predefined, restrictive search spaces. While recent large language model (LLM)-assisted NAS methods enab…
LLM as a Tool, Not an Agent: Code-Mined Tree Transformations for Neural Architecture Search
Masakazu Yoshimura, Zitang Sun, Yuiko Sakuma +3
Neural Architecture Search (NAS) aims to automatically discover high-performing deep neural network (DNN) architectures. However, conventional algorithm-driven NAS relies on carefu…
Do vision models perceive illusory motion in static images like humans?
Isabella Elaine Rosario, Fan L. Cheng, Zitang Sun +1
Understanding human motion processing is essential for building reliable, human-centered computer vision systems. Although deep neural networks (DNNs) achieve strong performance in…
Investigate the Low-level Visual Perception in Vision-Language based Image Quality Assessment
Yuan Li, Zitang Sun, Yen-Ju Chen +1
Recent advances in Image Quality Assessment (IQA) have leveraged Multi-modal Large Language Models (MLLMs) to generate descriptive explanations. However, despite their strong visua…
Building Reasonable Inference for Vision-Language Models in Blind Image Quality Assessment
Yuan Li, Zitang Sun, Yen-ju Chen +1
Recent progress in BIQA has been driven by VLMs, whose semantic reasoning abilities suggest that they might extract visual features, generate descriptive text, and infer quality in…
Online Data Curation for Object Detection via Marginal Contributions to Dataset-level Average Precision
Zitang Sun, Masakazu Yoshimura, Junji Otsuka +2
High-quality data has become a primary driver of progress under scale laws, with curated datasets often outperforming much larger unfiltered ones at lower cost. Online data curatio…
Machine Learning Modeling for Multi-order Human Visual Motion Processing
Zitang Sun, Yen-Ju Chen, Yung-Hao Yang +2
Our research aims to develop machines that learn to perceive visual motion as do humans. While recent advances in computer vision (CV) have enabled DNN-based models to accurately e…
Modelling Human Visual Motion Processing with Trainable Motion Energy Sensing and a Self-attention Network
Zitang Sun, Yen-Ju Chen, Yung-hao Yang +1
Visual motion processing is essential for humans to perceive and interact with dynamic environments. Despite extensive research in cognitive neuroscience, image-computable models t…
Unsupervised Learning Optical Flow in Multi-frame Dynamic Environment Using Temporal Dynamic Modeling
Zitang Sun, Shin'ya Nishida, Zhengbo Luo
For visual estimation of optical flow, a crucial function for many vision tasks, unsupervised learning, using the supervision of view synthesis has emerged as a promising alternati…
Rethinking ResNets: Improved Stacking Strategies With High Order Schemes
Zhengbo Luo, Zitang Sun, Weilian Zhou +2
Various deep neural network architectures (DNNs) maintain massive vital records in computer vision. While drawing attention worldwide, the design of the overall structure lacks gen…