7 papers · 1 filter
Modeling Scientific Experiment Scenes: Dataset and Model
Minghao Zou, Qingtian Zeng, Shangkun Liu +5
Scene Graph Generation (SGG) is fundamental to structured visual understanding, yet existing benchmarks focus mainly on daily-life images and overlook scientific experiment scenes…
Comparison Drives Preference: Reference-Aware Modeling for AI-Generated Video Quality Assessment
Minghao Zou, Gen Liu, Guanghui Yue +5
The rapid advancement of generative models has led to a growing volume of AI-generated videos, making the automatic quality assessment of such videos increasingly important. Existi…
Perception-oriented Bidirectional Attention Network for Image Super-resolution Quality Assessment
Yixiao Li, Xiaoyuan Yang, Guanghui Yue +6
Many super-resolution (SR) algorithms have been proposed to increase image resolution. However, full-reference (FR) image quality assessment (IQA) metrics for comparing and evaluat…
Temporal Inconsistency Guidance for Super-resolution Video Quality Assessment
Yixiao Li, Xiaoyuan Yang, Weide Liu +6
As super-resolution (SR) techniques introduce unique distortions that fundamentally differ from those caused by traditional degradation processes (e.g., compression), there is an i…
Knowledge Distillation for Road Detection based on cross-model Semi-Supervised Learning
Wanli Ma, Oktay Karakus, Paul L. Rosin
The advancement of knowledge distillation has played a crucial role in enabling the transfer of knowledge from larger teacher models to smaller and more efficient student models, a…
Deep Generative Model based Rate-Distortion for Image Downscaling Assessment
Yuanbang Liang, Bhavesh Garg, Paul L Rosin +1
In this paper, we propose Image Downscaling Assessment by Rate-Distortion (IDA-RD), a novel measure to quantitatively evaluate image downscaling algorithms. In contrast to image-ba…
DiverseNet: Decision Diversified Semi-supervised Semantic Segmentation Networks for Remote Sensing Imagery
Wanli Ma, Oktay Karakus, Paul L. Rosin
Semi-supervised learning (SSL) aims to help reduce the cost of the manual labelling process by leveraging a substantial pool of unlabelled data alongside a limited set of labelled…