15 citations · 24 across the 8 of their papers we have counts for
8 papers
Illuminating Visual Identity in Universal Multimodal Embeddings
Jiawei Cao, Junyi Feng, Jiashen Hua +5
Universal Multimodal Embeddings (UMEs) aim to unify various modalities and tasks into a shared representation space. In recent years, this field has witnessed substantial progress…
Hallucination Begins Where Saliency Drops
Xiaofeng Zhang, Yuanchao Zhu, Chaochen Gu +8
Recent studies have examined attention dynamics in large vision-language models (LVLMs) to detect hallucinations. However, existing approaches remain limited in reliably distinguis…
Seeing Clearly by Layer Two: Enhancing Attention Heads to Alleviate Hallucination in LVLMs
Xiaofeng Zhang, Yihao Quan, Chaochen Gu +6
The hallucination problem in multimodal large language models (MLLMs) remains a common issue. Although image tokens occupy a majority of the input sequence of MLLMs, there is limit…
From Redundancy to Relevance: Information Flow in LVLMs Across Reasoning Tasks
Xiaofeng Zhang, Yihao Quan, Chen Shen +7
Large Vision Language Models (LVLMs) achieve great performance on visual-language reasoning tasks, however, the black-box nature of LVLMs hinders in-depth research on the reasoning…
Enlighten-Your-Voice: When Multimodal Meets Zero-shot Low-light Image Enhancement
Xiaofeng Zhang, Zishan Xu, Hao Tang +4
Low-light image enhancement is a crucial visual task, and many unsupervised methods tend to overlook the degradation of visible information in low-light scenes, which adversely aff…
A Dual Attentive Generative Adversarial Network for Remote Sensing Image Change Detection
Luyi Qiu, Xiaofeng Zhang, ChaoChen Gu +1
Remote sensing change detection between bi-temporal images receives growing concentration from researchers. However, comparing two bi-temporal images for detecting changes is chall…
Memory augment is All You Need for image restoration
Xiao Feng Zhang, Chao Chen Gu, Shan Ying Zhu
Image restoration is a low-level vision task, most CNN methods are designed as a black box, lacking transparency and internal aesthetics. Although some methods combining traditiona…
SpA-Former: Transformer image shadow detection and removal via spatial attention
Xiao Feng Zhang, Chao Chen Gu, Shan Ying Zhu
In this paper, we propose an end-to-end SpA-Former to recover a shadow-free image from a single shaded image. Unlike traditional methods that require two steps for shadow detection…