collaborators

11 papers

cs.CV2026

ReflexTrack: A Feedback-Driven Agent for Training-Free Referring Video Object Segmentation

Yuanjia Li, Tianyang Xu, Tao Zhou +3

Referring video object segmentation (RVOS) requires segmenting a target specified by natural language throughout a video. Recent agentic approaches combine multimodal large languag…

cs.CV2026

Text-Driven Fusion for Infrared and Visible Images: Achieving Image Scene Adaptation on Hyperbolic Space

Huan Kang, Hui Li, Tianyang Xu +3

Infrared and visible image fusion aims to integrate complementary modalities, while existing Euclidean methods impose rigid distance metrics that distort multi-modal interactions a…

cs.CV2026

EvaNet: Towards More Efficient and Consistent Infrared and Visible Image Fusion Assessment

Chunyang Cheng, Tianyang Xu, Xiao-Jun Wu +4

Evaluation is essential in image fusion research, yet most existing metrics are directly borrowed from other vision tasks without proper adaptation. These traditional metrics, ofte…

cs.CV2026

Beyond Strict Pairing: Arbitrarily Paired Training for High-Performance Infrared and Visible Image Fusion

Yanglin Deng, Tianyang Xu, Chunyang Cheng +3

Infrared and visible image fusion(IVIF) combines complementary modalities while preserving natural textures and salient thermal signatures. Existing solutions predominantly rely on…

cs.CV2026

Multi-Paradigm Collaborative Adversarial Attack Against Multi-Modal Large Language Models

Yuanbo Li, Tianyang Xu, Cong Hu +3

The rapid progress of Multi-Modal Large Language Models (MLLMs) has significantly advanced downstream applications. However, this progress also exposes serious transferable adversa…

cs.CV2026

Towards Highly Transferable Vision-Language Attack via Semantic-Augmented Dynamic Contrastive Interaction

Yuanbo Li, Tianyang Xu, Cong Hu +3

With the rapid advancement and widespread application of vision-language pre-training (VLP) models, their vulnerability to adversarial attacks has become a critical concern. In gen…