activity
20242026
collaborators

6 papers

cs.CV2026

MSD-Score: Multi-Scale Distributional Scoring for Reference-Free Image Caption Evaluation

Shichao Kan, Xuyang Zhang, Haojie Zhang +7

Evaluating image captions without references remains challenging because global embedding similarity often misses fine-grained mismatches such as hallucinated objects, missing attr…

cs.CV2026

V-Retrver: Evidence-Driven Agentic Reasoning for Universal Multimodal Retrieval

Dongyang Chen, Chaoyang Wang, Dezhao Su +6

Multimodal Large Language Models (MLLMs) have recently been applied to universal multimodal retrieval, where Chain-of-Thought (CoT) reasoning improves candidate reranking. However,…

cs.LG2025

Contrastive Regularization over LoRA for Multimodal Biomedical Image Incremental Learning

Haojie Zhang, Yixiong Liang, Hulin Kuang +5

Multimodal Biomedical Image Incremental Learning (MBIIL) is essential for handling diverse tasks and modalities in the biomedical domain, as training separate models for each modal…

cs.CV2025

TMCIR: Token Merge Benefits Composed Image Retrieval

Chaoyang Wang, Zeyu Zhang, Long Teng +2

Composed Image Retrieval (CIR) retrieves target images using a multi-modal query that combines a reference image with text describing desired modifications. The primary challenge i…

cs.CV2025

HRDecoder: High-Resolution Decoder Network for Fundus Image Lesion Segmentation

Ziyuan Ding, Yixiong Liang, Shichao Kan +1

High resolution is crucial for precise segmentation in fundus images, yet handling high-resolution inputs incurs considerable GPU memory costs, with diminishing performance gains a…

cs.LG2024

How Does the Smoothness Approximation Method Facilitate Generalization for Federated Adversarial Learning?

Wenjun Ding, Ying An, Lixing Chen +3

Federated Adversarial Learning (FAL) is a robust framework for resisting adversarial attacks on federated learning. Although some FAL studies have developed efficient algorithms, t…