25 citations · 26 across the 11 of their papers we have counts for
12 papers
MedVeriSeg: Teaching LISA-Like Medical Segmentation Models to Verify Query Validity Without Extra Training
Qinyue Tong, Xiaozhen Wang, Ziqian Lu +3
Despite recent progress in text-prompt-based medical image segmentation, existing LISA-like MLLM-based methods typically generate masks regardless of whether the target specified i…
Multivariate Time Series Anomaly Detection via Dual-Branch Reconstruction and Autoregressive Flow-based Residual Density Estimation
Jun Liu, Ying Chen, Ziqian Lu +2
Multivariate Time Series Anomaly Detection (MTSAD) is critical for real-world monitoring scenarios such as industrial control and aerospace systems. Mainstream reconstruction-based…
Improving Anomaly Detection with Foundation-Model Synthesis and Wavelet-Domain Attention
Wensheng Wu, Zheming Lu, Ziqian Lu +5
Industrial anomaly detection faces significant challenges due to the scarcity of anomalous samples and the complexity of real-world anomalies. In this paper, we propose a foundatio…
Unlocking the Forgery Detection Potential of Vanilla MLLMs: A Novel Training-Free Pipeline
Rui Zuo, Qinyue Tong, Zhe-Ming Lu +1
With the rapid advancement of artificial intelligence-generated content (AIGC) technologies, including multimodal large language models (MLLMs) and diffusion models, image generati…
MediRound: Multi-Round Entity-Level Reasoning Segmentation in Medical Images
Qinyue Tong, Ziqian Lu, Jun Liu +3
Despite notable progress in text-guided medical image segmentation nowadays, these methods are limited to single-round dialogues and fail to support multi-round reasoning, which is…
MediSee: Reasoning-based Pixel-level Perception in Medical Images
Qinyue Tong, Ziqian Lu, Jun Liu +2
Despite remarkable advancements in pixel-level medical image perception, existing methods are either limited to specific tasks or heavily rely on accurate bounding boxes or text la…
Improving Skeleton-based Action Recognition with Interactive Object Information
Hao Wen, Ziqian Lu, Fengli Shen +2
Human skeleton information is important in skeleton-based action recognition, which provides a simple and efficient way to describe human pose. However, existing skeleton-based met…
Envisioning Class Entity Reasoning by Large Language Models for Few-shot Learning
Mushui Liu, Fangtai Wu, Bozheng Li +3
Few-shot learning (FSL) aims to recognize new concepts using a limited number of visual samples. Existing approaches attempt to incorporate semantic information into the limited vi…
CM-UNet: Hybrid CNN-Mamba UNet for Remote Sensing Image Semantic Segmentation
Mushui Liu, Jun Dan, Ziqian Lu +3
Due to the large-scale image size and object variations, current CNN-based and Transformer-based approaches for remote sensing image semantic segmentation are suboptimal for captur…
SYNC-CLIP: Synthetic Data Make CLIP Generalize Better in Data-Limited Scenarios
Mushui Liu, Weijie He, Ziqian Lu +1
Prompt learning is a powerful technique for transferring Vision-Language Models (VLMs) such as CLIP to downstream tasks. However, the prompt-based methods that are fine-tuned solel…
Prompt-based test-time real image dehazing: a novel pipeline
Zixuan Chen, Zewei He, Ziqian Lu +2
Existing methods attempt to improve models' generalization ability on real-world hazy images by exploring well-designed training schemes (\eg, CycleGAN, prior loss). However, most…
Accurate and lightweight dehazing via multi-receptive-field non-local network and novel contrastive regularization
Zewei He, Zixuan Chen, Jinlei Li +5
Recently, deep learning-based methods have dominated image dehazing domain. A multi-receptive-field non-local network (MRFNLN) consisting of the multi-stream feature attention bloc…