22 citations · 27 across the 22 of their papers we have counts for
25 papers
Uruqi: Learning Spatial Cognition from Visual Experience
Shichao Li, Meiqi Wang, Fei Su +1
Spatial intelligence requires maintaining a coherent understanding of the world as the embodied agent moves. Like humans, the agent must use its own motion to interpret changes acr…
From Model Patterns to Abstract Semantics in Compositional Zero-Shot Learning
Weize Li, Zhicheng Zhao, Fei Su
Compositional Zero Shot Learning aims to recognize unseen compositions by recombining learned primitives. Recent methods rely on vision language models and attempt to explicitly mo…
CHRep: Cross-modal Histology Representation and Post-hoc Calibration for Spatial Gene Expression Prediction
Changfan Wang, Xinran Wang, Donghai Liu +4
Spatial transcriptomics (ST) enables spatially resolved gene profiling but remains expensive and low-throughput, limiting large-cohort studies and routine clinical use. Predicting…
Robustness Risk of Conversational Retrieval: Identifying and Mitigating Noise Sensitivity in Qwen3-Embedding Model
Weishu Chen, Zhouhui Hou, Mingjie Zhan +2
We present an empirical study of embedding-based retrieval under realistic conversational settings, where queries are short, dialogue-like, and weakly specified, and retrieval corp…
Aligning What EEG Can See: Structural Representations for Brain-Vision Matching
Jingyi Tang, Shuai Jiang, Fei Su +1
Visual decoding from electroencephalography (EEG) has emerged as a highly promising avenue for non-invasive brain-computer interfaces (BCIs). Existing EEG-based decoding methods pr…
Post-TIPS Prediction via Multimodal Interaction: A Multi-Center Dataset and Framework for Survival, Complication, and Portal Pressure Assessment
Junhao Dong, Dejia Liu, Ruiqi Ding +6
Transjugular intrahepatic portosystemic shunt (TIPS) is an established procedure for portal hypertension, but provides variable survival outcomes and frequent overt hepatic encepha…
Automatic Synthesis of High-Quality Triplet Data for Composed Image Retrieval
Haiwen Li, Delong Liu, Zhaohui Hou +2
As a challenging vision-language (VL) task, Composed Image Retrieval (CIR) aims to retrieve target images using multimodal (image+text) queries. Although many existing CIR methods…
OLMA: One Loss for More Accurate Time Series Forecasting
Tianyi Shi, Zhu Meng, Yue Chen +5
Time series forecasting faces two important but often overlooked challenges. Firstly, the inherent random noise in the time series labels sets a theoretical lower bound for the for…
Data-Efficient Generalization for Zero-shot Composed Image Retrieval
Zining Chen, Zhicheng Zhao, Fei Su +2
Zero-shot Composed Image Retrieval (ZS-CIR) aims to retrieve the target image based on a reference image and a text description without requiring in-distribution triplets for train…
Rethinking Two-Stage Referring-by-Tracking in Referring Multi-Object Tracking: Make it Strong Again
Weize Li, Yunhao Du, Qixiang Yin +2
Referring Multi-Object Tracking (RMOT) aims to track multiple objects specified by natural language expressions in videos. With the recent significant progress of one-stage methods…
ICFNet: Integrated Cross-modal Fusion Network for Survival Prediction
Binyu Zhang, Zhu Meng, Junhao Dong +2
Survival prediction is a crucial task in the medical field and is essential for optimizing treatment options and resource allocation. However, current methods often rely on limited…
Filter or Compensate: Towards Invariant Representation from Distribution Shift for Anomaly Detection
Zining Chen, Xingshuang Luo, Weiqiu Wang +3
Recent Anomaly Detection (AD) methods have achieved great success with In-Distribution (ID) data. However, real-world data often exhibits distribution shift, causing huge performan…
UFO: Enhancing Diffusion-Based Video Generation with a Uniform Frame Organizer
Delong Liu, Zhaohui Hou, Mingjie Zhan +3
Recently, diffusion-based video generation models have achieved significant success. However, existing models often suffer from issues like weak consistency and declining image qua…
Modality and Task Adaptation for Enhanced Zero-shot Composed Image Retrieval
Haiwen Li, Fei Su, Zhicheng Zhao
As a challenging vision-language task, Zero-Shot Composed Image Retrieval (ZS-CIR) is designed to retrieve target images using bi-modal (image+text) queries. Typical ZS-CIR methods…
Hierarchical IoU Tracking based on Interval
Yunhao Du, Zhicheng Zhao, Fei Su
Multi-Object Tracking (MOT) aims to detect and associate all targets of given classes across frames. Current dominant solutions, e.g. ByteTrack and StrongSORT++, follow the hybrid…
MindShot: A Few-Shot Brain Decoding Framework via Transferring Cross-Subject Prior and Distilling Frequency Domain Knowledge
Shuai Jiang, Zhu Meng, Haiwen Li +3
Aiming to reconstruct visual stimuli from brain signals, brain decoding has recently made significant progress using functional magnetic resonance imaging (fMRI). However, it still…
Bring Adaptive Binding Prototypes to Generalized Referring Expression Segmentation
Weize Li, Zhicheng Zhao, Haochen Bai +1
Referring Expression Segmentation (RES) has attracted rising attention, aiming to identify and segment objects based on natural language expressions. While substantial progress has…
MLS-Track: Multilevel Semantic Interaction in RMOT
Zeliang Ma, Song Yang, Zhe Cui +4
The new trend in multi-object tracking task is to track objects of interest using natural language. However, the scarcity of paired prompt-instance data hinders its progress. To ad…
PracticalDG: Perturbation Distillation on Vision-Language Models for Hybrid Domain Generalization
Zining Chen, Weiqiu Wang, Zhicheng Zhao +3
Domain Generalization (DG) aims to resolve distribution shifts between source and target domains, and current DG methods are default to the setting that data from source and target…
YYDS: Visible-Infrared Person Re-Identification with Coarse Descriptions
Yunhao Du, Zhicheng Zhao, Fei Su
Visible-infrared person re-identification (VI-ReID) is challenging due to considerable cross-modality discrepancies. Existing works mainly focus on learning modality-invariant feat…
iKUN: Speak to Trackers without Retraining
Yunhao Du, Cheng Lei, Zhicheng Zhao +1
Referring multi-object tracking (RMOT) aims to track multiple objects based on input textual descriptions. Previous works realize it by simply integrating an extra textual module i…
Video-based Visible-Infrared Person Re-Identification with Auxiliary Samples
Yunhao Du, Cheng Lei, Zhicheng Zhao +2
Visible-infrared person re-identification (VI-ReID) aims to match persons captured by visible and infrared cameras, allowing person retrieval and tracking in 24-hour surveillance s…
Automatic Synthetic Data and Fine-grained Adaptive Feature Alignment for Composed Person Retrieval
Delong Liu, Haiwen Li, Zhaohui Hou +3
Person retrieval has attracted rising attention. Existing methods are mainly divided into two retrieval modes, namely image-only and text-only. However, they are unable to make ful…
Now and Future of Artificial Intelligence-based Signet Ring Cell Diagnosis: A Survey
Zhu Meng, Junhao Dong, Limei Guo +4
Signet ring cells (SRCs), associated with a high propensity for peripheral metastasis and poor prognosis, critically influence surgical decision-making and outcome prediction. Howe…