Fei Su

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…

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…

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…

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…