activity
20242026
collaborators

5 papers

cs.CV2026

Not Just What's There: Enabling CLIP to Comprehend Negated Visual Descriptions Without Fine-tuning

Junhao Xiao, Zhiyu Wu, Hao Lin +5

Vision-Language Models (VLMs) like CLIP struggle to understand negation, often embedding affirmatives and negatives similarly (e.g., matching "no dog" with dog images). Existing me…

cs.CV2026

Path-Decoupled Hyperbolic Flow Matching for Few-Shot Adaptation

Lin Li, Ziqi Jiang, Gefan Ye +5

Recent advances in cross-modal few-shot adaptation treat visual-semantic alignment as a continuous feature transport problem via Flow Matching (FM). However, we argue that Euclidea…

cs.CV2026

Compositional Feature Augmentation for Unbiased Scene Graph Generation

Lin Li, Guikun Chen, Jun Xiao +3

Scene Graph Generation (SGG) aims to detect all the visual relation triplets \texttt{sub}, \texttt{pred}, \texttt{obj} in a given image. With the emergence of various advance…

cs.CV2025

Compositional Zero-shot Learning via Progressive Language-based Observations

Lin Li, Guikun Chen, Zhen Wang +2

Compositional zero-shot learning aims to recognize unseen state-object compositions by leveraging known primitives (state and object) during training. However, effectively modeling…

cs.CV2024

Decomposed Prototype Learning for Few-Shot Scene Graph Generation

Xingchen Li, Jun Xiao, Guikun Chen +4

Today's scene graph generation (SGG) models typically require abundant manual annotations to learn new predicate types. Therefore, it is difficult to apply them to real-world appli…