activity
20192025
most citedGeneralizing to Evolving Domains with Latent Structure-Aware Sequential Autoencoder

5 citations · 15 across the 10 of their papers we have counts for

collaborators
Showing cs.CVShow all

6 papers · 1 filter

cs.CV2025

Enhancing Zero-Shot Image Recognition in Vision-Language Models through Human-like Concept Guidance

Hui Liu, Wenya Wang, Kecheng Chen +6

In zero-shot image recognition tasks, humans demonstrate remarkable flexibility in classifying unseen categories by composing known simpler concepts. However, existing vision-langu…

cs.CV2025

Q-PART: Quasi-Periodic Adaptive Regression with Test-time Training for Pediatric Left Ventricular Ejection Fraction Regression

Jie Liu, Tiexin Qin, Hui Liu +5

In this work, we address the challenge of adaptive pediatric Left Ventricular Ejection Fraction (LVEF) assessment. While Test-time Training (TTT) approaches show promise for this t…

cs.CV2024

Test-time adaptation for image compression with distribution regularization

Kecheng Chen, Pingping Zhang, Tiexin Qin +3

Current test- or compression-time adaptation image compression (TTA-IC) approaches, which leverage both latent and decoder refinements as a two-step adaptation scheme, have potenti…

cs.CV2021

LibFewShot: A Comprehensive Library for Few-shot Learning

Wenbin Li, Ziyi, Wang +9

Few-shot learning, especially few-shot image classification, has received increasing attention and witnessed significant advances in recent years. Some recent studies implicitly sh…

cs.CV2020

Diversity Helps: Unsupervised Few-shot Learning via Distribution Shift-based Data Augmentation

Tiexin Qin, Wenbin Li, Yinghuan Shi +1

Few-shot learning aims to learn a new concept when only a few training examples are available, which has been extensively explored in recent years. However, most of the current wor…

cs.CV2019★ 3 cited

Automatic Data Augmentation by Learning the Deterministic Policy

Yinghuan Shi, Tiexin Qin, Yong Liu +3

Aiming to produce sufficient and diverse training samples, data augmentation has been demonstrated for its effectiveness in training deep models. Regarding that the criterion of th…