activity
20232025
most citedChatGPT-Powered Hierarchical Comparisons for Image Classification

11 citations · 13 across the 3 of their papers we have counts for

collaborators

5 papers

cs.CV2025

HAMoBE: Hierarchical and Adaptive Mixture of Biometric Experts for Video-based Person ReID

Yiyang Su, Yunping Shi, Feng Liu +1

Recently, research interest in person re-identification (ReID) has increasingly focused on video-based scenarios, which are essential for robust surveillance and security in varied…

cs.CV2024

Open-Set Biometrics: Beyond Good Closed-Set Models

Yiyang Su, Minchul Kim, Feng Liu +2

Biometric recognition has primarily addressed closed-set identification, assuming all probe subjects are in the gallery. However, most practical applications involve open-set biome…

cs.CV20242 cited

KeyPoint Relative Position Encoding for Face Recognition

Minchul Kim, Yiyang Su, Feng Liu +2

In this paper, we address the challenge of making ViT models more robust to unseen affine transformations. Such robustness becomes useful in various recognition tasks such as face…

cs.CV2023

INFAMOUS-NeRF: ImproviNg FAce MOdeling Using Semantically-Aligned Hypernetworks with Neural Radiance Fields

Andrew Hou, Feng Liu, Zhiyuan Ren +4

We propose INFAMOUS-NeRF, an implicit morphable face model that introduces hypernetworks to NeRF to improve the representation power in the presence of many training subjects. At t…

cs.CV202311 cited

ChatGPT-Powered Hierarchical Comparisons for Image Classification

Zhiyuan Ren, Yiyang Su, Xiaoming Liu

The zero-shot open-vocabulary challenge in image classification is tackled by pretrained vision-language models like CLIP, which benefit from incorporating class-specific knowledge…