activity
20242026
collaborators

6 papers

cs.CV2026

OmniFashion: Towards Generalist Fashion Intelligence via Multi-Task Vision-Language Learning

Zhengwei Yang, Andi Long, Hao Li +3

Fashion intelligence spans multiple tasks, i.e., retrieval, recommendation, recognition, and dialogue, yet remains hindered by fragmented supervision and incomplete fashion annotat…

cs.CV2025

Expanding Zero-Shot Object Counting with Rich Prompts

Huilin Zhu, Senyao Li, Jingling Yuan +5

Expanding pre-trained zero-shot counting models to handle unseen categories requires more than simply adding new prompts, as this approach does not achieve the necessary alignment…

cs.AI2025

VEGAS: Towards Visually Explainable and Grounded Artificial Social Intelligence

Hao Li, Hao Fei, Zechao Hu +2

Social Intelligence Queries (Social-IQ) serve as the primary multimodal benchmark for evaluating a model's social intelligence level. While impressive multiple-choice question(MCQ)…

cs.CV2025

Cross-Modal Few-Shot Learning: a Generative Transfer Learning Framework

Zhengwei Yang, Yuke Li, Qiang Sun +3

Most existing studies on few-shot learning focus on unimodal settings, where models are trained to generalize to unseen data using a limited amount of labeled examples from a singl…

cs.CV2025

FocalCount: Towards Class-Count Imbalance in Class-Agnostic Counting

Huilin Zhu, Jingling Yuan, Zhengwei Yang +3

In class-agnostic object counting, the goal is to estimate the total number of object instances in an image without distinguishing between specific categories. Existing methods oft…

cs.CV2024

Zero-shot Object Counting with Good Exemplars

Huilin Zhu, Jingling Yuan, Zhengwei Yang +4

Zero-shot object counting (ZOC) aims to enumerate objects in images using only the names of object classes during testing, without the need for manual annotations. However, a criti…