activity
20202026
most citedLearning Open Set Network with Discriminative Reciprocal Points

241 citations · 330 across the 13 of their papers we have counts for

collaborators
Showing cs.CVShow all

15 papers · 1 filter

cs.CV2026

Mind the Discriminability Trap in Source-Free Cross-domain Few-shot Learning

Zhenyu Zhang, Yixiong Zou, Yuhua Li +2

Source-Free Cross-Domain Few-Shot Learning (SF-CDFSL) focuses on fine-tuning with limited training data from target domains (e.g., medical or satellite images), where Vision-Langua…

cs.CV2026

KTV: Keyframes and Key Tokens Selection for Efficient Training-Free Video LLMs

Baiyang Song, Jun Peng, Yuxin Zhang +3

Training-free video understanding leverages the strong image comprehension capabilities of pre-trained vision language models (VLMs) by treating a video as a sequence of static fra…

cs.CV2025

Decoupling Template Bias in CLIP: Harnessing Empty Prompts for Enhanced Few-Shot Learning

Zhenyu Zhang, Guangyao Chen, Yixiong Zou +2

The Contrastive Language-Image Pre-Training (CLIP) model excels in few-shot learning by aligning visual and textual representations. Our study shows that template-sample similarity…

cs.CV2025

Start Small, Think Big: Curriculum-based Relative Policy Optimization for Visual Grounding

Qingyang Yan, Guangyao Chen, Yixiong Zou

Chain-of-Thought (CoT) prompting has recently shown significant promise across various NLP and computer vision tasks by explicitly generating intermediate reasoning steps. However,…

cs.CV2025

When Every Millisecond Counts: Real-Time Anomaly Detection via the Multimodal Asynchronous Hybrid Network

Dong Xiao, Guangyao Chen, Peixi Peng +4

Anomaly detection is essential for the safety and reliability of autonomous driving systems. Current methods often focus on detection accuracy but neglect response time, which is c…

cs.CV2025

Adapter Naturally Serves as Decoupler for Cross-Domain Few-Shot Semantic Segmentation

Jintao Tong, Ran Ma, Yixiong Zou +3

Cross-domain few-shot segmentation (CD-FSS) is proposed to pre-train the model on a source-domain dataset with sufficient samples, and then transfer the model to target-domain data…