activity
20242026
most citedPSVMA+: Exploring Multi-granularity Semantic-visual Adaption for Generalized Zero-shot Learning

1 citations · 4 across the 10 of their papers we have counts for

collaborators
Showing cs.CVShow all

7 papers · 1 filter

cs.CV2026

Taming Real-World Space-Time Video Super-Resolution with One-Step Diffusion

Shuoyan Wei, Feng Li, Chen Zhou +3

Diffusion models have demonstrated exceptional success in video super-resolution (VSR), exhibiting powerful capabilities for generating fine-grained details. However, their potenti…

cs.CV2025

Harnessing Group-Oriented Consistency Constraints for Semi-Supervised Semantic Segmentation in CdZnTe Semiconductors

Peihao Li, Yan Fang, Man Liu +4

Labeling Cadmium Zinc Telluride (CdZnTe) semiconductor images is challenging due to the low-contrast defect boundaries, necessitating annotators to cross-reference multiple views.…

cs.CV2024★ 1 cited

PSVMA+: Exploring Multi-granularity Semantic-visual Adaption for Generalized Zero-shot Learning

Man Liu, Huihui Bai, Feng Li +5

Generalized zero-shot learning (GZSL) endeavors to identify the unseen categories using knowledge from the seen domain, necessitating the intrinsic interactions between the visual…

cs.CV2024★ 1 cited

Attend and Enrich: Enhanced Visual Prompt for Zero-Shot Learning

Man Liu, Huihui Bai, Feng Li +4

Zero-shot learning (ZSL) endeavors to transfer knowledge from seen categories to recognize unseen categories, which mostly relies on the semantic-visual interactions between image…

cs.CV2024

BlindDiff: Empowering Degradation Modelling in Diffusion Models for Blind Image Super-Resolution

Feng Li, Yixuan Wu, Zichao Liang +4

Diffusion models (DM) have achieved remarkable promise in image super-resolution (SR). However, most of them are tailored to solving non-blind inverse problems with fixed known deg…

cs.CV2024★ 1 cited

Towards the Uncharted: Density-Descending Feature Perturbation for Semi-supervised Semantic Segmentation

Xiaoyang Wang, Huihui Bai, Limin Yu +2

Semi-supervised semantic segmentation allows model to mine effective supervision from unlabeled data to complement label-guided training. Recent research has primarily focused on c…