Ziming Liu

Latest

Epsilon: Exploring Comprehensive Visual-Semantic Projection for Multi-Label Zero-Shot Learning
ParsNets: A Parsimonious Composition of Orthogonal and Low-Rank Linear Networks for Zero-Shot Learning
Easing Concept Bleeding in Diffusion via Entity Localization and Anchoring
ProCC: Progressive Cross-primitive Compatibility for Open-World Compositional Zero-Shot Learning
Towards Test-Time Refusals via Concept Negation
Anchor Sampling for Federated Learning with Partial Client Participation
(ML)2P-Encoder: On Exploration of Channel-class Correlation for Multi-label Zero-shot Learning
Decomposed Soft Prompt Guided Fusion Enhancing for Compositional Zero-Shot Learning
Graph Knows Unknowns: Reformulate Zero-shot Learning as Sample-level Graph Recognition
From Deterioration to Acceleration: A Calibration Approach to Rehabilitating Step Asynchronism in Federated Optimization
UTDNet: A Unified Triplet Decoder Network for Multimodal Salient Object Detection
Towards Unbiased Multi-label Zero-Shot Learning with Pyramid and Semantic Attention