Hao Fang

7

Papers

41

Total Citations

Papers (7)

Unified Embedding Alignment for Open-Vocabulary Video Instance Segmentation

Semantic and Sequential Alignment for Referring Video Object Segmentation

Generative Adapter: Contextualizing Language Models in Parameters with A Single Forward Pass

Hierarchical Features Matter: A Deep Exploration of Progressive Parameterization Method for Dataset Distillation

A Conditional Probability Framework for Compositional Zero-shot Learning

One Perturbation is Enough: On Generating Universal Adversarial Perturbations against Vision-Language Pre-training Models

Decoupled Motion Expression Video Segmentation