Yi Jin

11

Papers

110

Total Citations

Papers (11)

Stronger Fewer & Superior: Harnessing Vision Foundation Models for Domain Generalized Semantic Segmentation

ShotBench: Expert-Level Cinematic Understanding in Vision-Language Models

Improving Visual and Downstream Performance of Low-Light Enhancer with Vision Foundation Models Collaboration

Integral Fast Fourier Color Constancy

FreeDrag: Feature Dragging for Reliable Point-based Image Editing

Learning Combinatorial Solver for Graph Matching

Reusing the Task-Specific Classifier as a Discriminator: Discriminator-Free Adversarial Domain Adaptation

Robust Object Tracking Based on Temporal and Spatial Deep Networks

Disentangle then Parse: Night-time Semantic Segmentation with Illumination Disentanglement

HQ-CLIP: Leveraging Large Vision-Language Models to Create High-Quality Image-Text Datasets and CLIP Models

Deliberated Domain Bridging for Domain Adaptive Semantic Segmentation