Shu Kong

21

Papers

26

Total Citations

Papers (21)

Few-Shot Recognition via Stage-Wise Retrieval-Augmented Finetuning

Instance Tracking in 3D Scenes from Egocentric Videos

Information-Bottleneck Driven Binary Neural Network for Change Detection

Alpha-CLIP: A CLIP Model Focusing on Wherever You Want

Boosting Image Restoration via Priors from Pre-trained Models

The Neglected Tails in Vision-Language Models

LCA-on-the-Line: Benchmarking Out of Distribution Generalization with Class Taxonomies

Low-Rank Bilinear Pooling for Fine-Grained Classification

Recurrent Scene Parsing With Perspective Understanding in the Loop

Recurrent Pixel Embedding for Instance Grouping

Modularized Textual Grounding for Counterfactual Resilience

Domain Decluttering: Simplifying Images to Mitigate Synthetic-Real Domain Shift and Improve Depth Estimation

Camera Pose Matters: Improving Depth Prediction by Mitigating Pose Distribution Bias

Long-Tailed Recognition via Weight Balancing

OpenGAN: Open-Set Recognition via Open Data Generation

Multimodal Object Detection via Probabilistic Ensembling

Solving Instance Detection from an Open-World Perspective

Attention to the Burtiness in Visual Prompt Tuning!

Continual Learning with Evolving Class Ontologies

A High-Resolution Dataset for Instance Detection with Multi-View Object Capture

OV-PARTS: Towards Open-Vocabulary Part Segmentation