Shu Kong
30 papers · 2017–2026 · 8 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+6 more ↓ Show less ↑
🗺️ Taxonomy Completionist (59) 🏃 Academic Marathon · Sprint 🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Silver 🐣 Hot Topic Early Bird
🧬
Topic Evolution
🧭
Keyword Pioneer
🗃️
Keyword Collector
(132)
💎
Century Club · Bronze
🔥
Unstoppable · Silver
⚡
Prolific Year · Productive
Top co-authors
Research topics
Computer Vision
(19)
Machine Learning
(19)
Deep Learning
(15)
Analysis
(14)
Learning Types · Deep Learning
(10)
Artificial Intelligence
(9)
Learning Types · Machine Learning
(9)
Core AI
(8)
Core Methods
(7)
Domain-Specific
(7)
Application Areas
(5)
Learning Paradigms
(4)
Processing
(4)
Natural Language Processing
(2)
Architectures
(2)
Keywords
vision-language model
(6)
zero-shot learning
(5)
domain adaptation
(4)
semantic segmentation
(4)
object detection
(3)
foundation model
(3)
depth estimation
(3)
camera pose
(2)
metric learning
(2)
retrieval-augmented learning
(2)
3d object detection
(2)
class imbalance
(2)
autonomous vehicle
(2)
multimodal fusion
(2)
synthetic data
(2)
model compression
(2)
multimodal learning
(2)
autonomous driving
(2)
video understanding
(2)
instance detection
(2)
Papers
Roadside Monocular 3D Detection Prompted by 2D Detection
WACV 2026
Attention to the Burstiness in Visual Prompt Tuning!
ICCV 2025
Few-Shot Recognition via Stage-Wise Retrieval-Augmented Finetuning
CVPR 2025
Information-Bottleneck Driven Binary Neural Network for Change Detection
ICCV 2025
Solving Instance Detection from an Open-World Perspective
CVPR 2025
UAL-Bench: The First Comprehensive Unusual Activity Localization Benchmark
WACV 2025
Alpha-CLIP: A CLIP Model Focusing on Wherever You Want
CVPR 2024
Boosting Image Restoration via Priors from Pre-trained Models
CVPR 2024
CriSp: Leveraging Tread Depth Maps for Enhanced Crime-Scene Shoeprint Matching
ECCV 2024
Improving Knowledge Distillation via Regularizing Feature Direction and Norm
ECCV 2024
Instance Tracking in 3D Scenes from Egocentric Videos
CVPR 2024
LCA-on-the-Line: Benchmarking Out of Distribution Generalization with Class Taxonomies
ICML 2024
Revisiting Few-Shot Object Detection with Vision-Language Models
NeurIPS 2024
The Neglected Tails in Vision-Language Models
CVPR 2024
A High-Resolution Dataset for Instance Detection with Multi-View Object Capture
NeurIPS 2023
Creating a Forensic Database of Shoeprints From Online Shoe-Tread Photos
WACV 2023
Far3Det: Towards Far-Field 3D Detection
WACV 2023
OV-PARTS: Towards Open-Vocabulary Part Segmentation
NeurIPS 2023
Prompting Scientific Names for Zero-Shot Species Recognition
EMNLP 2023
Continual Learning with Evolving Class Ontologies
NeurIPS 2022
Long-Tailed Recognition via Weight Balancing
CVPR 2022
Multimodal Object Detection via Probabilistic Ensembling
ECCV 2022
Towards Long-Tailed 3D Detection
CoRL 2022
Camera Pose Matters: Improving Depth Prediction by Mitigating Pose Distribution Bias
CVPR 2021
OpenGAN: Open-Set Recognition via Open Data Generation
ICCV 2021
Domain Decluttering: Simplifying Images to Mitigate Synthetic-Real Domain Shift and Improve Depth Estimation
CVPR 2020
Modularized Textual Grounding for Counterfactual Resilience
CVPR 2019
Recurrent Pixel Embedding for Instance Grouping
CVPR 2018
Recurrent Scene Parsing With Perspective Understanding in the Loop
CVPR 2018
Low-Rank Bilinear Pooling for Fine-Grained Classification
CVPR 2017