Jinhong Lin
4 papers · 2024–2025 · 4 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 ↓
🌍
Conference Polyglot · Bronze
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(15)
Venues
Top co-authors
Research topics
Machine Learning
(4)
Deep Learning
(3)
Learning Types · Machine Learning
(3)
Artificial Intelligence
(2)
Computer Vision
(2)
Application Areas
(2)
Architectures
(2)
Learning Types · Deep Learning
(2)
Core AI · Computer Vision
(1)
Core AI · Artificial Intelligence
(1)
Core Methods
(1)
Learning Paradigms
(1)
Processing
(1)
Keywords
self-supervised learning
(3)
contrastive learning
(2)
vision transformer
(2)
representation learning
(2)
curriculum learning
(1)
multimodal learning
(1)
video understanding
(1)
visual representation
(1)
object tracking
(1)
efficient inference
(1)
token pruning
(1)
downstream performance
(1)
video dataset
(1)
clip model
(1)
sequence compression
(1)
token dropout
(1)
object representation learning
(1)
masked image modeling
(1)
model compression
(1)
masked autoencoding
(1)
Papers
From Prototypes to General Distributions: An Efficient Curriculum for Masked Image Modeling
CVPR 2025
Patch Ranking: Token Pruning as Ranking Prediction for Efficient CLIP
WACV 2025
TrackVerse: A Large-Scale Object-Centric Video Dataset for Image-Level Representation Learning
ICCV 2025
Accelerating Augmentation Invariance Pretraining
NeurIPS 2024