Junke Wang
7 papers · 2022–2025 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
π Conference Polyglot (4) π Interdisciplinary Bridge π§ Keyword Pioneer π£ Hot Topic Early Bird π Cross-Pollinator (11)
πΊοΈ
Taxonomy Completionist
(20)
π
The Namer
Conferences
CVPR (3)
NIPS (2)
ECCV (1)
ICCV (1)
Top co-authors
Keywords
transformer architecture
(2)
image generation
(2)
video understanding
(2)
multimodal learning
(2)
anomaly detection
(1)
temporal dynamics
(1)
action recognition
(1)
autoregressive model
(1)
video generation
(1)
video synthesis
(1)
video captioning
(1)
visual object tracking
(1)
prototype learning
(1)
image synthesis
(1)
instance segmentation
(1)
dense matching
(1)
generative model
(1)
diffusion model
(1)
temporal modeling
(1)
contrastive learning
(1)
Papers
Rethinking Discrete Tokens: Treating Them as Conditions for Continuous Autoregressive Image Synthesis
ICCV 2025
OmniViD: A Generative Framework for Universal Video Understanding
CVPR 2024
OmniTokenizer: A Joint Image-Video Tokenizer for Visual Generation
NIPS 2024
Look Before You Match: Instance Understanding Matters in Video Object Segmentation
CVPR 2023
OmniVL: One Foundation Model for Image-Language and Video-Language Tasks
NIPS 2022
Efficient Video Transformers with Spatial-Temporal Token Selection
ECCV 2022
ObjectFormer for Image Manipulation Detection and Localization
CVPR 2022