ResearchAlpha Leak

Conferences Topics Top Authors Rankings Browse All

Home/Authors/Junke Wang

Junke Wang

Topic trends: 32,543 papers · similarity ≥ 0.4 · year ≥ 2024 · Data sourced from Semantic Scholar

34,598 papers | Abstracts: 31,650 (91.5%) | Citations: 34,598 (100.0%) | arXiv: 26,074 (75.4%)

Built: Feb 15, 2026, 3:09 AM AMS

7

papers

481

total citations

papers (7)

ObjectFormer for Image Manipulation Detection and Localization

Perception Encoder: The best visual embeddings are not at the output of the network

NEURIPS 2025arXiv

Efficient Video Transformers with Spatial-Temporal Token Selection

Look Before You Match: Instance Understanding Matters in Video Object Segmentation

OmniViD: A Generative Framework for Universal Video Understanding

Rethinking Discrete Tokens: Treating Them as Conditions for Continuous Autoregressive Image Synthesis

OmniVL: One Foundation Model for Image-Language and Video-Language Tasks