Jason Kuen

25

Papers

65

Total Citations

Papers (25)

ImageFolder: Autoregressive Image Generation with Folded Tokens

Refer to Any Segmentation Mask Group With Vision-Language Prompts

MAGICK: A Large-scale Captioned Dataset from Matting Generated Images using Chroma Keying

Recurrent Attentional Networks for Saliency Detection

Motion-Guided Cascaded Refinement Network for Video Object Segmentation

Dual Attention Matching Network for Context-Aware Feature Sequence Based Person Re-Identification

Stochastic Downsampling for Cost-Adjustable Inference and Improved Regularization in Convolutional Networks

Multimodal Contrastive Training for Visual Representation Learning

Multi-Scale Aligned Distillation for Low-Resolution Detection

SelfDoc: Self-Supervised Document Representation Learning

Open-Vocabulary Instance Segmentation via Robust Cross-Modal Pseudo-Labeling

High Quality Segmentation for Ultra High-Resolution Images

TopNet: Transformer-Based Object Placement Network for Image Compositing

SceneComposer: Any-Level Semantic Image Synthesis

Scaling Object Detection by Transferring Classification Weights

High Quality Entity Segmentation

Meta Spatio-Temporal Debiasing for Video Scene Graph Generation

Improving the Reliability for Confidence Estimation

GALA: Toward Geometry-and-Lighting-Aware Object Search for Compositing

CA-SSL: Class-Agnostic Semi-Supervised Learning for Detection and Segmentation

DiffIP: Representation Fingerprints for Robust IP Protection of Diffusion Models

LazyDiT: Lazy Learning for the Acceleration of Diffusion Transformers

Self-Supervised Relationship Probing

UniDoc: Unified Pretraining Framework for Document Understanding

AIMS: All-Inclusive Multi-Level Segmentation for Anything