Zhengkai Jiang

15

Papers

164

Total Citations

Papers (15)

Learning Where to Focus for Efficient Video Object Detection

EnerVerse: Envisioning Embodied Future Space for Robotics Manipulation

Learning Unified Reference Representation for Unsupervised Multi-class Anomaly Detection

OSV: One Step is Enough for High-Quality Image to Video Generation

DiffuMatting: Synthesizing Arbitrary Objects with Matting-level Annotation

Lumina-T2X: Scalable Flow-based Large Diffusion Transformer for Flexible Resolution Generation

Prototypical Contrast Adaptation for Domain Adaptive Semantic Segmentation

SDSTrack: Self-Distillation Symmetric Adapter Learning for Multi-Modal Visual Object Tracking

RAGD: Regional-Aware Diffusion Model for Text-to-Image Generation

Density Matters: Improved Core-Set for Active Domain Adaptive Segmentation

Dynamic Fusion With Intra- and Inter-Modality Attention Flow for Visual Question Answering

Rethinking Counting and Localization in Crowds: A Purely Point-Based Framework

Rethinking Mobile Block for Efficient Attention-based Models

Rethinking Learnable Tree Filter for Generic Feature Transform

Fine-Grained Dynamic Head for Object Detection