Xingyu Zeng

9

Papers

77

Total Citations

Papers (9)

GoT: Unleashing Reasoning Capability of MLLM for Visual Generation and Editing

PUMA: Empowering Unified MLLM with Multi-granular Visual Generation

DeepID-Net: Deformable Deep Convolutional Neural Networks for Object Detection

GS3D: An Efficient 3D Object Detection Framework for Autonomous Driving

Learning Deep Representation With Large-Scale Attributes

Adapting Object Detectors with Conditional Domain Normalization

Rethinking Pseudo-LiDAR Representation

Scale-Aware Spatio-Temporal Relation Learning for Video Anomaly Detection

Gradient-based Visual Explanation for Transformer-based CLIP