Jiajun Deng

21

Papers

149

Total Citations

Papers (21)

Adaptive Offline Quintuplet Loss for Image-Text Matching

3D-LLaVA: Towards Generalist 3D LMMs with Omni Superpoint Transformer

Cycle-Consistency Learning for Captioning and Grounding

RaCFormer: Towards High-Quality 3D Object Detection via Query-based Radar-Camera Fusion

SpatialSplat: Efficient Semantic 3D from Sparse Unposed Images

Hierarchical Masked Autoregressive Models with Low-Resolution Token Pivots

GraspCoT: Integrating Physical Property Reasoning for 6-DoF Grasping under Flexible Language Instructions

Revisiting Open-Set Panoptic Segmentation

SynTag: Enhancing the Geometric Robustness of Inversion-based Generative Image Watermarking

S3R-GS: Streamlining the Pipeline for Large-Scale Street Scene Reconstruction

Bi-LRFusion: Bi-Directional LiDAR-Radar Fusion for 3D Dynamic Object Detection

TransVG: End-to-End Visual Grounding With Transformers

3DPPE: 3D Point Positional Encoding for Transformer-based Multi-Camera 3D Object Detection

SimFIR: A Simple Framework for Fisheye Image Rectification with Self-supervised Representation Learning

Invariant Training 2D-3D Joint Hard Samples for Few-Shot Point Cloud Recognition

Masked Motion Predictors are Strong 3D Action Representation Learners

Cyclic-Bootstrap Labeling for Weakly Supervised Object Detection

CMD: Self-Supervised 3D Action Representation Learning with Cross-Modal Mutual Distillation

Geometric Representation Learning for Document Image Rectification

CluB: Cluster Meets BEV for LiDAR-Based 3D Object Detection

CLIP4HOI: Towards Adapting CLIP for Practical Zero-Shot HOI Detection