Naiyan Wang

26

Papers

0

Total Citations

Papers (26)

Object Concepts Emerge from Motion

Bayesian Adaptive Matrix Factorization With Automatic Model Selection

DevNet: A Deep Event Network for Multimedia Event Detection and Evidence Recounting

Multi-Shot Pedestrian Re-Identification via Sequential Decision Making

LiDAR R-CNN: An Efficient and Universal 3D Object Detector

Learnable Graph Matching: Incorporating Graph Partitioning With Deep Feature Learning for Multiple Object Tracking

QueryDet: Cascaded Sparse Query for Accelerating High-Resolution Small Object Detection

Embracing Single Stride 3D Object Detector With Sparse Transformer

GIFS: Neural Implicit Function for General Shape Representation

3D Video Object Detection With Learnable Object-Centric Global Optimization

Anchor3DLane: Learning To Regress 3D Anchors for Monocular 3D Lane Detection

Understanding and Diagnosing Visual Tracking Systems

Factorized Bilinear Models for Image Recognition

Cross View Fusion for 3D Human Pose Estimation

Spectral Feature Transformation for Person Re-Identification

Scale-Aware Trident Networks for Object Detection

Sequence Level Semantics Aggregation for Video Object Detection

RangeDet: In Defense of Range View for LiDAR-Based 3D Object Detection

Direct Differentiable Augmentation Search

Once Detected, Never Lost: Surpassing Human Performance in Offline LiDAR based 3D Object Detection

Object as Query: Lifting Any 2D Object Detector to 3D Detection

FeatureNeRF: Learning Generalizable NeRFs by Distilling Foundation Models

Dynamic R-CNN: Towards High Quality Object Detection via Dynamic Training

Unsupervised Scale-consistent Depth and Ego-motion Learning from Monocular Video

Fully Sparse 3D Object Detection

Echoes Beyond Points: Unleashing the Power of Raw Radar Data in Multi-modality Fusion