Weiyao Lin

24

Papers

200

Total Citations

Papers (24)

HAC: Hash-grid Assisted Context for 3D Gaussian Splatting Compression

FRIH: Fine-Grained Region-Aware Image Harmonization

Unleashing Diffusion Transformers for Visual Correspondence by Modulating Massive Activations

Neural Compression for 3D Geometry Sets

Fractal Dimension Invariant Filtering and Its CNN-Based Implementation

Towards Accurate One-Stage Object Detection With AP-Loss

Variational Pedestrian Detection

Speed Up Object Detection on Gigapixel-Level Images With Patch Arrangement

RIDE: Reversal Invariant Descriptor Enhancement

Unsupervised Trajectory Clustering via Adaptive Multi-Kernel-Based Shrinkage

ThiNet: A Filter Level Pruning Method for Deep Neural Network Compression

End-to-End Video Instance Segmentation via Spatial-Temporal Graph Neural Networks

Multi-Level Curriculum for Training a Distortion-Aware Barrel Distortion Rectification Model

Enhancing Self-Supervised Video Representation Learning via Multi-Level Feature Optimization

PIoU Loss: Towards Accurate Oriented Object Detection in Complex Environments

CFAD: Coarse-to-Fine Action Detector for Spatiotemporal Action Localization

Multiple Sound Sources Localization from Coarse to Fine

Person Re-Identification With Correspondence Structure Learning

Collaborative Weakly Supervised Video Correlation Learning for Procedure-Aware Instructional Video Analysis

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

Picking Deep Filter Responses for Fine-Grained Image Recognition

Delving into the Cyclic Mechanism in Semi-supervised Video Object Segmentation

Discriminative Sounding Objects Localization via Self-supervised Audiovisual Matching

BasisFormer: Attention-based Time Series Forecasting with Learnable and Interpretable Basis