research
∙
08/17/2023
Knowledge-inspired Subdomain Adaptation for Cross-Domain Knowledge Transfer
Most state-of-the-art deep domain adaptation techniques align source and...
share
research
∙
07/29/2023
Instance-Wise Adaptive Tuning and Caching for Vision-Language Models
Large-scale vision-language models (LVLMs) pretrained on massive image-t...
research
∙
07/05/2023
Source Identification: A Self-Supervision Task for Dense Prediction
The paradigm of self-supervision focuses on representation learning from...
research
∙
03/17/2023
Refinement for Absolute Pose Regression with Neural Feature Synthesis
Absolute Pose Regression (APR) methods use deep neural networks to direc...
research
∙
09/14/2022
Label Refinement Network from Synthetic Error Augmentation for Medical Image Segmentation
Deep convolutional neural networks for image segmentation do not learn t...
research
∙
04/01/2022
DFNet: Enhance Absolute Pose Regression with Direct Feature Matching
We introduce a camera relocalization pipeline that combines absolute pos...
research
∙
01/04/2022
Modeling Users' Behavior Sequences with Hierarchical Explainable Network for Cross-domain Fraud Detection
With the explosive growth of the e-commerce industry, detecting online t...
research
∙
12/31/2021
Neural Hierarchical Factorization Machines for User's Event Sequence Analysis
Many prediction tasks of real-world applications need to model multi-ord...
research
∙
07/03/2021
SHORING: Design Provable Conditional High-Order Interaction Network via Symbolic Testing
Deep learning provides a promising way to extract effective representati...
research
∙
04/08/2021
Direct-PoseNet: Absolute Pose Regression with Photometric Consistency
We present a relocalization pipeline, which combines an absolute pose re...
research
∙
08/08/2020
Modeling the Field Value Variations and Field Interactions Simultaneously for Fraud Detection
With the explosive growth of e-commerce, online transaction fraud has be...
research
∙
06/26/2020
Region-of-interest guided Supervoxel Inpainting for Self-supervision
Self-supervised learning has proven to be invaluable in making best use ...
research
∙
10/14/2019
A New Local Transformation Module for Few-shot Segmentation
Few-shot segmentation segments object regions of new classes with a few ...
research
∙
09/21/2019
Class Activation Map generation by Multiple Level Class Grouping and Orthogonal Constraint
Class activation map (CAM) highlights regions of classes based on classi...
research
∙
07/29/2019
Multi-Task Attention-Based Semi-Supervised Learning for Medical Image Segmentation
We propose a novel semi-supervised image segmentation method that simult...
research
∙
04/15/2019
DuBox: No-Prior Box Objection Detection via Residual Dual Scale Detectors
Traditional neural objection detection methods use multi-scale features ...
research
∙
11/08/2018