
-
Using Long Short-Term Memory (LSTM) and Internet of Things (IoT) for localized surface temperature forecasting in an urban environment
The rising temperature is one of the key indicators of a warming climate...
read it
-
Neural Architecture Search with Random Labels
In this paper, we investigate a new variant of neural architecture searc...
read it
-
Momentum^2 Teacher: Momentum Teacher with Momentum Statistics for Self-Supervised Learning
In this paper, we present a novel approach, Momentum^2 Teacher, for stud...
read it
-
RepVGG: Making VGG-style ConvNets Great Again
We present a simple but powerful architecture of convolutional neural ne...
read it
-
Dynamic Hybrid Relation Network for Cross-Domain Context-Dependent Semantic Parsing
Semantic parsing has long been a fundamental problem in natural language...
read it
-
Implicit Feature Pyramid Network for Object Detection
In this paper, we present an implicit feature pyramid network (i-FPN) fo...
read it
-
Efficient Human Pose Estimation by Learning Deeply Aggregated Representations
In this paper, we propose an efficient human pose estimation network (DA...
read it
-
End-to-End Object Detection with Fully Convolutional Network
Mainstream object detectors based on the fully convolutional network has...
read it
-
Fine-Grained Dynamic Head for Object Detection
The Feature Pyramid Network (FPN) presents a remarkable approach to alle...
read it
-
Rethinking Learnable Tree Filter for Generic Feature Transform
The Learnable Tree Filter presents a remarkable approach to model struct...
read it
-
Fully Convolutional Networks for Panoptic Segmentation
In this paper, we present a conceptually simple, strong, and efficient f...
read it
-
UPFlow: Upsampling Pyramid for Unsupervised Optical Flow Learning
We present an unsupervised learning approach for optical flow estimation...
read it
-
Self-EMD: Self-Supervised Object Detection without ImageNet
In this paper, we propose a novel self-supervised representation learnin...
read it
-
Deep Positional and Relational Feature Learning for Rotation-Invariant Point Cloud Analysis
In this paper we propose a rotation-invariant deep network for point clo...
read it
-
Joint COCO and Mapillary Workshop at ICCV 2019: COCO Instance Segmentation Challenge Track
In this report, we present our object detection/instance segmentation sy...
read it
-
EqCo: Equivalent Rules for Self-supervised Contrastive Learning
In this paper, we propose a method, named EqCo (Equivalent Rules for Con...
read it
-
Activate or Not: Learning Customized Activation
Modern activation layers use non-linear functions to activate the neuron...
read it
-
Funnel Activation for Visual Recognition
We present a conceptually simple but effective funnel activation for ima...
read it
-
WeightNet: Revisiting the Design Space of Weight Networks
We present a conceptually simple, flexible and effective framework for w...
read it
-
BorderDet: Border Feature for Dense Object Detection
Dense object detectors rely on the sliding-window paradigm that predicts...
read it
-
AutoAssign: Differentiable Label Assignment for Dense Object Detection
In this paper, we propose an anchor-free object detector with a fully di...
read it
-
LabelEnc: A New Intermediate Supervision Method for Object Detection
In this paper we propose a new intermediate supervision method, named La...
read it
-
End-to-end Interpretable Learning of Non-blind Image Deblurring
Non-blind image deblurring is typically formulated as a linear least-squ...
read it
-
Approximation algorithms for general cluster routing problem
Graph routing problems have been investigated extensively in operations ...
read it
-
Structured and Localized Image Restoration
We present a novel approach to image restoration that leverages ideas fr...
read it
-
Online Reinforcement Learning Control by Direct Heuristic Dynamic Programming: from Time-Driven to Event-Driven
In this paper time-driven learning refers to the machine learning method...
read it
-
Spherical Motion Dynamics of Deep Neural Networks with Batch Normalization and Weight Decay
We comprehensively reveal the learning dynamics of deep neural networks ...
read it
-
A real-time multi-constraints obstacle avoidance method based on LiDAR
Obstacle avoidance is one of the essential and indispensable functions f...
read it
-
Joint Multi-Dimension Pruning
We present joint multi-dimension pruning (named as JointPruning), a new ...
read it
-
Dynamic Memory Induction Networks for Few-Shot Text Classification
This paper proposes Dynamic Memory Induction Networks (DMIN) for few-sho...
read it
-
A Survey on Dialog Management: Recent Advances and Challenges
Dialog management (DM) is a crucial component in a task-oriented dialog ...
read it
-
Angle-based Search Space Shrinking for Neural Architecture Search
In this work, we present a simple and general search space shrinking met...
read it
-
Stitcher: Feedback-driven Data Provider for Object Detection
Object detectors commonly vary quality according to scales, where the pe...
read it
-
Attentive Normalization for Conditional Image Generation
Traditional convolution-based generative adversarial networks synthesize...
read it
-
Learning Human-Object Interaction Detection using Interaction Points
Understanding interactions between humans and objects is one of the fund...
read it
-
Dynamic Region-Aware Convolution
We propose a new convolution called Dynamic Region-Aware Convolution (DR...
read it
-
Learning Dynamic Routing for Semantic Segmentation
Recently, numerous handcrafted and searched networks have been applied f...
read it
-
Detection in Crowded Scenes: One Proposal, Multiple Predictions
We propose a simple yet effective proposal-based object detector, aiming...
read it
-
High-Order Information Matters: Learning Relation and Topology for Occluded Person Re-Identification
Occluded person re-identification (ReID) aims to match occluded person i...
read it
-
PointINS: Point-based Instance Segmentation
A single-point feature has shown its effectiveness in object detection. ...
read it
-
Learning Delicate Local Representations for Multi-Person Pose Estimation
In this paper, we propose a novel method called Residual Steps Network (...
read it
-
A Big Data Enabled Channel Model for 5G Wireless Communication Systems
The standardization process of the fifth generation (5G) wireless commun...
read it
-
Market Power in Convex Hull Pricing
The start up costs in many kinds of generators lead to complex cost stru...
read it
-
Towards Stabilizing Batch Statistics in Backward Propagation of Batch Normalization
Batch Normalization (BN) is one of the most widely used techniques in De...
read it
-
PVN3D: A Deep Point-wise 3D Keypoints Voting Network for 6DoF Pose Estimation
In this work, we present a novel data-driven method for robust 6DoF obje...
read it
-
Conductor Galloping Prediction on Imbalanced Datasets: SVM with Smart Sampling
Conductor galloping is the high-amplitude, low-frequency oscillation of ...
read it
-
A Statistical Learning Approach to Reactive Power Control in Distribution Systems
Pronounced variability due to the growth of renewable energy sources, fl...
read it
-
Learnable Tree Filter for Structure-preserving Feature Transform
Learning discriminative global features plays a vital role in semantic s...
read it
-
Disentangled Image Matting
Most previous image matting methods require a roughly-specificed trimap ...
read it
-
HRGE-Net: Hierarchical Relational Graph Embedding Network for Multi-view 3D Shape Recognition
View-based approach that recognizes 3D shape through its projected 2D im...
read it