AAAI 2020 论文

Posted 2021-03-10 ahuzcl

Detection && classification：

TANet: Robust 3D Object Detection from Point Clouds with Triple Attention

RDSNet: A New Deep Architecture for Reciprocal Object Detection and Instance Segmentation

ZoomNet: Part-Aware Adaptive Zooming Neural Network for 3D Object Detection

 FASTER Recurrent Networks for Efficient Video Classification

PedHunter: Occlusion Robust Pedestrian Detector in Crowded Scenes

Relational Learning for Joint Head and Human Detection

Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression

Web-Supervised Network with Softly Update-Drop Training for Fine-Grained Visual Classification

Channel Interaction Networks for Fine-Grained Image Categorization

Universal-RCNN: Universal Object Detector via Transferable Graph R-CNN

Deep Embedded Complementary and Interactive Information for Multi-view Classification

Graph Attention Based Proposal 3D ConvNets for Action Detection

Object Instance Mining for Weakly Supervised Object Detection

Temporal Context Enhanced Feature Aggregation for Video Object Detection

CBNet:A Novel Composite Backbone Network Architecture for Object Detection

Segmentation：

GFF: Gated Fully Fusion for Semantic Segmentation

Geometry Sharing Network for 3D Point Cloud Classification and Segmentation

CIAN: Cross-Image Affinity Net for Weakly Supervised Semantic Segmentation

An Adversarial Perturbation Oriented Domain Adaptation Approach for Semantic Segmentation

An Annotation Sparsification Strategy for 3D Medical Image Segmentation via Representative Selection and Self-Training

Deep Object Co-segmentation via Spatial-Semantic Network Modulation

Dynamic Sampling Network for Semantic Segmentation

Face：

Mis-classified Vector Guided Softmax Loss for Face Recognition

Learning Meta Model for Zero- and Few-shot Face Anti-spoofing

Regularized Fine-grained Meta Face Anti-spoofing

FAN-Face: a simple orthogonal improvement to deep face recognition

 

Tracking：

Pose-Assisted Multi-Camera Collaboration for Active Object Tracking

Complementary-View Multiple Human Tracking

POST: POlicy-based Switch Tracking

SPSTracker: Sub-Peak Suppression of Response Map for Robust Object Tracking

Release the power of online-training for robust visual tracking

Multi-Task Driven Feature Models for Thermal Infrared Tracking

 

Net 加速

Pruning from Scratch

Channel Pruning Guided by Classification Loss and Feature Importance

Layerwise Sparse Coding for Pruned Deep Neural Networks with Extreme Compression Ratio

Reborn Filters: Pruning Convolutional Neural Networks with Limited Data

Sparsity-inducing Binarized Neural Networks

Binarized Neural Architecture Search

Pose Estimation

FDN: Feature Decoupling Network for Head Pose Estimation

3D Single-Person Concurrent Activity Detection Using Stacked Relation Network

RE-ID：

Infrared-Visible Cross-Modal Person Re-Identification with an X Modality

Multi-spectral Vehicle Re-identification: A Challenge

Single Camera Training for Person Re-identification

Hierarchical Online Instance Matching for Person Search

Cross-Modality Paired-Images Generation for RGB-Infrared Person Re-Identification

 

Autonomous Driving：

AutoRemover: Automatic Object Removal for Autonomous Driving Videos

 

other：

Residual Neural Processes

URNet : User-Resizable Residual Networks with Conditional Gating Module

Dynamical System Inspired Adaptive Time Stepping Controller for Residual Network Families

Stochastic Loss Function

Context-Aware Zero-Shot Recognition

Subspace Capsule Network

Capsule Routing via Variational Bayes

Facial Attribute Capsules for Noise Face Super Resolution

Scale-wise Convolution for Image Restoration

Random Erasing Data Augmentation

Random Erasing Data Augmentation

GBCNs: Genetic Binary Convolutional Networks for Enhancing the Performance of 1-bit DCNNs

Particle Filter Recurrent Neural Networks

Cross-Modality Attention with Semantic Graph Embedding for Multi-Label Classification

Parsing as Pretraining