Paper Review and A. I. Contents
This section includes a review of some of the materials that I have presented since 2014 as graduate student and now as researcher in South Korea.
This material has been built on the basis of the referenced papers. I am uploading this content online for educational purposes to help students and researchers understand the concepts and fundamentals of some of the most relevant articles on deep learning and computer vision for object detection, image classification, instance-semantic segmentation, open-set recognition, reinforcement learning, activity recognition, generative adversarial networks, and others.
* Please use this material with the corresponding reference.
For any comments or concerns about the contents, feel free to email me at afuentes@jbnu.ac.kr.
More materials will be added soon...
2021
20210326_YOLOv4.pdfYOLO v4: Optimal Speed and Accuracy of Object Detection
Object detection
20210205_UniversalDomainAdaptation.pdfUniversal Domain Adaptation
Open set domain adaptation
20210108_Large-Scale Object Detection.pdfLarge-Scale Object Detection in the Wild for Imbalanced Multi-Labels
Object detection
2020
20201120_Rethinking Pre-training.pdfRethinking Pre-training and Self-training
Image classification
20200811_MultipleObjg_Tracking.pdfMultiple Object Forecasting: Predicting Future Object Locations in Diverse Environments
Object tracking
20200811_CSPNet.pdfCSPNet: A new backbone that can enhance learning capabilities of CNN
Feature extractor
20200717_Transformers.pdfAttention is all you need
Spatio-temporal model (Fundament of Transformers)
20200521_ActorCondAttention.pdfActor Conditioned Attention Maps for Video Action Detection
Video action detection
20200417_FixNet.pdfFixing the train-test resolution discrepancy
FixEfficientNet
20200225_CBNet.pdfCBNet: A Novel Composite Backbone Network Architecture for Object Detection
CBNet (Object detection)
20200121_Class_Balanced.pdfClass-Balanced Loss Based on Effective Number of Samples
Class imbalance
2019
20191207_EfficnetNet.pdfEfficientDet: Scalable and Efficient Object Detection
EfficientDet (Object detection)
20191026_Bottom-up Object Detection.pdfBottom-up Object Detection by Grouping Extreme and Center Points
CornerNet
20190809_OpenSet.pdfC2AE: Class Conditioned Auto-Encoder for Open-set Recognition
Open-set recognition
20190723_Cascade_RCNN.pdfCascade R-CNN: High Quality Object Detection and Instance Segmentation
Cascade R-CNN (Object detection and instance segmentation)
20190712_Libra_RCNN.pdfLibra R-CNN: Towards Balanced Learning for Object Detection
Object detection
20190615_Hierarchical.pdfHierarchical Relational Networks for Group Activity Recognition and Retrieval
Activity recognition
20190518_TridentNet.pdfScale-Aware Trident Networks for Object Detection
TridentNet (Object detection)
20190413_Sniper.pdfSNIPER: Efficient Multi-Scale Training
SniperNet (Object detection)
2090316_FeatureSelectiveAnchor.pdfFeature Selective Anchor-Free Module for Single-Shot Object Detection
Object detection
20190215_ReinforcementLearning.pdfAn Introduction to Deep Reinforcement Learning
Reinforcement Learning
20190108_DeformableCNN.pdfDeformable Convolutional Networks
Optimization of feature extractors
2018
20181208_PELEENet.pdfPelee: A Real-Time Object Detection System on Mobile Devices
PeleeNet (Object detection)
20181110_ActivityRecognition.pdfA Review on Activity Recognition
Action recognition
20181010_MegDet.pdfMegDet: A large Mini-Batch Object Detector
Object detection
20180908_AttnGAN.pdfAttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networks
AttnGAN (Generative Adversarial Networks)
From Text-to-Image
20180814_Feature_Gen_Nets.pdfFeature Generating Networks for Zero-Shot Learning
Zero-Shot Learning
20180724_MobileNetV2.pdfMobileNetV2: Inverted Residuals and Linear Bottlenecks
Object detection
20180709_Taskonomy.pdfTaskonomy: Disentangling Task Transfer Learning
Transfer Learning
20180622_Analyzing_Filters_Toward_Efficient_ConvNet.pdfAnalyzing Filters Toward Efficient ConvNet
Understanding ConvNets
20180421_NASNet.pdfLearning Transferable Architectures for Scalable Image Recognition
NASNet (Image Recognition)
20180309_FractalNet.pdfFractalNet: Ultra-Deep Neural Networks Without Residuals
FractalNet (Image Recognition)
20180123_SSD.pdfSingle-Shot Refinement Neural Network for Object Detection
SSR (Object detection)
20180105_FocalLoss.pdfFocal Loss for Dense Object Detection
RetinaNet (Object detection)
2017
20171121_Understanding Deep Learning.pdfUnderstanding Deep Learning Requires Re-thinking Generalization
Generalization
20170818_ Residual Attention.pdfResidual Attention Network for Image Classification
Image classification
20170801_DenseNet.pdfDensely Connected Convolutional Networks
DenseNet
20170709_MobileNets.pdfMobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
Image classification and object detection
20170527_Human-Object.pdfDetecting and Recognizing Human-Objects Interactions
Human-Object Interaction
20170318_YOLO9000.pdfYOLO9000: Better, Faster, Stronger
Object detection
20170216_Unsupervised GANet.pdfUnsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
Fundament of GAN
20160119_SpeedAccuracy.pdfSpeed/accuracy trade-offs for modern convolutional object detectors
Tradeoff between accuracy and speed of deep nets for object detection
2016
20161224_SSD.pdfSSD: Single Shot MultiBox Detector
SSD (Object detection)
20161119_ProNet2.pdfProNet: Learning to Propose Object-specific Boxes for Cascaded Neural Networks
Object detection
20161022_Learning_deep features.pdfLearning Deep Features for Discriminative Localization
Object localization
20160902_Identiy mapping.pdfIdentity Mappings in Deep Residual Networks
Identity in residual networks
20160720_T-CNN.pdfT-CNN: Tubelets with Convolutional Neural Networks for Object Detection from Videos
Object detection in videos
20160423_Faster R-CNN.pdfFaster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Object detection
20160305_PedestrianDetectionAidedByDeepLearningSemanticTasks.pdfPedestrian Detection aided by Deep Learning Semantic Tasks
Pedestrian detection
20160115_RecurrentCNN.pdfRecurrent Convolutional Neural Networks for Objects Recognition
RCNN (Object detection)
20150904_FLowNet.pdfFlowNet: Learning Optical Flow with Convolutional Networks
Optical flow
2015
Traditional hand-crafted-based methods for pedestrian detection, motion estimation, optical flow.
20151107_Stereo Vision CNN.pdfComputing the Stereo Matching Cost with a Convolutional Neural Network
Stereo vision CNN
20150805_Dense Stereo for Pedestrian Detection.pdfThe Benefits of Dense Stereo for Pedestrian Detection
Dense stereo vision
20150713_Moving objects detection and Credal.pdfMoving Objects Detection and Credal Boosting Based Recognition in Urban Environmets
Moving objects detection
20150625_Will the pedestrian cross .pdfWill the Pedestrian Cross? A study on Pedestrian Path Prediction
Pedestrian detection
20150506_Unsupervised flow-based motion segmentation.pdfUnsupervised flow-based motion analysis for an autonomous moving system
Motion analysis
20150418_Locating objects in car-driving sequences.pdfLocating moving objects in car-driving sequences
Moving objects detection
20150403_Stixel motion estimation.pdfStixels motion estimation without optical flow computation
Motion estimation
20150207_Probabilistic models.pdfPedestrian detection from traffic scenes based on probabilistic models of the contour fragments
Pedestrian detection
20152001_3D Optical flow.pdfFeature- and Depth-Supported Modified Total Variation Optical Flow for 3D Motion Field Estimation in Real Scenes
Optical flow
2014
Traditional hand-crafted-based methods for pedestrian detection, motion estimation, optical flow.
20141101_Moving Pedestrian Detection Based on Motion Segmentation.pdfMoving Pedestrian Detection Based on Motion Segmentation
Motion segmentation
20141128_Motion segmentation.pdfMotion Segmentation Using Optical Flow for Pedestrian Detection from Moving Vehicle
Pedestrian detection
20140927_PedestrianDetection.pdfTowards a Real-Time Pedestrian Detection based on a deformable template model
Pedestrian detection
20140814_New features pedestrian.pdfNew features and insights for pedestrian detection
Pedestrian detections
20140707_Pedestrian Detection.pdfPedestrian Detection: An Evaluation of the State of the Art
Pedestrian detection
20140505_Study Relationships HG and CV.pdfStudying Relationships Between Human Gaze, Description, and Computer Vision
Human and computer vision