Skip to content

Latest commit

 

History

History
142 lines (128 loc) · 8.02 KB

papers.md

File metadata and controls

142 lines (128 loc) · 8.02 KB
Raw

papers useful for me

on the way

  • Detecting Semantic Parts on Partially Occluded Objects
  • MegDet: A Large Mini-Batch Object Detector: A Large Mini-Batch Object Detector
  • Single-Shot Refinement Neural Network for Object Detection
  • Large kernel matters–improve semantic segmentation by global convolutional network.
  • S-OHEM: Stratified Online Hard Example Mining for Object Detection
  • Non-local Neural Networks
  • Improving Object Detection With One Line of Code
  • CMS-RCNN: Contextual Multi-Scale Region-based CNN for Unconstrained Face Detection
  • A MultiPath Network for Object Detection
  • Rethinking the Inception Architecture for Computer Vision
  • Towards High Performance Video Object Detection（MSRA）
  • Relation Networks for Object Detection（MSRA）
  • Single-Shot Object Detection with Enriched Semantics
  • Rank of Experts: Detection Network Ensemble
  • Multi-Channel CNN-based Object Detection for Enhanced Situation Awareness
  • FSSD: Feature Fusion Single Shot Multibox Detector
  • Learning Object Detectors from Scratch with Gated Recurrent Feature Pyramids
  • Cascade R-CNN: Delving into High Quality Object Detection
  • Feature Agglomeration Networks for Single Stage Face Detection
  • R-CNN for Small Object Detection
  • R-FCN-3000 at 30fps: Decoupling Detection and Classification
  • Context Augmentation for Convolutional Neural Networks
  • Beyond Grand Theft Auto V for Training, Testing and Enhancing Deep Learning in Self Driving Cars
  • Deep Regionlets for Object Detection
  • Class Rectification Hard Mining for Imbalanced Deep Learning
  • Weaving Multi-scale Context for Single Shot Detector
  • FHEDN: A based on context modeling Feature Hierarchy Encoder-Decoder Network for face detection
  • Deep Koalarization: Image Colorization using CNNs and Inception-ResNet-v2
  • Object Classification using Ensemble of Local and Deep Features
  • The Effectiveness of Data Augmentation in Image Classification using Deep Learning
  • Object detection via a multi-region & semantic segmentation-aware CNN model
  • Multi-Scale Context Aggregation by Dilated Convolutions
  • Crafting GBD-Net for Object Detection
  • Object Detection via Aspect Ratio and Context Aware Region-based Convolutional Networks
  • Attentive Contexts for Object Detection
  • Contextual Object Detection with a Few Relevant Neighbors
  • Optimizing Region Selection for Weakly Supervised Object Detection
  • Spatial Memory for Context Reasoning in Object Detection
  • Objects as context for detecting their semantic parts
  • DSOD: Learning Deeply Supervised Object Detectors from Scratch

object detection

  • Light-Head R-CNN: In Defense of Two-Stage Object Detector
  • Chained Cascade Network for Object Detection (iccv2017)
  • CoupleNet: Coupling Global Structure with Local Parts for Object Detection (iccv2017)
  • Joint Learning of Object and Action Detectors (iccv2017)
  • Recurrent Scale Approximation for Object Detection in CNN (iccv2017)[github]
  • S3FD: Single Shot Scale-Invariant Face Detector (iccv2017)
  • VPGNet: Vanishing Point Guided Network for Lane and Road Marking Detection and Recognition (iccv2017)
  • Amulet: Aggregating Multi-level Convolutional Features for Salient Object Detection
  • Beyond Skip Connections: Top-Down Modulation for Object Detection
  • Cascade Region Proposal and Global Context for Deep Object Detection
  • Deformable Part-based Fully Convolutional Network for Object Detection
  • Dynamic Zoom-in Network for Fast Object Detection in Large Images
  • Enhancement of SSD by concatenating feature maps for object detection
  • Fast Vehicle Detection in Aerial Imagery
  • Fast YOLO: A Fast You Only Look Once System for Real-time Embedded Object Detection in Video
  • Feature-Fused SSD: Fast Detection for Small Objects
  • Grab, Pay and Eat: Semantic Food Detection for Smart Restaurants
  • Inside-Outside Net: Detecting Objects in Context with Skip Pooling and Recurrent Neural Networks
  • Mask RCNN
  • On the Utility of Context (or the Lack Thereof) for Object Detection
  • PVANet: Lightweight Deep Neural Networks for Real-time Object Detection
  • RON: Reverse Connection with Objectness Prior Networks for Object Detection.[github]
  • HyperNet: Towards Accurate Region Proposal Generation and Joint Object Detection.
  • Towards End-to-End Car License Plates Detection and Recognition with Deep Neural Networks
  • Training Region-based Object Detectors with Online Hard Example Mining
  • You Only Look Once: Unified, Real-Time Object Detection
  • SSD: Single Shot MultiBox Detector
  • Going deeper with convolutions
  • Faster R-CNN: Towards Real-Time Object
  • Detect to Track and Track to Detect
  • Detecting Faces Using Region-based Fully Convolutional Networks
  • Deep Neural Networks for Object Detection
  • Object detection from video tubelets with convolutional neural networks
  • T-CNN: tube- lets with convolutional neural networks for object detection from videos
  • Receptive Field Block Net for Accurate and Fast Object Detection
  • Repulsion Loss: Detecting Pedestrians in a Crowd
  • Finding tiny faces
  • SSH: Single Stage Headless Face Detector
  • Feature Selective Networks for Object Detection
  • An Analysis of Scale Invariance in Object Detection – SNIP

object recognition

  • Unsupervised Domain Adaptation for Face Recognition in Unlabeled Videos (iccv2017)
  • Learning Transferable Architectures for Scalable Image Recognition
  • Multi-label Image Recognition by Recurrently Discovering Attentional Regions
  • Object Recognition by Using Multi-level Feature Point Extraction
  • Random Subspace Two-dimensional LDA for Face Recognition
  • SqueezeDet: Unified, Small, Low Power Fully Convolutional Neural Networks for Real-Time Object Detection for Autonomous Driving

object classification

  • Convolutional neural networks pretrained on large face recognition datasets for emotion classification from video
  • Detecting and Grouping Identical Objects for Region Proposal and Classification
  • Food Recognition using Fusion of Classifiers based on CNNs

object tracking

  • Fully-convolutional siamese networks for object tracking
  • UCT: Learning Unified Convolutional Networks for Real-time Visual Tracking
  • Visual object tracking using adaptive correlation filters cvpr2010
  • Hierarchical convolutional features for visual tracking
  • High- speed tracking with kernelized correlation filters
  • Learning Multi-Domain Convolutional Neural Networks for Visual Tracking
  • Multi-region two-stream R-CNN for action detection

image segmentation

  • DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs
  • Fully Convolutional Networks for Semantic Segmentation
  • HyperDense-Net A hyper-densely connected CNN for multi-modal image semantic segmentation

others

  • Are we ready for Autonomous Driving?The KITTI Vision Benchmark Suite
  • Channel Pruning for Accelerating Very Deep Neural Networks
  • Deformable Convolutional Networks (iccv2017)
  • EraseReLU: A Simple Way to Ease the Training of Deep Convolution Neural Networks
  • Fast Recurrent Fully Convolutional Networks for Direct Perception in Autonomous Driving
  • Fully Context-Aware Video Prediction
  • Interpretable R-CNN
  • Interpreting Convolutional Neural Networks Through Compression
  • Region-Based Image Retrieval Revisited
  • Smart Mirror: Intelligent Makeup Recommendation and Synthesis
  • Swish: a Self-Gated Activation Function
  • VGGFace2: A dataset for recognising faces across pose and age
  • What is an object ?
  • Stacked hourglass networks for human pose estimation
  • Deep learning for detecting multiple space-time action tubes in videos
  • DeepPainter: Painter Classification Using Deep Convolutional Autoencoders