元學習論文總結||小樣本學習論文總結

2017-2019年計算機視覺頂會文章收錄 AAAI2017-2019 CVPR2017-2019 ECCV2018 ICCV2017-2019 ICLR2017-2019 NIPS2017-2019

https://www.cnblogs.com/wangxiaocvpr/category/754856.html

?

Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networks

該文被密碼保護。

posted @?2019-06-01 09:55?AHU-WangXiao 閱讀(2) |?評論 (0)?編輯

Learning Conditioned Graph Structures for Interpretable Visual Question Answering

該文被密碼保護。

posted @?2019-05-29 00:32?AHU-WangXiao 閱讀(2) |?評論 (0)?編輯

Spatial-Temporal Relation Networks for Multi-Object Tracking

摘要: Spatial-Temporal Relation Networks for Multi-Object Tracking 2019-05-21?11:07:49 Paper:?https://arxiv.org/pdf/1904.11489.pdf 1. Background and Motivat閱讀全文

posted @?2019-05-21 11:09?AHU-WangXiao 閱讀(75) |?評論 (0)?編輯

Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression

摘要: Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression 2019-05-20?19:34:55 Paper:?https://arxiv.org/pdf/1902.09630.pdf P閱讀全文

posted @?2019-05-20 19:37?AHU-WangXiao 閱讀(18) |?評論 (0)?編輯

End-To-End Memory Networks

摘要: End-To-End Memory Networks 2019-05-20?14:37:35 Paper：https://papers.nips.cc/paper/5846-end-to-end-memory-networks.pdf Code：https://github.com/facebook閱讀全文

posted @?2019-05-20 14:39?AHU-WangXiao 閱讀(16) |?評論 (0)?編輯

Graph Convolutional Tracking

該文被密碼保護。

posted @?2019-05-05 11:00?AHU-WangXiao 閱讀(4) |?評論 (0)?編輯

Target-Aware Deep Tracking

摘要: Target-Aware Deep Tracking 2019-05-03?11:33:18 Paper:?https://arxiv.org/pdf/1904.01772.pdf Code:?https://github.com/XinLi-zn/TADT 1. Background and Mo閱讀全文

posted @?2019-05-03 11:50?AHU-WangXiao 閱讀(125) |?評論 (0)?編輯

論文筆記：Progressive Differentiable Architecture Search:Bridging the Depth Gap between Search and Evaluation

該文被密碼保護。

posted @?2019-04-30 11:50?AHU-WangXiao 閱讀(10) |?評論 (0)?編輯

論文筆記：Heterogeneous Memory Enhanced Multimodal Attention Model for Video Question Answering

摘要: Heterogeneous Memory Enhanced Multimodal Attention Model for?Video Question Answering 2019-04-25?21:43:11 Paper：https://arxiv.org/pdf/1904.04357.pdf C閱讀全文

posted @?2019-04-25 21:46?AHU-WangXiao 閱讀(65) |?評論 (0)?編輯

論文筆記：Decoders Matter for Semantic Segmentation: Data-Dependent Decoding Enables Flexible Feature Aggregation

摘要: Decoders Matter for Semantic Segmentation:?Data-Dependent Decoding Enables Flexible Feature Aggregation 2019-04-24?16:53:25 Paper：https://arxiv.org/pd閱讀全文

posted @?2019-04-24 16:58?AHU-WangXiao 閱讀(77) |?評論 (0)?編輯

論文筆記：Fast Neural Architecture Search of Compact Semantic Segmentation Models via Auxiliary Cells

摘要: Fast Neural Architecture Search of Compact Semantic Segmentation Models?via Auxiliary Cells 2019-04-24?14:49:10 Paper：https://arxiv.org/pdf/1810.10804閱讀全文

posted @?2019-04-24 14:51?AHU-WangXiao 閱讀(54) |?評論 (0)?編輯

論文筆記：Feature Selective Anchor-Free Module for Single-Shot Object Detection

該文被密碼保護。

posted @?2019-04-22 09:47?AHU-WangXiao 閱讀(1) |?評論 (0)?編輯

論文筆記：Unsupervised Deep Tracking

該文被密碼保護。

posted @?2019-04-15 22:15?AHU-WangXiao 閱讀(1) |?評論 (0)?編輯

論文筆記：SPM-Tracker: Series-Parallel Matching for Real-Time Visual Object Tracking

該文被密碼保護。

posted @?2019-04-10 10:43?AHU-WangXiao 閱讀(2) |?評論 (0)?編輯

論文筆記：Prediction-Tracking-Segmentation

摘要: Prediction-Tracking-Segmentation 2019-04-09?18:47:30 Paper：https://arxiv.org/pdf/1904.03280.pdf 之所以要講這篇文章，是因為，我很喜歡這個文章的思路，即：基于 prediction 的跟蹤。廢話不多說，來看閱讀全文

posted @?2019-04-09 18:49?AHU-WangXiao 閱讀(268) |?評論 (3)?編輯

論文筆記：Hierarchical Attentive Recurrent Tracking

該文被密碼保護。

posted @?2019-04-03 22:00?AHU-WangXiao 閱讀(4) |?評論 (0)?編輯

論文筆記：SiamRPN++: Evolution of Siamese Visual Tracking with Very Deep Networks

摘要: SiamRPN++: Evolution of Siamese Visual Tracking with Very Deep Networks 2019-04-02?12:44:36 Paper：https://arxiv.org/pdf/1812.11703.pdf Project：https:/閱讀全文

posted @?2019-04-02 12:45?AHU-WangXiao 閱讀(238) |?評論 (0)?編輯

論文筆記：Self-Attention Generative Adversarial Networks

該文被密碼保護。

posted @?2019-03-21 22:21?AHU-WangXiao 閱讀(11) |?評論 (0)?編輯

論文筆記：Siamese Cascaded Region Proposal Networks for Real-Time Visual Tracking

摘要: Siamese Cascaded Region Proposal Networks for Real-Time Visual Tracking 2019-03-20?16:45:23 Paper：https://arxiv.org/pdf/1812.06148.pdf Code：（尚無） 背景與動機閱讀全文

posted @?2019-03-20 16:51?AHU-WangXiao 閱讀(316) |?評論 (0)?編輯

論文筆記：ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware

摘要: ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware 2019-03-19?16:13:18 Paper：https://openreview.net/forum?id=HylVB3AqYm Code：閱讀全文

posted @?2019-03-19 16:14?AHU-WangXiao 閱讀(265) |?評論 (0)?編輯

論文筆記：DARTS: Differentiable Architecture Search

摘要: DARTS: Differentiable Architecture Search 2019-03-19?10:04:26accepted by ICLR 2019 Paper：https://arxiv.org/pdf/1806.09055.pdf Code：https://github.com/閱讀全文

posted @?2019-03-19 10:05?AHU-WangXiao 閱讀(324) |?評論 (0)?編輯

論文筆記：Progressive Neural Architecture Search

摘要: Progressive Neural Architecture Search 2019-03-18?20:28:13 Paper：http://openaccess.thecvf.com/content_ECCV_2018/papers/Chenxi_Liu_Progressive_Neural_A閱讀全文

posted @?2019-03-18 20:42?AHU-WangXiao 閱讀(96) |?評論 (0)?編輯

論文筆記：Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation

摘要: Auto-DeepLab:?Hierarchical Neural Architecture Search for Semantic Image Segmentation2019-03-18?14:45:44 Paper：https://arxiv.org/pdf/1901.02985 Offica閱讀全文

posted @?2019-03-18 14:52?AHU-WangXiao 閱讀(253) |?評論 (0)?編輯

論文筆記：Deeper and Wider Siamese Networks for Real-Time Visual Tracking

摘要: Deeper and Wider Siamese Networks for Real-Time Visual TrackingUpdated on 2019-04-01?16:10:37 Paper (arXiv V3)：https://arxiv.org/pdf/1901.01660.pdf Co閱讀全文

posted @?2019-03-14 20:01?AHU-WangXiao 閱讀(130) |?評論 (0)?編輯

論文筆記：ATOM: Accurate Tracking by Overlap Maximization

摘要: ATOM: Accurate Tracking by Overlap Maximization 2019-03-12 23:48:42 Paper：https://arxiv.org/pdf/1811.07628 Code:?https://github.com/visionml/pytrackin閱讀全文

posted @?2019-03-12 23:54?AHU-WangXiao 閱讀(465) |?評論 (0)?編輯

論文筆記：Learning deep representations by mutual information estimation and maximization

該文被密碼保護。

posted @?2019-02-21 22:15?AHU-WangXiao 閱讀(3) |?評論 (0)?編輯

論文筆記：Learning Attribute-Specific Representations for Visual Tracking

摘要: Learning Attribute-Specific Representations for Visual Tracking AAAI-2019 Paper：http://faculty.ucmerced.edu/mhyang/papers/aaai2019_tracking.pdf 本文提出一種閱讀全文

posted @?2019-02-20 23:35?AHU-WangXiao 閱讀(393) |?評論 (4)?編輯

論文筆記：Learning regression and verification networks for long-term visual tracking

摘要: Learning regression and verification networks for long-term visual tracking 2019-02-18?22:12:25 Paper：https://arxiv.org/abs/1809.04320 Code：https://gi閱讀全文

posted @?2019-02-18 22:14?AHU-WangXiao 閱讀(207) |?評論 (0)?編輯

論文筆記：Towards Diverse and Natural Image Descriptions via a Conditional GAN

摘要: 論文筆記：Towards Diverse and Natural Image Descriptions via a Conditional GAN ICCV 2017 Paper: http://openaccess.thecvf.com/content_ICCV_2017/papers/Dai_T閱讀全文

posted @?2019-01-24 22:18?AHU-WangXiao 閱讀(175) |?評論 (0)?編輯

論文筆記：DRAW: A Recurrent Neural Network For Image Generation

該文被密碼保護。

posted @?2019-01-14 19:44?AHU-WangXiao 閱讀(1) |?評論 (0)?編輯

Learning deep representations by mutual information estimation and maximization

該文被密碼保護。

posted @?2018-12-16 16:10?AHU-WangXiao 閱讀(12) |?評論 (0)?編輯

Convolutional Pose Machines

摘要: Convolutional Pose Machines 2018-12-10?18:17:20 Paper：https://www.cv-foundation.org/openaccess/content_cvpr_2016/papers/Wei_Convolutional_Pose_Machine閱讀全文

posted @?2018-12-10 18:21?AHU-WangXiao 閱讀(104) |?評論 (0)?編輯

High Performance Visual Tracking with Siamese Region Proposal Network

該文被密碼保護。

posted @?2018-11-26 18:36?AHU-WangXiao 閱讀(42) |?評論 (0)?編輯

論文閱讀：Deep Attentive Tracking via Reciprocative Learning

摘要: Deep Attentive Tracking via Reciprocative Learning 2018-11-14?13:30:36 Paper:?https://arxiv.org/abs/1810.03851 Project page:?https://ybsong00.github.i閱讀全文

posted @?2018-11-14 14:12?AHU-WangXiao 閱讀(283) |?評論 (0)?編輯

Paper Read: Convolutional Image Captioning

摘要: Convolutional Image Captioning 2018-11-04?20:42:07 Paper:?http://openaccess.thecvf.com/content_cvpr_2018/papers/Aneja_Convolutional_Image_Captioning_C閱讀全文

posted @?2018-11-04 20:44?AHU-WangXiao 閱讀(103) |?評論 (0)?編輯

論文筆記: Mutual Learning to Adapt for Joint Human Parsing and Pose Estimation

摘要: Mutual Learning to Adapt for Joint Human Parsing and Pose Estimation 2018-11-03?09:58:58 Paper:?http://openaccess.thecvf.com/content_ECCV_2018/papers/閱讀全文

posted @?2018-11-03 10:03?AHU-WangXiao 閱讀(65) |?評論 (0)?編輯

Macro-Micro Adversarial Network for Human Parsing

摘要: Macro-Micro Adversarial Network for Human Parsing ECCV-2018 2018-10-27?15:15:07 Paper:?https://arxiv.org/pdf/1807.08260.pdf Code:?https://github.com/R閱讀全文

posted @?2018-10-27 15:17?AHU-WangXiao 閱讀(132) |?評論 (0)?編輯

論文筆記：Mask R-CNN

摘要: Mask R-CNN 2018-11-23?21:00:33 Paper：https://arxiv.org/pdf/1703.06870.pdf Code： Official Implementation:?https://github.com/facebookresearch/maskrcnn-閱讀全文

posted @?2018-10-23 22:47?AHU-WangXiao 閱讀(78) |?評論 (0)?編輯

論文筆記：Real-Time MDNet

摘要: Real-Time MDNet ECCV 2018 2018-10-22?15:52:01 Paper：http://openaccess.thecvf.com/content_ECCV_2018/papers/Ilchae_Jung_Real-Time_MDNet_ECCV_2018_paper.閱讀全文

posted @?2018-10-22 15:58?AHU-WangXiao 閱讀(312) |?評論 (0)?編輯

論文筆記：Visual Semantic Navigation Using Scene Priors

摘要: Visual Semantic Navigation Using Scene Priors 2018-10-21?19:39:26 Paper: https://arxiv.org/pdf/1810.06543.pdf Demo：https://www.youtube.com/watch?v=otK閱讀全文

posted @?2018-10-21 19:43?AHU-WangXiao 閱讀(169) |?評論 (0)?編輯

論文筆記：Relational inductive biases, deep learning, and graph networks

該文被密碼保護。

posted @?2018-10-08 14:20?AHU-WangXiao 閱讀(6) |?評論 (0)?編輯

論文筆記：Improving Deep Visual Representation for Person Re-identification by Global and Local Image-language Association

摘要: Improving Deep Visual Representation for?Person Re-identification by Global and Local?Image-language Association2018-09-29?19:36:43 Paper：http://opena閱讀全文

posted @?2018-09-29 19:39?AHU-WangXiao 閱讀(163) |?評論 (2)?編輯

論文筆記：Exploring Visual Relationship for Image Captioning

該文被密碼保護。

posted @?2018-09-23 21:53?AHU-WangXiao 閱讀(3) |?評論 (0)?編輯

【論文筆記】CBAM: Convolutional Block Attention Module

摘要: CBAM: Convolutional Block Attention Module 2018-09-14?21:52:42 Paper：http://openaccess.thecvf.com/content_ECCV_2018/papers/Sanghyun_Woo_Convolutional_閱讀全文

posted @?2018-09-14 22:01?AHU-WangXiao 閱讀(1177) |?評論 (0)?編輯

論文筆記：Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks

摘要: Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks ICML 2017 Paper：https://arxiv.org/pdf/1703.03400.pdf Code for the regression and sup閱讀全文

posted @?2018-09-09 21:37?AHU-WangXiao 閱讀(829) |?評論 (0)?編輯

論文筆記：Concept Mask: Large-Scale Segmentation from Semantic Concepts

摘要: Concept Mask: Large-Scale Segmentation from Semantic Concepts 2018-08-21?11:16:07 Paper：https://arxiv.org/pdf/1808.06032.pdf 本文做了這么一件事：給定一張圖片以及概念名詞，輸出閱讀全文

posted @?2018-08-21 13:31?AHU-WangXiao 閱讀(174) |?評論 (0)?編輯

論文筆記：A Structured Self-Attentive Sentence Embedding

摘要: A Structured Self-Attentive Sentence Embedding ICLR 2017 2018-08-19 14:07:29 Paper：https://arxiv.org/pdf/1703.03130.pdf Code（PyTorch）:?https://github.閱讀全文

posted @?2018-08-19 15:44?AHU-WangXiao 閱讀(817) |?評論 (0)?編輯

深度學習課程筆記（十八）Deep Reinforcement Learning - Part 1 (17/11/27) Lectured by Yun-Nung Chen @ NTU CSIE

摘要: 深度學習課程筆記（十八）Deep Reinforcement Learning - Part 1 (17/11/27) Lectured by Yun-Nung Chen @ NTU CSIE 2018-08-11?13:42:23 This video can be found from:?htt閱讀全文

posted @?2018-08-11 13:50?AHU-WangXiao 閱讀(547) |?評論 (1)?編輯

論文筆記：Show, Attend and Tell: Neural Image Caption Generation with Visual Attention

摘要: Show, Attend and Tell: Neural Image Caption?Generation with Visual Attention 2018-08-10?10:15:06 Paper (ICML-2015)：http://proceedings.mlr.press/v37/xu閱讀全文

posted @?2018-08-10 10:20?AHU-WangXiao 閱讀(219) |?評論 (0)?編輯

論文閱讀：Learning Visual Question Answering by Bootstrapping Hard Attention

摘要: Learning Visual Question Answering by Bootstrapping Hard Attention Google DeepMind ECCV-2018 2018-08-05?19:24:44 Paper：https://arxiv.org/abs/1808.0030閱讀全文

posted @?2018-08-05 20:27?AHU-WangXiao 閱讀(272) |?評論 (3)?編輯

（轉）Understanding Memory in Deep Learning Systems: The Neuroscience, Psychology and Technology Perspectives

摘要: Understanding Memory in Deep Learning Systems: The Neuroscience, Psychology and Technology Perspectives 2018-08-05?18:50:06 This blog is copied from:?閱讀全文

posted @?2018-08-05 18:55?AHU-WangXiao 閱讀(78) |?評論 (0)?編輯

論文閱讀：Videos as Space-Time Region Graphs

摘要: Videos as Space-Time Region Graphs ECCV 2018 Xiaolong Wang 2018-08-03?11:16:01 Paper：arXiv 本文利用視頻中時空上的 proposal 之間的關系，來進行行為識別的建模。 如上圖所示，本文將 video 看做是?閱讀全文

posted @?2018-08-03 11:18?AHU-WangXiao 閱讀(819) |?評論 (0)?編輯

論文筆記：Person Re-identification with Deep Similarity-Guided Graph Neural Network

摘要: Person Re-identification with?Deep Similarity-Guided Graph Neural Network 2018-07-27?17:41:45 Paper：?https://128.84.21.199/pdf/1807.09975.pdf 本文將 Grap閱讀全文

posted @?2018-07-27 17:44?AHU-WangXiao 閱讀(467) |?評論 (0)?編輯

Paper Read: Robust Deep Multi-modal Learning Based on Gated Information Fusion Network

摘要: Robust Deep Multi-modal Learning Based on?Gated Information Fusion Network 2018-07-27?14:25:26 Paper：https://arxiv.org/pdf/1807.06233.pdf Related Pape閱讀全文

posted @?2018-07-27 14:53?AHU-WangXiao 閱讀(324) |?評論 (7)?編輯

Paper Read: Deep learning

該文被密碼保護。

posted @?2018-07-23 22:58?AHU-WangXiao 閱讀(1) |?評論 (0)?編輯

論文筆記：Learning Dynamic Memory Networks for Object Tracking

摘要: Learning Dynamic Memory Networks for Object?Tracking ECCV 2018Updated on?2018-08-05?16:36:30 Paper: arXiv version Code: https://github.com/skyoung/Mem閱讀全文

posted @?2018-07-21 16:44?AHU-WangXiao 閱讀(805) |?評論 (0)?編輯

論文筆記：Variational Capsules for Image Analysis and Synthesis

摘要: Variational Capsules for Image Analysis and Synthesis 2018-07-16?16:54:36 Paper：?https://arxiv.org/pdf/1807.04099.pdf 隨著深度學習的崛起，已經有很多不同的應用領域都取得了巨大的成功，閱讀全文

posted @?2018-07-16 17:43?AHU-WangXiao 閱讀(123) |?評論 (0)?編輯

論文筆記之：Semi-Supervised Learning via Compact Latent Space Clustering

該文被密碼保護。

posted @?2018-07-12 17:19?AHU-WangXiao 閱讀(2) |?評論 (0)?編輯

An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling

摘要: An Empirical Evaluation of Generic Convolutional and Recurrent Networks?for Sequence Modeling?2018-05-16?16:09:15 Introduction： 本文提出一種 TCN （Temporal C閱讀全文

posted @?2018-05-16 16:25?AHU-WangXiao 閱讀(281) |?評論 (0)?編輯

Multi-attention Network for One Shot Learning

摘要: Multi-attention Network for One Shot Learning 2018-05-15?22:35:50 本文的貢獻點在于： 1. 表明類別標簽信息對 one shot learning 可以提供幫助，并且設計一種方法來挖掘該信息； 2. 提出一種 attention ne閱讀全文

posted @?2018-05-15 22:54?AHU-WangXiao 閱讀(295) |?評論 (0)?編輯

論文筆記：Frustum PointNets for 3D Object Detection from RGB-D Data

該文被密碼保護。

posted @?2018-05-03 21:55?AHU-WangXiao 閱讀(3) |?評論 (0)?編輯

論文筆記：Tracking by Natural Language Specification

摘要: Tracking by Natural Language Specification 2018-04-27?15:16:13 Paper:?http://openaccess.thecvf.com/content_cvpr_2017/papers/Li_Tracking_by_Natural_CVP閱讀全文

posted @?2018-04-27 15:32?AHU-WangXiao 閱讀(287) |?評論 (0)?編輯

論文筆記：Diffusion-Convolutional Neural Networks （傳播-卷積神經網絡）

摘要: Diffusion-Convolutional Neural Networks （傳播-卷積神經網絡）2018-04-09?21:59:02 1. Abstract: 我們提出傳播-卷積神經網絡（DCNNs），一種處理 graph-structured data 的新模型。隨著 DCNNs 的介紹，閱讀全文

posted @?2018-04-09 22:48?AHU-WangXiao 閱讀(853) |?評論 (0)?編輯

論文閱讀之：Deep Meta Learning for Real-Time Visual Tracking based on Target-Specific Feature Space

摘要: Deep Meta Learning for Real-Time Visual Tracking based on Target-Specific?Feature Space 2018-01-04 15:58:15 寫在前面：為什么要看這個paper？這篇 paper 貌似是第一個將 meta-le閱讀全文

posted @?2018-01-04 16:08?AHU-WangXiao 閱讀(1068) |?評論 (0)?編輯

論文筆記之：Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering

該文被密碼保護。

posted @?2017-12-18 00:30?AHU-WangXiao 閱讀(10) |?評論 (0)?編輯

論文筆記之：SeqGAN: Sequence generative adversarial nets with policy gradient

摘要: SeqGAN: Sequence generative adversarial nets with policy gradient AAAI-2017 Paper:?https://arxiv.org/abs/1609.05473 Offical Tensorflow Code:?https://g閱讀全文

posted @?2017-11-26 21:14?AHU-WangXiao 閱讀(890) |?評論 (0)?編輯

論文筆記之：GraphGAN: Graph Representation Learning with Generative Adversarial Nets

該文被密碼保護。

posted @?2017-11-25 11:14?AHU-WangXiao 閱讀(7) |?評論 (0)?編輯

Interacted Action-Driven Visual Tracking Algorithm

該文被密碼保護。

posted @?2017-11-19 21:35?AHU-WangXiao 閱讀(4) |?評論 (0)?編輯

論文筆記：Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments

摘要: Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments 2017-10-25 16:38:23 【Project Page】https://blog.openai.com/learning-to-cooperat閱讀全文

posted @?2017-10-25 18:08?AHU-WangXiao 閱讀(437) |?評論 (0)?編輯

Paper Reading: Perceptual Generative Adversarial Networks for Small Object Detection

摘要: Perceptual Generative Adversarial Networks for Small Object Detection 2017-07-11 19:47:46 CVPR 2017 This paper use GAN to handle the issue of small ob閱讀全文

posted @?2017-07-11 21:04?AHU-WangXiao 閱讀(702) |?評論 (0)?編輯

Paper Reading: In Defense of the Triplet Loss for Person Re-Identification

摘要: In Defense of the Triplet Loss for Person Re-Identification 2017-07-02 14:04:20 This blog comes from:?http://blog.csdn.net/shuzfan/article/details/700閱讀全文

posted @?2017-07-02 14:11?AHU-WangXiao 閱讀(1207) |?評論 (0)?編輯

論文筆記之：Deep Attributes Driven Multi-Camera Person Re-identification

摘要: Deep Attributes Driven Multi-Camera Person?Re-identification?2017-06-28 21:38:55 【Motivation】 本文的網絡設計主要分為三個部分： Stage 1: Fully-supervised dCNN training閱讀全文

posted @?2017-06-28 21:53?AHU-WangXiao 閱讀(1047) |?評論 (1)?編輯

論文閱讀：Deep Reinforcement Learning based Image Captioning with Embedding Reward

該文被密碼保護。

posted @?2017-04-29 11:41?AHU-WangXiao 閱讀(8) |?評論 (0)?編輯

論文筆記之：Learning Cross-Modal Deep Representations for Robust Pedestrian Detection

摘要: Learning Cross-Modal Deep Representations for Robust Pedestrian Detection 2017-04-11 19:40:22 Motivation： 本文主要是考慮了在光照極端惡劣的情況下，如何充分的利用 thermal data 進行協閱讀全文

posted @?2017-04-11 19:56?AHU-WangXiao 閱讀(1098) |?評論 (0)?編輯

PredNet --- Deep Predictive coding networks for video prediction and unsupervised learning --- 論文筆記

摘要: PredNet Deep Predictive coding networks for video prediction and unsupervised learning ICLR 2017 2017.03.12 Code and video examples can be found at: h閱讀全文

posted @?2017-03-12 19:50?AHU-WangXiao 閱讀(1253) |?評論 (0)?編輯

Learning to Compare Image Patches via Convolutional Neural Networks --- Reading Summary

摘要: Learning to Compare Image Patches via Convolutional Neural Networks Reading Summary 2017.03.08 Target: this paper attempt to learn a geneal similarity閱讀全文

posted @?2017-03-08 21:23?AHU-WangXiao 閱讀(676) |?評論 (0)?編輯

論文筆記之：Co-saliency Detection via A Self-paced Multiple-instance Learning Framework

摘要: Co-saliency Detection via A Self-paced?Multiple-instance Learning Framework T-PAMI 2016 摘要：Co-saliency detection 從一組圖像中提取出共同顯著的物體。一方面，傳統的檢測方法嚴重依賴于手工設計閱讀全文

posted @?2016-11-04 09:37?AHU-WangXiao 閱讀(645) |?評論 (0)?編輯

論文筆記之：Hybrid computing using a neural network with dynamic external memory

摘要: Hybrid computing using a neural network with dynamic external memory Nature 2016 updated on 2018-07-21?15:30:31 Paper：http://www.nature.com/nature/jou閱讀全文

posted @?2016-10-14 13:15?AHU-WangXiao 閱讀(1418) |?評論 (0)?編輯

論文筆記之： Deep Metric Learning via Lifted Structured Feature Embedding

摘要: Deep Metric Learning via Lifted Structured Feature Embedding CVPR 2016 摘要：本文提出一種距離度量的方法，充分的發揮 training batches 的優勢，by lifting the vector of pairwise d閱讀全文

posted @?2016-09-29 20:02?AHU-WangXiao 閱讀(7700) |?評論 (3)?編輯

論文筆記之：Fully-Convolutional Siamese Networks for Object Tracking

摘要: Fully-Convolutional Siamese Network?for Object Tracking Updated on 2018-11-19?10:17:29 Paper: http://www.robots.ox.ac.uk/~vedaldi/assets/pubs/bertinet閱讀全文

posted @?2016-09-22 18:27?AHU-WangXiao 閱讀(8656) |?評論 (3)?編輯

論文筆記之：End-to-End Localization and Ranking for Relative Attributes

摘要: End-to-End Localization and Ranking for?Relative Attributes arXiv Paper 摘要：本文提出一種 end-to-end 的屬性識別方法，能夠同時定位和相對屬性的排序（simultaneously localize and rank r閱讀全文

posted @?2016-08-10 11:55?AHU-WangXiao 閱讀(238) |?評論 (0)?編輯

論文筆記之：Playing for Data: Ground Truth from Computer Games

摘要: Playing for Data: Ground Truth from Computer Games ECCV 2016 Project Page：http://download.visinf.tu-darmstadt.de/data/from_games/index.html arXiv Pape閱讀全文

posted @?2016-08-10 01:33?AHU-WangXiao 閱讀(909) |?評論 (0)?編輯

論文閱讀之：Is Faster R-CNN Doing Well for Pedestrian Detection?

摘要: Is Faster R-CNN Doing Well for Pedestrian Detection? ECCV 2016 Liliang Zhang & Kaiming He 原文鏈接：http://arxiv.org/pdf/1607.07032v2.pdf Code ：?https://gi閱讀全文

posted @?2016-08-07 20:11?AHU-WangXiao 閱讀(6415) |?評論 (17)?編輯

論文筆記之：Generative Adversarial Nets

摘要: Generative Adversarial Nets NIPS 2014 摘要：本文通過對抗過程，提出了一種新的框架來預測產生式模型，我們同時訓練兩個模型：一個產生式模型 G，該模型可以抓住數據分布；還有一個判別式模型 D 可以預測來自訓練樣本　而不是 G 的樣本的概率．訓練 G 的目的是讓 D?閱讀全文

posted @?2016-08-06 21:49?AHU-WangXiao 閱讀(8124) |?評論 (6)?編輯

3D CNN for Video Processing

摘要: 3D CNN for Video Processing Updated on?2018-08-06?19:53:57 本文主要是總結下當前流行的處理 Video 信息的深度神經網絡的處理方法． 參考文獻： 1.?3D Convolutional Neural Networks?for Human A閱讀全文

posted @?2016-08-03 21:05?AHU-WangXiao 閱讀(552) |?評論 (0)?編輯

Introduction to Monte Carlo Tree Search （蒙特卡羅搜索樹簡介）

摘要: Introduction to Monte Carlo Tree Search （蒙特卡羅搜索樹簡介） 部分翻譯自“Monte Carlo Tree Search and Its Applications”。 論文鏈接：http://digitalcommons.morris.umn.edu/cgi閱讀全文

posted @?2016-07-15 19:12?AHU-WangXiao 閱讀(1563) |?評論 (0)?編輯

論文筆記：Mastering the game of Go with deep neural networks and tree search

摘要: Mastering the game of Go with deep neural networks and tree search Nature 2015 這是本人論文筆記系列第二篇 Nature 的文章了，第一篇是 DQN。好緊張！好興奮！ 本文可謂是在世界上賺夠了吸引力！ 圍棋游戲被看做是 A閱讀全文

posted @?2016-07-14 21:08?AHU-WangXiao 閱讀(118) |?評論 (0)?編輯

論文筆記之：Continuous Deep Q-Learning with Model-based Acceleration

摘要: Continuous Deep Q-Learning with Model-based Acceleration 本文提出了連續動作空間的深度強化學習算法。 開始正文之前，首先要弄清楚兩個概念：Model-free 和 Model-based。引用 周志華老師的《機器學習》中的一段話來解釋這個概念，閱讀全文

posted @?2016-07-12 20:39?AHU-WangXiao 閱讀(912) |?評論 (0)?編輯

論文筆記之：Human-level control through deep reinforcement learning

摘要: Human-level control through deep reinforcement?learning Nature 2015 Google DeepMind Abstract RL 理論 在動物行為上，深入到心理和神經科學的角度，關于在一個環境中如何使得 agent 優化他們的控制，提供了閱讀全文

posted @?2016-06-13 16:00?AHU-WangXiao 閱讀(172) |?評論 (0)?編輯

論文筆記之：Multiple Object Recognition With Visual Attention

摘要: Multiple Object Recognition With?Visual Attention Google DeepMind ICRL 2015 本文提出了一種基于 attention 的用于圖像中識別多個物體的模型。該模型是利用RL來訓練?Deep RNN，以找到輸入圖像中最相關的區域。盡管閱讀全文

posted @?2016-06-05 00:41?AHU-WangXiao 閱讀(3923) |?評論 (0)?編輯

論文筆記之：Attention For Fine-Grained Categorization

摘要: Attention For Fine-Grained Categorization Google ICLR 2015 本文說是將Ba et al. 的基于RNN 的attention model 拓展為受限更少，或者說是非受限的視覺場景。這個工作和前者很大程度上的不同在于，用一個更加有效的視覺網絡，閱讀全文

posted @?2016-06-04 23:47?AHU-WangXiao 閱讀(855) |?評論 (1)?編輯

論文筆記之：From Facial Parts Responses to Face Detection: A Deep Learning Approach

該文被密碼保護。

posted @?2016-06-01 20:54?AHU-WangXiao 閱讀(132) |?評論 (0)?編輯

論文筆記之： Bilinear CNN Models for Fine-grained Visual Recognition

摘要: Bilinear CNN Models for Fine-grained Visual Recognition CVPR 2015 本文提出了一種雙線性模型( bilinear models)，一種識別結構，該結構由兩個特征提取器產生，兩個輸出是圖像每一個位置的外積(outer product)，然閱讀全文

posted @?2016-05-30 01:08?AHU-WangXiao 閱讀(3048) |?評論 (0)?編輯

論文筆記之： Recurrent Models of Visual Attention

摘要: Recurrent Models of Visual Attention Google DeepMind 模擬人類看東西的方式，我們并非將目光放在整張圖像上，盡管有時候會從總體上對目標進行把握，但是也是將目光按照某種次序（例如，從上倒下，從左到右等等）在圖像上進行掃描，然后從一個區域轉移到另一個區域閱讀全文

posted @?2016-05-28 15:06?AHU-WangXiao 閱讀(10378) |?評論 (1)?編輯

論文筆記之：Localizing by Describing: Attribute-Guided Attention Localization for Fine-Grained Recognition

摘要: Localizing by Describing: Attribute-Guided?Attention Localization for Fine-Grained Recognition Baidu Research 本文主要是將part描述利用起來，協助進行part定位，針對每一個定位好的par閱讀全文

posted @?2016-05-27 21:45?AHU-WangXiao 閱讀(467) |?評論 (0)?編輯

論文筆記之：Fully Convolutional Attention Localization Networks: Efficient Attention Localization for Fine-Grained Recognition

摘要: Fully Convolutional Attention Localization Networks: Efficient Attention?Localization for Fine-Grained Recognition 細粒度的識別（Fine-grained recognition）的挑戰閱讀全文

posted @?2016-05-26 20:38?AHU-WangXiao 閱讀(2896) |?評論 (0)?編輯

論文筆記之： Wide Residual Networks

摘要: Wide Residual Networks閱讀全文

posted @?2016-05-25 20:45?AHU-WangXiao 閱讀(531) |?評論 (0)?編輯

論文筆記之：Dynamic Label Propagation for Semi-supervised Multi-class Multi-label Classification ICCV 2013

摘要: Dynamic Label Propagation for?Semi-supervised Multi-class Multi-label Classification ICCV 2013 在基于Graph的半監督學習方法中，分類的精度高度依賴于可用的有標簽數據 和 相似性度量的精度。此處，本文提出閱讀全文

posted @?2016-05-23 15:50?AHU-WangXiao 閱讀(223) |?評論 (0)?編輯

論文筆記之：MatchNet: Unifying Feature and Metric Learning for Patch-Based Matching

摘要: MatchNet: Unifying Feature and Metric Learning for Patch-Based Matching CVPR 2015 本來都寫到一半了，突然筆記本死機了，淚崩！好吧，重新寫！本文提出了一種聯合的學習patch表示的一個深度網絡 和 魯棒的特征比較的網絡結閱讀全文

posted @?2016-05-21 17:53?AHU-WangXiao 閱讀(3528) |?評論 (0)?編輯

論文筆記之：Active Object Localization with Deep Reinforcement Learning

摘要: Active Object Localization with Deep Reinforcement Learning ICCV 2015 最近Deep Reinforcement Learning算是火了一把，在Google Deep Mind的主頁上，更是許多關于此的paper，基本都發在ICM閱讀全文

posted @?2016-04-27 13:16?AHU-WangXiao 閱讀(3314) |?評論 (10)?編輯

論文閱讀之　Inferring Analogous Attributes CVPR 2014

摘要: Inferring Analogous Attributes CVPR 2014 Chao-Yeh Chen and Kristen Grauman Abstract: The appearance of an attribute can vary considerably from class t閱讀全文

?

?

近200篇小樣本學習領域/元學習領域論文集

至?vieo.zhu@foxmail.com申請

?

?

總結

以上是生活随笔為你收集整理的论文阅读博客||很多论文阅读笔记的全部內容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網站內容還不錯，歡迎將生活随笔推薦給好友。