论文阅读博客||很多论文阅读笔记

元学习论文总结||小样本学习论文总结

2017-2019年计算机视觉顶会文章收录 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

该文被密码保护。

posted @ 2019-06-01 09:55 AHU-WangXiao 阅读(2) | 评论 (0) 编辑

Learning Conditioned Graph Structures for Interpretable Visual Question Answering

该文被密码保护。

posted @ 2019-05-29 00:32 AHU-WangXiao 阅读(2) | 评论 (0) 编辑

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阅读全文

posted @ 2019-05-21 11:09 AHU-WangXiao 阅读(75) | 评论 (0) 编辑

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阅读全文

posted @ 2019-05-20 19:37 AHU-WangXiao 阅读(18) | 评论 (0) 编辑

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阅读全文

posted @ 2019-05-20 14:39 AHU-WangXiao 阅读(16) | 评论 (0) 编辑

Graph Convolutional Tracking

该文被密码保护。

posted @ 2019-05-05 11:00 AHU-WangXiao 阅读(4) | 评论 (0) 编辑

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阅读全文

posted @ 2019-05-03 11:50 AHU-WangXiao 阅读(125) | 评论 (0) 编辑

论文笔记：Progressive Differentiable Architecture Search:Bridging the Depth Gap between Search and Evaluation

该文被密码保护。

posted @ 2019-04-30 11:50 AHU-WangXiao 阅读(10) | 评论 (0) 编辑

论文笔记：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阅读全文

posted @ 2019-04-25 21:46 AHU-WangXiao 阅读(65) | 评论 (0) 编辑

论文笔记：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阅读全文

posted @ 2019-04-24 16:58 AHU-WangXiao 阅读(77) | 评论 (0) 编辑

论文笔记：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阅读全文

posted @ 2019-04-24 14:51 AHU-WangXiao 阅读(54) | 评论 (0) 编辑

论文笔记：Feature Selective Anchor-Free Module for Single-Shot Object Detection

该文被密码保护。

posted @ 2019-04-22 09:47 AHU-WangXiao 阅读(1) | 评论 (0) 编辑

论文笔记：Unsupervised Deep Tracking

该文被密码保护。

posted @ 2019-04-15 22:15 AHU-WangXiao 阅读(1) | 评论 (0) 编辑

论文笔记：SPM-Tracker: Series-Parallel Matching for Real-Time Visual Object Tracking

该文被密码保护。

posted @ 2019-04-10 10:43 AHU-WangXiao 阅读(2) | 评论 (0) 编辑

论文笔记：Prediction-Tracking-Segmentation

摘要: Prediction-Tracking-Segmentation 2019-04-09 18:47:30 Paper：https://arxiv.org/pdf/1904.03280.pdf 之所以要讲这篇文章，是因为，我很喜欢这个文章的思路，即：基于 prediction 的跟踪。废话不多说，来看阅读全文

posted @ 2019-04-09 18:49 AHU-WangXiao 阅读(268) | 评论 (3) 编辑

论文笔记：Hierarchical Attentive Recurrent Tracking

该文被密码保护。

posted @ 2019-04-03 22:00 AHU-WangXiao 阅读(4) | 评论 (0) 编辑

论文笔记：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:/阅读全文

posted @ 2019-04-02 12:45 AHU-WangXiao 阅读(238) | 评论 (0) 编辑

论文笔记：Self-Attention Generative Adversarial Networks

该文被密码保护。

posted @ 2019-03-21 22:21 AHU-WangXiao 阅读(11) | 评论 (0) 编辑

论文笔记：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：（尚无） 背景与动机阅读全文

posted @ 2019-03-20 16:51 AHU-WangXiao 阅读(316) | 评论 (0) 编辑

论文笔记：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：阅读全文

posted @ 2019-03-19 16:14 AHU-WangXiao 阅读(265) | 评论 (0) 编辑

论文笔记：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/阅读全文

posted @ 2019-03-19 10:05 AHU-WangXiao 阅读(324) | 评论 (0) 编辑

论文笔记：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阅读全文

posted @ 2019-03-18 20:42 AHU-WangXiao 阅读(96) | 评论 (0) 编辑

论文笔记：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阅读全文

posted @ 2019-03-18 14:52 AHU-WangXiao 阅读(253) | 评论 (0) 编辑

论文笔记：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阅读全文

posted @ 2019-03-14 20:01 AHU-WangXiao 阅读(130) | 评论 (0) 编辑

论文笔记：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阅读全文

posted @ 2019-03-12 23:54 AHU-WangXiao 阅读(465) | 评论 (0) 编辑

论文笔记：Learning deep representations by mutual information estimation and maximization

该文被密码保护。

posted @ 2019-02-21 22:15 AHU-WangXiao 阅读(3) | 评论 (0) 编辑

论文笔记：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 本文提出一种阅读全文

posted @ 2019-02-20 23:35 AHU-WangXiao 阅读(393) | 评论 (4) 编辑

论文笔记：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阅读全文

posted @ 2019-02-18 22:14 AHU-WangXiao 阅读(207) | 评论 (0) 编辑

论文笔记：Towards Diverse and Natural Image Descriptions via a Conditional GAN

摘要: 论文笔记：Towards Diverse and Natural Image Descriptions via a Conditional GAN ICCV 2017 Paper: http://openaccess.thecvf.com/content_ICCV_2017/papers/Dai_T阅读全文

posted @ 2019-01-24 22:18 AHU-WangXiao 阅读(175) | 评论 (0) 编辑

论文笔记：DRAW: A Recurrent Neural Network For Image Generation

该文被密码保护。

posted @ 2019-01-14 19:44 AHU-WangXiao 阅读(1) | 评论 (0) 编辑

Learning deep representations by mutual information estimation and maximization

该文被密码保护。

posted @ 2018-12-16 16:10 AHU-WangXiao 阅读(12) | 评论 (0) 编辑

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阅读全文

posted @ 2018-12-10 18:21 AHU-WangXiao 阅读(104) | 评论 (0) 编辑

High Performance Visual Tracking with Siamese Region Proposal Network

该文被密码保护。

posted @ 2018-11-26 18:36 AHU-WangXiao 阅读(42) | 评论 (0) 编辑

论文阅读：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阅读全文

posted @ 2018-11-14 14:12 AHU-WangXiao 阅读(283) | 评论 (0) 编辑

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阅读全文

posted @ 2018-11-04 20:44 AHU-WangXiao 阅读(103) | 评论 (0) 编辑

论文笔记: 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/阅读全文

posted @ 2018-11-03 10:03 AHU-WangXiao 阅读(65) | 评论 (0) 编辑

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阅读全文

posted @ 2018-10-27 15:17 AHU-WangXiao 阅读(132) | 评论 (0) 编辑

论文笔记：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-阅读全文

posted @ 2018-10-23 22:47 AHU-WangXiao 阅读(78) | 评论 (0) 编辑

论文笔记：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.阅读全文

posted @ 2018-10-22 15:58 AHU-WangXiao 阅读(312) | 评论 (0) 编辑

论文笔记：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阅读全文

posted @ 2018-10-21 19:43 AHU-WangXiao 阅读(169) | 评论 (0) 编辑

论文笔记：Relational inductive biases, deep learning, and graph networks

该文被密码保护。

posted @ 2018-10-08 14:20 AHU-WangXiao 阅读(6) | 评论 (0) 编辑

论文笔记：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阅读全文

posted @ 2018-09-29 19:39 AHU-WangXiao 阅读(163) | 评论 (2) 编辑

论文笔记：Exploring Visual Relationship for Image Captioning

该文被密码保护。

posted @ 2018-09-23 21:53 AHU-WangXiao 阅读(3) | 评论 (0) 编辑

【论文笔记】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_阅读全文

posted @ 2018-09-14 22:01 AHU-WangXiao 阅读(1177) | 评论 (0) 编辑

论文笔记：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阅读全文

posted @ 2018-09-09 21:37 AHU-WangXiao 阅读(829) | 评论 (0) 编辑

论文笔记：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 本文做了这么一件事：给定一张图片以及概念名词，输出阅读全文

posted @ 2018-08-21 13:31 AHU-WangXiao 阅读(174) | 评论 (0) 编辑

论文笔记：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.阅读全文

posted @ 2018-08-19 15:44 AHU-WangXiao 阅读(817) | 评论 (0) 编辑

深度学习课程笔记（十八）Deep Reinforcement Learning - Part 1 (17/11/27) Lectured by Yun-Nung Chen @ NTU CSIE

摘要: 深度学习课程笔记（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阅读全文

posted @ 2018-08-11 13:50 AHU-WangXiao 阅读(547) | 评论 (1) 编辑

论文笔记：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阅读全文

posted @ 2018-08-10 10:20 AHU-WangXiao 阅读(219) | 评论 (0) 编辑

论文阅读：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阅读全文

posted @ 2018-08-05 20:27 AHU-WangXiao 阅读(272) | 评论 (3) 编辑

（转）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: 阅读全文

posted @ 2018-08-05 18:55 AHU-WangXiao 阅读(78) | 评论 (0) 编辑

论文阅读：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 本文利用视频中时空上的 proposal 之间的关系，来进行行为识别的建模。 如上图所示，本文将 video 看做是 阅读全文

posted @ 2018-08-03 11:18 AHU-WangXiao 阅读(819) | 评论 (0) 编辑

论文笔记：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 本文将 Grap阅读全文

posted @ 2018-07-27 17:44 AHU-WangXiao 阅读(467) | 评论 (0) 编辑

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阅读全文

posted @ 2018-07-27 14:53 AHU-WangXiao 阅读(324) | 评论 (7) 编辑

Paper Read: Deep learning

该文被密码保护。

posted @ 2018-07-23 22:58 AHU-WangXiao 阅读(1) | 评论 (0) 编辑

论文笔记：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阅读全文

posted @ 2018-07-21 16:44 AHU-WangXiao 阅读(805) | 评论 (0) 编辑

论文笔记：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 随着深度学习的崛起，已经有很多不同的应用领域都取得了巨大的成功，阅读全文

posted @ 2018-07-16 17:43 AHU-WangXiao 阅读(123) | 评论 (0) 编辑

论文笔记之：Semi-Supervised Learning via Compact Latent Space Clustering

该文被密码保护。

posted @ 2018-07-12 17:19 AHU-WangXiao 阅读(2) | 评论 (0) 编辑

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： 本文提出一种 TCN （Temporal C阅读全文

posted @ 2018-05-16 16:25 AHU-WangXiao 阅读(281) | 评论 (0) 编辑

Multi-attention Network for One Shot Learning

摘要: Multi-attention Network for One Shot Learning 2018-05-15 22:35:50 本文的贡献点在于： 1. 表明类别标签信息对 one shot learning 可以提供帮助，并且设计一种方法来挖掘该信息； 2. 提出一种 attention ne阅读全文

posted @ 2018-05-15 22:54 AHU-WangXiao 阅读(295) | 评论 (0) 编辑

论文笔记：Frustum PointNets for 3D Object Detection from RGB-D Data

该文被密码保护。

posted @ 2018-05-03 21:55 AHU-WangXiao 阅读(3) | 评论 (0) 编辑

论文笔记：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阅读全文

posted @ 2018-04-27 15:32 AHU-WangXiao 阅读(287) | 评论 (0) 编辑

论文笔记：Diffusion-Convolutional Neural Networks （传播-卷积神经网络）

摘要: Diffusion-Convolutional Neural Networks （传播-卷积神经网络）2018-04-09 21:59:02 1. Abstract: 我们提出传播-卷积神经网络（DCNNs），一种处理 graph-structured data 的新模型。随着 DCNNs 的介绍，阅读全文

posted @ 2018-04-09 22:48 AHU-WangXiao 阅读(853) | 评论 (0) 编辑

论文阅读之：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 写在前面：为什么要看这个paper？这篇 paper 貌似是第一个将 meta-le阅读全文

posted @ 2018-01-04 16:08 AHU-WangXiao 阅读(1068) | 评论 (0) 编辑

论文笔记之：Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering

该文被密码保护。

posted @ 2017-12-18 00:30 AHU-WangXiao 阅读(10) | 评论 (0) 编辑

论文笔记之：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阅读全文

posted @ 2017-11-26 21:14 AHU-WangXiao 阅读(890) | 评论 (0) 编辑

论文笔记之：GraphGAN: Graph Representation Learning with Generative Adversarial Nets

该文被密码保护。

posted @ 2017-11-25 11:14 AHU-WangXiao 阅读(7) | 评论 (0) 编辑

Interacted Action-Driven Visual Tracking Algorithm

该文被密码保护。

posted @ 2017-11-19 21:35 AHU-WangXiao 阅读(4) | 评论 (0) 编辑

论文笔记：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阅读全文

posted @ 2017-10-25 18:08 AHU-WangXiao 阅读(437) | 评论 (0) 编辑

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阅读全文

posted @ 2017-07-11 21:04 AHU-WangXiao 阅读(702) | 评论 (0) 编辑

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阅读全文

posted @ 2017-07-02 14:11 AHU-WangXiao 阅读(1207) | 评论 (0) 编辑

论文笔记之：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】 本文的网络设计主要分为三个部分： Stage 1: Fully-supervised dCNN training阅读全文

posted @ 2017-06-28 21:53 AHU-WangXiao 阅读(1047) | 评论 (1) 编辑

论文阅读：Deep Reinforcement Learning based Image Captioning with Embedding Reward

该文被密码保护。

posted @ 2017-04-29 11:41 AHU-WangXiao 阅读(8) | 评论 (0) 编辑

论文笔记之：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： 本文主要是考虑了在光照极端恶劣的情况下，如何充分的利用 thermal data 进行协阅读全文

posted @ 2017-04-11 19:56 AHU-WangXiao 阅读(1098) | 评论 (0) 编辑

PredNet --- Deep Predictive coding networks for video prediction and unsupervised learning --- 论文笔记

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阅读全文

posted @ 2017-03-12 19:50 AHU-WangXiao 阅读(1253) | 评论 (0) 编辑

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阅读全文

posted @ 2017-03-08 21:23 AHU-WangXiao 阅读(676) | 评论 (0) 编辑

论文笔记之：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 从一组图像中提取出共同显著的物体。一方面，传统的检测方法严重依赖于手工设计阅读全文

posted @ 2016-11-04 09:37 AHU-WangXiao 阅读(645) | 评论 (0) 编辑

论文笔记之：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阅读全文

posted @ 2016-10-14 13:15 AHU-WangXiao 阅读(1418) | 评论 (0) 编辑

论文笔记之： Deep Metric Learning via Lifted Structured Feature Embedding

摘要: Deep Metric Learning via Lifted Structured Feature Embedding CVPR 2016 摘要：本文提出一种距离度量的方法，充分的发挥 training batches 的优势，by lifting the vector of pairwise d阅读全文

posted @ 2016-09-29 20:02 AHU-WangXiao 阅读(7700) | 评论 (3) 编辑

论文笔记之：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阅读全文

posted @ 2016-09-22 18:27 AHU-WangXiao 阅读(8656) | 评论 (3) 编辑

论文笔记之：End-to-End Localization and Ranking for Relative Attributes

摘要: End-to-End Localization and Ranking for Relative Attributes arXiv Paper 摘要：本文提出一种 end-to-end 的属性识别方法，能够同时定位和相对属性的排序（simultaneously localize and rank r阅读全文

posted @ 2016-08-10 11:55 AHU-WangXiao 阅读(238) | 评论 (0) 编辑

论文笔记之：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阅读全文

posted @ 2016-08-10 01:33 AHU-WangXiao 阅读(909) | 评论 (0) 编辑

论文阅读之：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 原文链接：http://arxiv.org/pdf/1607.07032v2.pdf Code ： https://gi阅读全文

posted @ 2016-08-07 20:11 AHU-WangXiao 阅读(6415) | 评论 (17) 编辑

论文笔记之：Generative Adversarial Nets

摘要: Generative Adversarial Nets NIPS 2014 摘要：本文通过对抗过程，提出了一种新的框架来预测产生式模型，我们同时训练两个模型：一个产生式模型 G，该模型可以抓住数据分布；还有一个判别式模型 D 可以预测来自训练样本　而不是 G 的样本的概率．训练 G 的目的是让 D 阅读全文

posted @ 2016-08-06 21:49 AHU-WangXiao 阅读(8124) | 评论 (6) 编辑

3D CNN for Video Processing

摘要: 3D CNN for Video Processing Updated on 2018-08-06 19:53:57 本文主要是总结下当前流行的处理 Video 信息的深度神经网络的处理方法． 参考文献： 1. 3D Convolutional Neural Networks for Human A阅读全文

posted @ 2016-08-03 21:05 AHU-WangXiao 阅读(552) | 评论 (0) 编辑

Introduction to Monte Carlo Tree Search （蒙特卡罗搜索树简介）

摘要: Introduction to Monte Carlo Tree Search （蒙特卡罗搜索树简介） 部分翻译自“Monte Carlo Tree Search and Its Applications”。 论文链接：http://digitalcommons.morris.umn.edu/cgi阅读全文

posted @ 2016-07-15 19:12 AHU-WangXiao 阅读(1563) | 评论 (0) 编辑

论文笔记：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 这是本人论文笔记系列第二篇 Nature 的文章了，第一篇是 DQN。好紧张！好兴奋！ 本文可谓是在世界上赚够了吸引力！ 围棋游戏被看做是 A阅读全文

posted @ 2016-07-14 21:08 AHU-WangXiao 阅读(118) | 评论 (0) 编辑

论文笔记之：Continuous Deep Q-Learning with Model-based Acceleration

摘要: Continuous Deep Q-Learning with Model-based Acceleration 本文提出了连续动作空间的深度强化学习算法。 开始正文之前，首先要弄清楚两个概念：Model-free 和 Model-based。引用 周志华老师的《机器学习》中的一段话来解释这个概念，阅读全文

posted @ 2016-07-12 20:39 AHU-WangXiao 阅读(912) | 评论 (0) 编辑

论文笔记之：Human-level control through deep reinforcement learning

摘要: Human-level control through deep reinforcement learning Nature 2015 Google DeepMind Abstract RL 理论 在动物行为上，深入到心理和神经科学的角度，关于在一个环境中如何使得 agent 优化他们的控制，提供了阅读全文

posted @ 2016-06-13 16:00 AHU-WangXiao 阅读(172) | 评论 (0) 编辑

论文笔记之：Multiple Object Recognition With Visual Attention

摘要: Multiple Object Recognition With Visual Attention Google DeepMind ICRL 2015 本文提出了一种基于 attention 的用于图像中识别多个物体的模型。该模型是利用RL来训练 Deep RNN，以找到输入图像中最相关的区域。尽管阅读全文

posted @ 2016-06-05 00:41 AHU-WangXiao 阅读(3923) | 评论 (0) 编辑

论文笔记之：Attention For Fine-Grained Categorization

摘要: Attention For Fine-Grained Categorization Google ICLR 2015 本文说是将Ba et al. 的基于RNN 的attention model 拓展为受限更少，或者说是非受限的视觉场景。这个工作和前者很大程度上的不同在于，用一个更加有效的视觉网络，阅读全文

posted @ 2016-06-04 23:47 AHU-WangXiao 阅读(855) | 评论 (1) 编辑

论文笔记之：From Facial Parts Responses to Face Detection: A Deep Learning Approach

该文被密码保护。

posted @ 2016-06-01 20:54 AHU-WangXiao 阅读(132) | 评论 (0) 编辑

论文笔记之： Bilinear CNN Models for Fine-grained Visual Recognition

摘要: Bilinear CNN Models for Fine-grained Visual Recognition CVPR 2015 本文提出了一种双线性模型( bilinear models)，一种识别结构，该结构由两个特征提取器产生，两个输出是图像每一个位置的外积(outer product)，然阅读全文

posted @ 2016-05-30 01:08 AHU-WangXiao 阅读(3048) | 评论 (0) 编辑

论文笔记之： Recurrent Models of Visual Attention

摘要: Recurrent Models of Visual Attention Google DeepMind 模拟人类看东西的方式，我们并非将目光放在整张图像上，尽管有时候会从总体上对目标进行把握，但是也是将目光按照某种次序（例如，从上倒下，从左到右等等）在图像上进行扫描，然后从一个区域转移到另一个区域阅读全文

posted @ 2016-05-28 15:06 AHU-WangXiao 阅读(10378) | 评论 (1) 编辑

论文笔记之：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 本文主要是将part描述利用起来，协助进行part定位，针对每一个定位好的par阅读全文

posted @ 2016-05-27 21:45 AHU-WangXiao 阅读(467) | 评论 (0) 编辑

论文笔记之：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 细粒度的识别（Fine-grained recognition）的挑战阅读全文

posted @ 2016-05-26 20:38 AHU-WangXiao 阅读(2896) | 评论 (0) 编辑

论文笔记之： Wide Residual Networks

摘要: Wide Residual Networks阅读全文

posted @ 2016-05-25 20:45 AHU-WangXiao 阅读(531) | 评论 (0) 编辑

论文笔记之：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的半监督学习方法中，分类的精度高度依赖于可用的有标签数据 和 相似性度量的精度。此处，本文提出阅读全文

posted @ 2016-05-23 15:50 AHU-WangXiao 阅读(223) | 评论 (0) 编辑

论文笔记之：MatchNet: Unifying Feature and Metric Learning for Patch-Based Matching

摘要: MatchNet: Unifying Feature and Metric Learning for Patch-Based Matching CVPR 2015 本来都写到一半了，突然笔记本死机了，泪崩！好吧，重新写！本文提出了一种联合的学习patch表示的一个深度网络 和 鲁棒的特征比较的网络结阅读全文

posted @ 2016-05-21 17:53 AHU-WangXiao 阅读(3528) | 评论 (0) 编辑

论文笔记之：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的主页上，更是许多关于此的paper，基本都发在ICM阅读全文

posted @ 2016-04-27 13:16 AHU-WangXiao 阅读(3314) | 评论 (10) 编辑

论文阅读之　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阅读全文

 

 

近200篇小样本学习领域/元学习领域论文集

至 [email protected]申请