ICCV2017 論文瀏覽記錄

版權聲明：本文爲博主原創文章，未經博主容許不得轉載。 https://blog.csdn.net/qq_25819827/article/details/78469118

以前很早就想試着作一下試着把頂會的論文瀏覽一遍看一下本身感興趣的，順便統計一下國內高校或者研究機構的研究方向，下面是做爲一個圖像處理初學者在瀏覽完論文後的 以爲有趣的文章：
ICCV2017 論文瀏覽記錄
1.google deepmind :Look, Listen and Learn 多信息融合感受很厲害
2.The Weizmann Institute of Science：Non-Uniform Blind Deblurring by Reblurring 非均勻盲模糊
3.中科大(微軟亞洲研究院) :CVAE-GAN: Fine-Grained Image Generation through Asymmetric Training 對抗網絡對物體分類
4.University of California：Exploiting Spatial Structure for Localizing Manipulated Image Regions CNN+LSTM 圖像處理
5.CVLab, EPFL, Lausanne, Switzerland：Deep Occlusion Reasoning for Multi-Camera Multi-Target Detection 對比RCNN有優點
6.Computer Vision Lab, TU Dresden ：Bounding Boxes, Segmentations and Object Coordinates:How Important is Recognition for 3D Scene Flow Estimation in Autonomous Driving Scenarios 無人駕駛，車的檢測
7.University of Pennsylvania：Am I a Baller? Basketball Performance Assessment
from First-Person Videos 第一視角來評估籃球運動員的表現
8.Institute of Geodesy and Photogrammetry, ETH Zurich（蘇黎世理工）：Semantically Informed Multiview Surface Refinement 圖像語義分割
9.University of Maryland：Soft-NMS – Improving Object Detection With One Line of Code（聽名字好像很牛逼）
10.Michigan State University：Illuminating Pedestrians via Simultaneous Detection & Segmentation 行人檢測分割
11.The University of Nottingham:Binarized Convolutional Landmark Localizers for Human Pose Estimation and Face Alignment with Limited Resources 人體檢測
12.University of Surrey Guildford:SubUNets: End-to-end Hand Shape and Continuous Sign Language Recognition CNN+LSTM端到端的手語識別
13.CMU：One Network to Solve Them All — Solving Linear Inverse Problems using Deep Projection Models 圖像修復
14.南理工（南大）：Adversarial PoseNet: A Structure-aware Convolutional Network for Human Pose Estimation 人姿態估計
15.Intel Labs：Fast Image Processing with Fully-Convolutional Networks，圖片的後期處理，愛攝像的能夠看
16.北航：Look, Perceive and Segment: Finding the Salient Objects in Images
via Two-stream Fixation-Semantic CNNs SOD目標檢測
17.港中文（騰訓優圖）：Makeup-Go: Blind Reversion of Portrait Edit 照片去美化，人像還原
18.University of Southern California：Query-guided Regression Network with Context Policy for Phrase Grounding 圖像描述
19.國立清華(微軟亞洲研究院):Show, Adapt and Tell: Adversarial Training of Cross-domain Image Captioner 圖像語義理解
20.清華：Surface Normals in the Wild 表面方向單目圖像的深度估計
21.清華：SegFlow: Joint Learning for Video Object Segmentation and Optical Flow 視頻分割 光流算法
22. 中科大（港中文）：Online Multi-Object Tracking Using CNN-based Single Object Tracker with Spatial-Temporal Attention Mechanism 目標跟蹤
23.Institute of Mathematics of the Romanian Academy：Unsupervised learning from video to detect foreground objects in single images目標檢測
24.Google Brain：Pixel Recursive Super Resolution 超分辨率
25.Microsoft Research Asia：Deformable Convolutional Networks
26.港中文：Towards Diverse and Natural Image Descriptions via a Conditional GAN 對抗網絡對圖像的理解
27Georgia Institute of Technology：Learning Cooperative Visual Dialog Agents with Deep Reinforcement Learning 協做對話
28.Imperial College London：Semantic Image Synthesis via Adversarial Learning 用天然語言描述圖像合成
29.Inria：BlitzNet: A Real-Time Deep Network for Scene Understanding場景分割 貝葉斯網絡
30.CMU：Cut, Paste and Learn: Surprisingly Easy Synthesis for Instance Detection 小數據集對物體進行識別
31.美圖：Parallel Tracking and Verifying: A Framework for Real-Time and High Accuracy Visual Tracking 跟蹤 蠻好的
32.Graz University of Technology: Detect to Track and Track to Detect 目標檢測與跟蹤（給了github 進去倒是空的，有點惋惜）
33.MPI for Intelligent Systems：Semantic Video CNNs through Representation Warping視頻語義分析
34.CMU：Learning Background-Aware Correlation Filters for Visual Tracking 跟蹤
35.CMU：Need for Speed: A Benchmark for Higher Frame Rate Object Tracking 高速跟蹤的基準
36.中科大：A Multimodal Deep Regression Bayesian Network for Affective Video Content Analyses 深度迴歸貝葉斯的視頻情感分析
37.清華：VQS: Linking Segmentations to Questions and Answers for Supervised Attention in VQA and Question-Focused Semantic Segmentation 圖像分割+語義理解
38.University of Texas at Austin：On-Demand Learning for Deep Image Restoration 圖像復原
39.University of Southern California：TALL: Temporal Activity Localization via Language Query 經過語言查詢進行時態活動定位
40.CS Department Stanford University：Fine-grained Recognition in the Wild: A Multi-Task Domain Adaptation Approach 野外物體識別 李飛飛的
41.Nanyang Technological University:An Empirical Study of Language CNN for Image Captioning 圖像語義
42.天大：Learning Dynamic Siamese Network for Visual Object Tracking 追蹤
43.University of Illinois, Urbana-Champaign：Aligned Image-Word Representations Improve Inductive Transfer Across
Vision-Language Tasks 視覺問答
44.Stanford University:Characterizing and Improving Stability in Neural Style Transfer 畫風轉換 李飛飛
45.University Politehnica of Bucharest：Unsupervised object segmentation in video by selection of highly probable positive features 圖像分割
46.香港大學：SCNet: Learning Semantic Correspondence語義對應
47.西交大：Channel Pruning for Accelerating Very Deep Neural Networks 修剪深網絡 孫劍
48.Facebook AI Research：Mask R-CNN 好像性能能夠和faster RCNN媲美 VIP
49.UC Berkeley：Localizing Moments in Video with Natural Language 視頻語義
50.The University of Tokyo:Joint Detection and Recounting of Abnormal Events by Learning Deep Generic Knowledge 圖像語義
51.University of California：Learning to Reason: End-to-End Module Networks for Visual Question Answering 視覺問答
52.北大：Centered Weight Normalization in Accelerating Training of Deep Neural Networks 對網絡權重進行從新規劃
53.CMU：Learning Policies for Adaptive Tracking with Deep Feature Cascades 跟蹤
54.國科大：Wavelet-SRNet: A Wavelet-based CNN for Multi-scale Face Super Resolution 人臉超分辨率
55.University of California：Scene Parsing with Global Context Embedding 圖像分割
56.ETH Zurich：DSLR-Quality Photos on Mobile Devices with Deep Convolutional Networks 學習提升照片的質量
57NUS Graduate School for Integrative Science and Engineering：Video Scene Parsing with Predictive Feature Learning
視頻情景解析
58.Stanford University：Inferring and Executing Programs for Visual Reasoning 情景推理 李飛飛
59.Rochester Institute of Technology：An Analysis of Visual Question Answering Algorithms 視覺問答
60.Joint learning of object and action detectors 物體跟蹤與動做識別
61.Tel Aviv University：Temporal Tessellation: A Unified Approach for Video Analysis 視頻語義分析
62.University of Mannheim：Higher-Order Minimum Cost Lifted Multicuts for Motion Segmentation物體分割
63.Korea University：CDTS: Collaborative Detection, Tracking, and Segmentation for Online Multiple Object Segmentation in Videos 視頻檢測分割
64.Twitter：Fast Face-swap Using Convolutional Neural Networks 快速換臉，好像蠻有意思的
65.Stanford University：Dense-Captioning Events in Videos 視頻語義 能上下文 李飛飛
66.National University of Singapore：Dual-Glance Model for Deciphering Social Relationships 圖片中的社會關係 在圖像語義理解時可能有用
67.港中文：Identity-Aware Textual-Visual Matching with Latent Co-attention 圖片與句子描述之間的相識度
68.大連理工：Is Second-order Information Helpful for Large-scale Visual Recognition? 關於卷積神經網深層信息
69.Snap Inc（閱後即焚應用），雅虎，谷歌：Learning from Noisy Labels with Distillation 從雜亂標籤中學習，對標註不精確
70.港中文：Learning to Disambiguate by Asking Discriminative Questions 消除回答奇異的方法，關於VQA
71.成電：Leveraging Weak Semantic Relevance for Complex Video Event Classification 視頻事件分析
72.港中文：Scene Graph Generation from Objects, Phrases and Region Captions 圖像語義
73.港中文：Situation Recognition with Graph Neural Networks 識別情景
74.清華：Recurrent Topic-Transition GAN for Visual Paragraph Generation 對抗網絡來進行語義生成
75.深圳大學（港中文）：Cascaded Feature Network for Semantic Segmentation of RGB-D Images 圖像語義分割
76.港中文（商湯）：HydraPlus-Net: Attentive Deep Features for Pedestrian Analysis 人姿態分析
77.商湯（港中文）：Recurrent Scale Approximation for Object Detection in CNN 目標的多尺度檢測 湯曉鷗
78.中科院：Referring Expression Generation and Comprehension via Attributes 經過索引產生語義
79.Facebook AI Research：Predicting Deeper into the Future of Semantic Segmentation 預測語義
80.中山大學：Deep Dual Learning for Semantic Image Segmentation 語義理解減小對標籤數據的依賴
81.University of Illinois at Urbana-Champaign:Recurrent Models for Situation Recognition 情景識別
82.University of Zurich：Rotation equivariant vector field networks cnn+旋轉變化
83.IIT Hyderabad： Attentive Semantic Video Generation using Captions 視頻字幕 語義
84.Bosch：Universal Adversarial Perturbations Against Semantic Image Segmentation 加噪聲對圖像分割
85.POSTECH：MarioQA: Answering Questions by Watching Gameplay Videos 經過遊戲視頻進行QA
86.IIIT-Delhi：Face Sketch Matching via Coupled Deep Transform Learning 人臉與素描的匹配
87.University of Maryland：SSH: Single Stage Headless Face Detector 數臉
88.Yonsei University：Modelling the Scene Dependent Imaging in Cameras with a Deep Neural Network 用深度學習改進照片的質量
89.Mapillary Research：The Mapillary Vistas Dataset for Semantic Understanding of Street Scenes街頭情景語義理解
90.阿里（西電，西交）：Hierarchical Multimodal LSTM for Dense Visual-Semantic Embedding 語義理解
91.MIT CSAIL：Personalized Cinemagraphs using Semantic Understanding and Collaborative Learning 語義理解和協做學習
92.University of Southern California：Realistic Dynamic Facial Textures from a Single Image using GANs用對抗網絡進行面部紋理處理
93.Max Planck Institute for Informatics Saarland Informatics Campus Saabrucken：Towards a Visual Privacy Advisor:
Understanding and Predicting Privacy Risks in Images圖像關於隱私
94.Aristotle University of Thessaloniki Thessalonik：Learning Bag-of-Features Pooling for Deep Convolutional Neural Networks 提出一種新的卷積BoF
95.Weakly-supervised learning of visual relations 視覺關聯弱監督學習，和語義有部分相關
96.University of Illinois at Urbana-Champaign：Phrase Localization and Visual Relationship Detection with Comprehensive Image-Language Cues 圖像語義
97.IMEC, Belgium：Encoder Based Lifelong Learning 終身學習 好像蠻有意思的
98.Technische Universitat Munich ：Learning in an Uncertain World: Representing Ambiguity Through Multiple Hypotheses 預測不肯定 表達
99.Max Planck Institute for Intelligent Systems: EnhanceNet: Single Image Super-Resolution Through Automated Texture Synthesis 超分辨率 紋理
100.University of Maryland：Guided Perturbations: Self-corrective Behavior in Convolutional Neural Networks 主動向卷積網絡中加入擾動來提升網絡穩定性
101.Georgia Institute of Technology：Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization網絡可視化
國內：
102.Saarland Informatics Campus:Speaking the Same Language: Matching Machine to Human Captions by Adversarial Training 用對抗網絡將視頻與字幕對應起來
103.CMU：What Actions are Needed for Understanding Human Actions in Videos? 視頻人行爲分析
104.University of Jena：Generalized orderless pooling performs implicit salient matching CNN中對pooling層進行優化
105.Rutgers University, Department of Electrical and Computer Engineering：Generating High-Quality Crowd Density Maps using Contextual Pyramid CNNs 數人頭
106.University of Massachusetts：Reasoning about Fine-grained Attribute Phrases using Reference Games 提出框架描述圖片的細微區別
107.Google Research:Revisiting Unreasonable Effectiveness of Data in Deep Learning Era 蠻有意思的
108.港中文（Uber，曠視，騰訊優圖）：Detail-revealing Deep Video Super-resolution 視頻超分辨率 賈佳亞
109.上交：SORT: Second-Order Response Transform for Visual Recognition 將二階操做引入神經網絡
110.CMU：Transitive Invariance for Self-supervised Visual Representation Learning 何凱明
111.Uppsala University：Neural Ctrl-F: Segmentation-free Query-by-String Word Spotting in Handwritten Manuscript Collections 單詞位置識別
112.Facebook AI Research：Unsupervised Creation of Parameterized Avatars 根據人臉畫卡通圖像
113.The Johns Hopkins University：Adversarial Examples for Semantic Segmentation and Object Detection語義分割與目標檢測
114.The Johns Hopkins University：Genetic CNN 遺傳CNN
115. 港中文：Supplementary Meta-Learning: Towards a Dynamic Model For Deep Neural Networks 補充單元學習
116. 港中文（深圳大學）：Online Robust Image Alignment via Subspace Learning from Gradient Orientations
117.Berkeley AI Research (BAIR) laboratory：Unpaired Image-to-Image Translation
using Cycle-Consistent Adversarial Networks 喔
118.The University of Adelaide：Towards Context-aware Interaction Recognition for Visual Relationship Detection語義
119.Athens Technological & Educational Inst:Offline Handwritten Signature Modeling and Verification Based on Archetypal Analysis 簽名識別
國內：
1.華科（微軟亞洲研究院）：Ensemble Diffusion for Retrieval
華科：Transformed Low -rank Model for Line Pattern Noise Removal 去噪
華科：AOD-Net: All-in-One Dehazing Network
華科（西北工業）：When Unsupervised Domain Adaptation Meets Tensor Representations
華科（西北大學）：Jointly Attentive Spatial-Temporal Pooling Networks for Video-based Person Re-Identification 人的檢測
華科：Multi-modal Factorized Bilinear Pooling with Co-Attention Learning for Visual Question Answering 視覺問答
2.中科大(微軟亞洲研究院) :CVAE-GAN: Fine-Grained Image Generation through
Asymmetric Training
中科大（微軟亞洲研究院）：Coherent Online Video Style Transfer 關於視頻畫風轉換
中科大：A Multimodal Deep Regression Bayesian Network for Affective Video Content Analyses 深度迴歸貝葉斯的視頻情感分析
中科大（港中文）：Online Multi-Object Tracking Using CNN-based Single Object Tracker with Spatial-Temporal
中科大：DualNet: Learn Complementary Features for Image Recognition 圖像識別
中科大：VegFru: A Domain-Specific Dataset for Fine-grained Visual Categorization VegFru分類可視化
中科大：Deep Facial Action Unit Recognition from Partially Labeled Data
中科大（中山大學）：Boosting Image Captioning with Attributes 圖像的字幕
中科大：Learning Multi-Attention Convolutional Neural Network for Fine-Grained Image Recognition 圖像識別
中科大（微軟）：Flow-Guided Feature Aggregation for Video Object Detection 目標檢測
3.華南理工（蘭州大學）：A Joint Intrinsic-Extrinsic Prior Model for Retinex
華南理工（香港城市大學，中科院）Delving into Salient Object Subitizing and Detection 圖像分割
4.香港理工（哈工大）：Higher-order Integration of Hierarchical Convolutional Activations for Fine-grained Visual Categorization
香港理工（西交大，哈工大）：Joint Convolutional Analysis and Synthesis Sparse Representation for Single Image Layer Separation
香港理工（深圳大學）：3D Surface Detail Enhancement from A Single Normal Map 3D重建
香港理工：Towards More Accurate Iris Recognition Using Deeply Learned Spatially Corresponding Features 虹膜
香港理工（西電）：Multi-channel Weighted Nuclear Norm Minimization for Real Color Image Denoising 去噪
5.中科院（國科大，南審）：Egocentric Gesture Recognition Using Recurrent 3D Convolutional Neural Networks with Spatiotemporal Transformer Modules 手勢識別；
中科院（國科大）：Deep Adaptive Image Clustering深自適應聚類
中科院：Attention Mechanism 目標跟蹤
中科院：Deep Direct Regression for Multi-Oriented Scene Text Detection 文本識別
中科院：Beyond Face Rotation: Global and Local Perception GAN for Photorealistic and Identity Preserving Frontal View Synthesis關於人臉
中科院（上海科技大學，華爲）：Learning Discriminative Latent Attributes for Zero-Shot Classification（遷移學習沒看過）
中科院（西北工業）：Image2song: Song Retrieval via Bridging Image Content and Lyric Words 根據圖片內容選歌詞
中科院：Referring Expression Generation and Comprehension via Attributes 經過索引產生語義
中科院（西交大）：Tensor RPCA by Bayesian CP Factorization with Complex Noise 視頻分割，不一樣場景場景進行處理
中科院（騰訊AILab ，南理工，國科大）：Video Deblurring via Semantic Segmentation and Pixel-Wise Non-Linear Kernel
中科院（國科大）：Depth and Image Restoration from Light Field in a Scattering Medium 圖像恢復
中科院：Recursive Spatial Transformer (ReST) for Alignment-Free Face Recognition 人臉識別
中科院（天大，南方科技大學，騰訊AILab，港中文）：Range Loss for Deep Face Recognition with Long-Tailed Training Data 人臉識別相關
中科院：S3FD: Single Shot Scale-invariant Face Detector 人臉檢測器
中科院（360，國科大）：Scale-adaptive Convolutions for Scene Parsing 情景解析
中科院（南審）：CoupleNet: Coupling Global Structure with Local Parts for Object Detection 目標檢測
6.清華：HashNet: Deep Learning to Hash by Continuation
清華：Surface Normals in the Wild 單目圖像的深度估計
清華 ：SegFlow: Joint Learning for Video Object Segmentation and Optical Flow視頻分割 光流算法
清華：VQS: Linking Segmentations to Questions and Answers for Supervised Attention in VQA and Question-Focused Semantic Segmentation 圖像分割+語義理解
清華（騰訊AILab，360AI institute）FoveaNet: Perspective-aware Urban Scene Parsing 城市場景識別 自動駕駛
清華：Recurrent Topic-Transition GAN for Visual Paragraph Generation 對抗網絡來進行語義生成
清華：Mutual Enhancement for Detection of Multiple Logos in Sports Videos 商標檢測
清華：Cross-Modal Deep Variational Hashing 哈希多媒體檢索
清華：Learning Efficient Convolutional Networks through Network Slimming 加速網絡
清華：Decoder Network over Lightweight Reconstructed Feature for Fast Semantic Style Transfer 風格轉化
清華：Revisiting Cross-channel Information Transfer for Chromatic Aberration Correction 經過多通道關聯來矯正色差
清華（南理工）：Learning to Super-Resolve Blurry Face and Text Images 超分辨率
清華：Single Image Action Recognition using Semantic Body Part Actions 動做識別
7.深圳大學（西北工業，華南理工）：A Self-Balanced Min-Cut Algorithm for Image Clustering 聚類
深圳大學（港中文）：Cascaded Feature Network for Semantic Segmentation of RGB-D Images 圖像語義分割
8.南理工（南大）：Adversarial PoseNet: A Structure-aware Convolutional Network for Human Pose Estimation 人姿態估計（圖像理解）
南理工（大連理工，騰訊優圖，UC）：Learning Discriminative Data Fitting Functions for Blind Image Deblurring 圖像去模糊
9.北航：Look, Perceive and Segment: Finding the Salient Objects in Images via Two-stream Fixation-Semantic CNNs SOD目標檢測
北航：Primary Video Object Segmentation via Complementary CNNs and Neighborhood Reversible Flow 視頻圖像分割
北航：Embedding 3D Geometric Features for Rigid Object Part Segmentation 三維分割
北航（清華）：BodyFusion: Real-time Capture of Human Motion and Surface Geometry Using a Single Depth Camera 運動捕捉 表情捕捉
10.北京交通大學：Low-Rank Tensor Completion: A Pseudo-Bayesian Learning Approach
北京交通大學（中科院）：Robust Object Tracking based on Temporal and Spatial Deep Networks 基於時間和空間上的目標跟蹤
11.港中文（騰訊優圖）：Makeup-Go: Blind Reversion of Portrait Edit 照片去美化，人像還原
港中文：Towards Diverse and Natural Image Descriptions via a Conditional GAN 對抗網絡對圖像的理解
港中文：Identity-Aware Textual-Visual Matching with Latent Co-attention 圖片與句子描述之間的相識度
港中文：Learning to Disambiguate by Asking Discriminative Questions 消除回答奇異的方法，關於VQA
港中文：Scene Graph Generation from Objects, Phrases and Region Captions 圖像語義
港中文：Situation Recognition with Graph Neural Networks 識別情景
港中文：SGN: Sequential Grouping Networks for Instance Segmentation SGN圖像分割
港中文：Chained Cascade Network for Object Detection 連級網絡對對象的檢測
港中文：Video Frame Synthesis using Deep Voxel Flow 視頻幀合成 湯曉鷗
港中文（商湯）：Learning Deep Neural Networks for Vehicle Re-ID with Visual-spatio-temporal Path Proposals車輛再識別
港中文（Uber，曠視，騰訊優圖）：Detail-revealing Deep Video Super-resolution 視頻超分辨率 賈佳亞
港中文（騰訊優圖，曠視）：Zero-order Reverse Filtering反向濾波 賈佳亞
港中文：Learning Feature Pyramids for Human Pose Estimation 人姿態
港中文：StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networks
港中文：Supplementary Meta-Learning: Towards a Dynamic Model For Deep Neural Networks 補充單元學習
港中文：Temporal Action Detection with Structured Segment Networks 視頻分享 湯曉鷗
港中文（深圳大學）：Online Robust Image Alignment via Subspace Learning from Gradient Orientations
港中文：Unsupervised Learning of Stereo Matching 無監督學習立體匹配
港中文：Be Your Own Prada: Fashion Synthesis with Structural Coherence 關於時尚
港中文（商湯）：HydraPlus-Net: Attentive Deep Features for Pedestrian Analysis 人姿態分析
12.國立清華:No More Discrimination: Cross City Adaptation of Road Scene Segmenters 圖像分割（無人駕駛）
國立清華(微軟亞洲研究院):Show, Adapt and Tell: Adversarial Training of Cross-domain Image Captioner 圖像語義理解
國立清華：Robust Pseudo Random Fields for Light-Field Stereo Matching經驗的貝葉斯定理框架-魯棒僞隨機場
國立清華：Anticipating Daily Intention using On-Wrist Motion Triggered Sensing
13.海康（復旦，上交）：Focusing Attention: Towards Accurate Text Recognition in Natural Images OCR
14.騰訊優圖：Weakly- and Self-Supervised Learning for Content-Aware Deep Image Retargeting 選擇合適的放大方式對圖像進行縮放
騰訊優圖（港中文）：High-Quality Correspondence and Segmentation Estimation for Dual-Lens Smart-Phone Portraits 手機雙攝 圖像處理
騰訊優圖：Weakly Supervised Object Localization Using Things and Stuff Transfer
15.復旦：Temporal Context Network for Activity Localization in Videos
復旦（騰訊AILab）：Multi-scale Deep Learning Architectures for Person Re-identification人的
復旦（清華）：DSOD: Learning Deeply Supervised Object Detectors from Scratch 目標檢測器
復旦：Towards 3D Human Pose Estimation in the Wild: a Weakly-supervised Approach人姿態檢測
16.西電：Deep Clustering via Joint Convolutional Autoencoder Embedding and Relative Entropy Minimization
17.大連理工（南理工，桂林電子）：Blind Image Deblurring with Outlier Handling 模糊圖像清晰
大連理工，哈工大：Is Second-order Information Helpful for Large-scale Visual Recognition? 關於卷積神經網深層信息
大連理工：Stepwise Metric Promotion for Unsupervised Video Person Re-identification 無監督學習人識別
大連理工：Unsupervised Domain Adaptation for Face Recognition in Unlabeled Videos 無監督學習人臉識別
大連理工：A Stagewise Refinement Model for Detecting Salient Objects in Images 分割
大連理工：Amulet: Aggregating Multi-level Convolutional Features for Salient Object Detection 突出對象檢測
大連理工：Learning Uncertain Convolutional Features for Accurate Saliency Detection特徵點
大連理工（首都師範大學）：Surface Registration via Foliation
18.國科大（中科院，港中文）：RPAN: An End-to-End Recurrent Pose-Attention Network for Action
Recognition in Videos
國科大：Wavelet-SRNet: A Wavelet-based CNN for Multi-scale Face Super Resolution 人臉超分辨率
國科大（中科院）：Multimodal Gaussian Process Latent Variable Models with Harmonization 高斯過程隱變量模型
國科大（微軟亞洲研究院，中科院）：Human Pose Estimation using Global and Local Normalization 用局部和全局來判斷人的姿態
國科大：Soft Proposal Networks for Weakly Supervised Object Localization 定位
19.山東大學(微軟研究院):A Generic Deep Architecture for Single Image Reflection Removal and Image Smoothing 去鏡子反光
20.西交大：Complex Event Detection by Identifying Reliable Shots from Untrimmed Videos
西交大：Channel Pruning for Accelerating Very Deep Neural Networks 修剪深網絡 孫劍
西交大：Monocular 3D Human Pose Estimation by Predicting Depth on Joints 單目人姿態估計並預測深度
西交大：Predicting Human Activities Using Stochastic Grammar 人行動的預測
西交大：Should We Encode Rain Streaks in Video as Deterministic or Stochastic?
西交大：View Adaptive Recurrent Neural Networks for High Performance Human Action Recognition from Skeleton Data 人骨骼
21.美圖：Parallel Tracking and Verifying: A Framework for Real-Time and High Accuracy Visual Tracking 跟蹤 蠻好的
22.南開：Structure-measure: A New Way to Evaluate Foreground Maps 目標分割 程明明實驗室的的
23.上交（騰訊優圖）：RMPE: Regional Multi-Person Pose Estimation多人姿態估計
上交（北大）：Performance Guaranteed Network Acceleration via High-Order Residual Quantization網絡加速
上交（上海科學技術大學，上海大學）：Semi-Global Weighted Least Squares in Image Filtering 濾波
上交：SORT: Second-Order Response Transform for Visual Recognition 將二階操做引入神經網絡
20.西北工業（華南理工）：Self-paced Kernel Estimation for Robust Blind Im age Deblurring 圖像復原
西北工業：Monocular Dense 3D Reconstruction of a Complex Dynamic Scene from Two Perspective Frames
西北工業：Towards End-to-end Text Spotting with Convolutional Recurrent Neural Networks文字識別
西北工業：Efficient Global 2D-3D Matching for Camera Localization in a Large-Scale 3D Map 地圖定位
西北工業：Supervision by Fusion: Towards Unsupervised Learning of Deep Salient Object Detector 圖像分割
21.天大：Learning Dynamic Siamese Network for Visual Object Tracking 追蹤
22.香港大學：High-Resolution Shape Completion Using Deep Neural Networks for Global Structure and Local Geometry Inference 模型復原
香港大學：SCNet: Learning Semantic Correspondence語義對應
23.臺灣大學：Drone-based Object Counting by Spatially Regularized Regional Proposal Network
24.北大：Centered Weight Normalization in Accelerating Training of Deep Neural Networks 對網絡權重進行從新規劃
北大（圖森）：Factorized Bilinear Models for Image Recognition 雙線性分類
北大：Attention-aware Deep Reinforcement Learning for Video Face Recognition 視頻人臉識別
北大（北理工）：Learning long-term dependencies for action recognition with a biologically-inspired deep network 提出生物啓發網絡
北大（北理工）：Exploiting Multi-Grain Ranking Constraints for Precisely Searching Visually-similar Vehicles 檢測測量相識度
北大（上海交通大學）：Hard-Aware Deeply Cascaded Embedding
25.百度：WordSup: Exploiting Word Annotations for Character based Text Detection 文字識別
26.香港科技大學（清華）：SurfaceNet: An End-to-end 3D Neural Network for Multiview Stereopsis
香港科技大學（上海交通大學）：Online Video Object Detection using Association LSTM 用LSTM進行視頻人檢測
香港科技大學（華南理工）Lattice Long Short-Term Memory for Human Action Recognition 用CNN和LSTM來記錄人的動做
香港科技大學：Temporal Dynamic Graph LSTM for Action-driven Video Object Detection LSTM 事件的檢測
27.騰訊AILab （360AI Institute）：Video Scene Parsing with Predictive Feature Learning 視頻情景解析
騰訊AILab（商湯）：Detecting Faces Using Inside Cascaded Contextual CNN 聯級CNN 檢測
28.成電：Leveraging Weak Semantic Relevance for Complex Video Event Classification 視頻事件分析
29.國立臺灣：Unrolled Memory Inner-Products: An Abstract GPU Operator for Efficient Vision-Related Computations 關於GPU
30.北師大：3DCNN-DQN-RNN: A Deep Reinforcement Learning Framework for Semantic Parsing of Large-scale 3D Point Clouds 大規模深度學習點雲
31.浙大：Infant Footprint Recognition 嬰兒足跡識別
浙大（微軟研究院）：In this paper, we address the problem of person reidentification, which refers to associating the persons captured from different cameras 人識別
32.合肥工業（西南交通，騰訊AILab，360AI Institute）：Neural Person Search Machines 找人
33.商湯（港中文）：Recurrent Scale Approximation for Object Detection in CNN 目標的多尺度檢測 湯曉鷗
商湯（ 清華，港中文）：Orientation Invariant Feature Embedding and Spatial Temporal Regularization for Vehicle Re-identification 車輛識別
34.上海科技大學：A Revisit of Sparse Coding Based Anomaly Detection in Stacked RNN Framework 稀疏編碼
上海科技大學：Catadioptric HyperSpectral Light Field Imaging 成像技術
上海科技大學：Deep Free-Form Deformation Network for Object-Mask Registration 目標檢測
上海科技大學：Generative Modeling of Audible Shapes for Object Perception 圖像與發聲物體識別
上海科技大學：Ray Space Features for Plenoptic Structure-from-Motion
上海科技大學：Structured Attentions for Visual Question Answering
35.中山大學：Deep Dual Learning for Semantic Image Segmentation 語義理解減小對標籤數據的依賴
中山大學：Deep Growing Learning 半監督學習相關的
中山大學（商湯）：Multi-label Image Recognition by Recurrently Discovering Attentional Regions 多標籤識別
中山大學：RGB-Infrared Cross-Modality Person Re-Identification RGB+紅外 人的識別
中山大學：Cross-view Asymmetric Metric Learning for Unsupervised Person Re-identification 人檢測
36.南京大學（上交）：ThiNet: A Filter Level Pruning Method for Deep Neural Network Compression 關於神經網絡的修剪
南京大學：Adaptive Feeding: Achieving Fast and Accurate Detections by Adaptively Combining Object Detectors 目標檢測
南京大學（清華）：Monocular Free-head 3D Gaze Tracking with Deep Learning and Geometry Constraints 目光檢測
37.北郵：Object-level Proposals 圖像邊緣相關的
38.香港城市大學：Least Squares Generative Adversarial Networks
香港城市大學（深網視界）：CREST: Convolutional Residual Learning for Visual Tracking 視覺跟蹤
39.阿里（西電，西交）：Hierarchical Multimodal LSTM for Dense Visual-Semantic Embedding 語義理解
40.上海大學：Multi-stage Multi-recursive-input Fully Convolutional Networks for Neuronal Boundary Detection 卷積網絡進行邊緣檢測
41.同濟：Compositional Human Pose Regression 用迴歸來判斷人的姿態
同濟：Scale Recovery for Monocular Visual Odometry Using Depth Estimated with
Deep Convolutional Neural Fields 單目深度估計
42.哈工大：Non-Rigid Object Tracking via Deformable Patches using Shape-Preserved KC and Level Sets 提出了一種濾波器來對對象進行跟蹤
43.帝視技術：Image Super-Resolution Using Dense Skip Connections 超分辨率
44.北理工：Deep Cropping via Attention Box Prediction and Aesthetics Assessment
北理工：Super-Trajectory for Video Segmentation 視頻分割
北理工：Transferring Objects: Joint Inference of Container and Human Pose 人姿式識別
45.百度：Deep Metric Learning with Angular Loss 特徵檢測方法
46.360：Recurrent 3D-2D Dual Learning for Large-pose Facial Landmark Detection
47.臺灣中央研究院（國立臺灣大學）：DeepCD: Learning Deep Complementary Descriptors for Patch Representation 共同窗習 圖像補丁
48.廈門大學：We propose a deep network architecture for the pansharpening problem called PanNet 關於PanNet
49.香港浸會大學：Dynamic Label Graph Matching for Unsupervised Video Re-Identification 標籤估計
50.青島大學（大連理工）：Intrinsic 3D Dynamic Surface Tracking based on Dynamic Ricci Flow and Teichmuller Map 3D
51.雲南師範大學：Point Set Registration with Global-local Correspondence and Transformation Estimation
52.武漢科技大學（美圖）：Saliency Pattern Detection by Ranking Structured Trees

統計了後明白了：
你爸爸永遠是你爸爸 ，港中文的論文數給跪了