计算机视觉领域顶会CVPR 2018 接受论文列表

2018 年 5 月 26 日 专知

【导读】计算机视觉最具影响力的学术会议之一的IEEE CVPR将于2018年6月18日-22日在美国盐湖城召开举行。据 CVPR 官网显示,今年大会有超过 3300 篇论文投稿,其中录取 979 篇;相比去年 783 篇论文,今年增长了近 25%。



详细录用名单日前已经公布,可参见:http://cvpr2018.thecvf.com/files/cvpr_2018_final_accept_list.txt


https://github.com/amusi/daily-paper-computer-vision/blob/master/2018/cvpr2018-paper-list.csv


论文列表:


CVPR 2018 Accepted Papers

Single-Shot Refinement Neural Network for Object Detection
Video  Captioning via Hierarchical Reinforcement Learning
DensePose:  Multi-Person Dense Human Pose Estimation In The Wild
DensePose:  Multi-Person Dense Human Pose Estimation In The Wild
Frustum  PointNets for 3D Object Detection from RGB-D Data
Tips and  Tricks for Visual Question Answering: Learnings from the 2017 Challenge
Rethinking  the Faster R-CNN Architecture for Temporal Action Localization
Shape from  Shading through Shape Evolution
Shape from  Shading through Shape Evolution
A  High-Quality Denoising Dataset for Smartphone Cameras
Improving  Color Reproduction Accuracy in the Camera Imaging Pipeline
End-to-End  Dense Video Captioning with Masked Transformer
End-to-End  Dense Video Captioning with Masked Transformer
pOSE: Pseudo  Object Space Error for Initialization-Free Bundle Adjustment
Learning to  Segment Every Thing
Density-aware  Single Image De-raining using a Multi-stream Dense Network
Densely  Connected Pyramid Dehazing Network
Embodied  Question Answering
TieNet:  Text-Image Embedding Network for Common Thorax Disease Classification and  Reporting in Chest X-rays
TieNet:  Text-Image Embedding Network for Common Thorax Disease Classification and  Reporting in Chest X-rays
Towards  Open-Set Identity Preserving Face Synthesis
Baseline  Desensitizing In Translation Averaging
Learning  from the Deep: A Revised Underwater Image Formation Model
Context  Encoding for Semantic Segmentation
Context  Encoding for Semantic Segmentation
Deep Texture  Manifold for Ground Terrain Recognition
DS*: Tighter  Lifting-Free Convex Relaxations for Quadratic Matching Problems
Sparse,  Smart Contours to Represent and Edit Images
Every Smile  is Unique: Landmark-guided Diverse Smile Generation
Generative  Non-Rigid Shape Completion with Graph Convolutional Autoencoders
Learning a  Discriminative Prior for Blind Image Deblurring
Attentional  ShapeContextNet for Point Cloud Recognition
Learning  Superpixels with Segmentation-Aware Affinity Loss
Real-World  Repetition Estimation by Div, Grad and Curl
Real-World  Repetition Estimation by Div, Grad and Curl
Recurrent  Saliency Transformation Network: Incorporating Multi-Stage Visual Cues for  Small Organ Segmentation
MegaDepth:  Learning Single-View Depth Prediction from Internet Photos
Learning  Intrinsic Image Decomposition from Watching the World
Learning  Intrinsic Image Decomposition from Watching the World
Don't Just  Assume; Look and Answer: Overcoming Priors for Visual Question Answering
Human-centric  Indoor Scene Synthesis Using Stochastic Grammar
Learning by  Asking Questions
Instance  Embedding Transfer to Unsupervised Video Object Segmentation
Detect-and-Track:  Efficient Pose Estimation in Videos
Self-Supervised  Adversarial Hashing Networks for Cross-Modal Retrieval
Guided  Proofreading of Automatic Segmentations for Connectomics
Augmented  Skeleton Space Transfer for Depth-based Hand Pose Estimation
Augmented  Skeleton Space Transfer for Depth-based Hand Pose Estimation
Context-aware  Synthesis for Video Frame Interpolation
2D/3D Pose  Estimation and Action Recognition using Multitask Deep Learning
NAG: Network  for Adversary Generation
LiteFlowNet:  A Lightweight Convolutional Neural Network for Optical Flow Estimation
LiteFlowNet:  A Lightweight Convolutional Neural Network for Optical Flow Estimation
Avatar-Net:  Multi-scale Zero-shot Style Transfer by Feature Decoration
Multi-view  Harmonized Bilinear Network for 3D Object Recognition
Multi-view  Harmonized Bilinear Network for 3D Object Recognition
Tangent  Convolutions for Dense Prediction in 3D
Tangent  Convolutions for Dense Prediction in 3D
Semi-parametric  Image Synthesis
Semi-parametric  Image Synthesis
Interactive  Image Segmentation with Latent Diversity
3D Hand Pose  Estimation: From Current Achievements to Future Goals
3D Hand Pose  Estimation: From Current Achievements to Future Goals
W2F: A  Weakly-Supervised to Fully-Supervised Framework for Object Detection
BlockDrop:  Dynamic Inference Paths in Residual Networks
BlockDrop:  Dynamic Inference Paths in Residual Networks
MapNet:  Geometry-Aware Learning of Maps for Camera Localization
MapNet:  Geometry-Aware Learning of Maps for Camera Localization
BPGrad:  Towards Global Optimality in Deep Learning via Branch and Pruning
Salient  Object Detection Driven by Fixation Prediction
3D Object  Detection with Latent Support Surfaces
Practical  Block-wise Neural Network Architecture Generation
Practical  Block-wise Neural Network Architecture Generation
Glimpse  Clouds: Human Activity Recognition from Unstructured Feature Points
Are You  Talking to Me? Reasoned Visual Dialog Generation through Adversarial Learning
Are You  Talking to Me? Reasoned Visual Dialog Generation through Adversarial Learning
Visual  Grounding via Accumulated Attention
Supervision-by-Registration:  An Unsupervised Approach to Improve the Precision of Facial Landmark  Detectors
ISTA-Net:  Interpretable Optimization-Inspired Deep Network for Image Compressive  Sensing
Perturbative  Neural Networks: Rethinking Convolution in CNNs
Nonlinear 3D  Face Morphable Model
Nonlinear 3D  Face Morphable Model
Neural Baby  Talk
Neural Baby  Talk
Towards Pose  Invariant Face Recognition in the Wild
MoNet: Deep  Motion Exploitation for Video Object Segmentation
Exploring  Disentangled Feature Representation Beyond Face Identification
Towards  Effective Low-bitwidth Convolutional Neural Networks
Parallel  Attention: A Unified Framework for Visual Object Discovery through Dialogs  and Queries
Learning  Facial Action Units from Web Images with Scalable Weakly Supervised  Clustering
Few-Shot  Image Recognition by Predicting Parameters from Activations
Few-Shot  Image Recognition by Predicting Parameters from Activations
Single-Shot  Object Detection with Enriched Semantics
Unifying  Identification and Context Learning for Person Recognition
Separating  Self-Expression and Visual Content in Hashtag Supervision
Multi-Cue  Correlation Filters for Robust Visual Tracking
Beyond  Trade-off: Accelerate FCN-based Face Detection with Higher Accuracy
On the  Robustness of Semantic Segmentation Models to Adversarial Attacks
PWC-Net:  CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume
PWC-Net:  CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume
Illuminant  Spectra-based Source Separation Using Flash Photography
Illuminant  Spectra-based Source Separation Using Flash Photography
Tracking  Multiple Objects Outside the Line of Sight using Speckle Imaging
Tracking  Multiple Objects Outside the Line of Sight using Speckle Imaging
Improved  Human Pose Estimation through Adversarial Data Augmentation
Generative  Adversarial Learning Towards Fast Weakly Supervised Detection
Audio to  Body Dynamics
Audio to  Body Dynamics
The  Unreasonable Effectiveness of Deep Features as a Perceptual Metric
Frame-Recurrent  Video Super-Resolution
Deep Mutual  Learning
Real-world  Anomaly Detection in Surveillance Videos
Soccer on  Your Tabletop
Diversity  Regularized Spatiotemporal Attention for Video-based Person Re-identification
HashGAN:  Deep Learning to Hash with Pair Conditional Wasserstein GAN
Excitation  Backprop for RNNs
Dynamic-Structured  Semantic Propagation Network
Super SloMo:  High Quality Estimation of Multiple Intermediate Frames for Video  Interpolation
Super SloMo:  High Quality Estimation of Multiple Intermediate Frames for Video  Interpolation
SPLATNet:  Sparse Lattice Networks for Point Cloud Processing
SPLATNet:  Sparse Lattice Networks for Point Cloud Processing
Video  Representation Learning Using Discriminative Pooling
Attend and  Interact: Higher-Order Object Interactions for Video Understanding
Human Pose  Estimation with Parsing Induced Learner
4D Human  Body Correspondences from Panoramic Depth Maps
Recognizing  Human Actions as Evolution of Pose Estimation Maps
GraphBit:  Bitwise Interaction Mining via Deep Reinforcement Learning
Deep  Adversarial Metric Learning
Deep  Adversarial Metric Learning
Revisiting  Video Saliency: A Large-scale Benchmark and a New Model
Graph-Cut  RANSAC
Five-point  Fundamental Matrix Estimation for Uncalibrated Cameras
Hashing as  Tie-Aware Learning to Rank
Optimizing  Local Feature Descriptors for Nearest Neighbor Matching
Total  Capture: A 3D Deformation Model for Tracking Faces, Hands, and Bodies
Total  Capture: A 3D Deformation Model for Tracking Faces, Hands, and Bodies
Consensus  Maximization for Semantic Region Correspondences
Consensus  Maximization for Semantic Region Correspondences
ST-GAN:  Spatial Transformer Generative Adversarial Networks for Image Compositing
Motion-Guided  Cascaded Refinement Network for Video Object Segmentation
Zigzag  Learning for Weakly Supervised Object Detection
Look,  Imagine and Match: Improving Textual-Visual Cross-Modal Retrieval with  Generative Models
Look,  Imagine and Match: Improving Textual-Visual Cross-Modal Retrieval with  Generative Models
VITON: An  Image-based Virtual Try-on Network
VITON: An  Image-based Virtual Try-on Network
Cross-Domain  Self-supervised Multi-task Feature Learning Using Synthetic Game Imagery
LayoutNet:  Reconstructing the 3D Room Layout from a Single RGB Image
Thoracic  Disease Identification and Localization with Limited Supervision
Stochastic  Downsampling for Cost-Adjustable Inference and Improved Regularization in  Convolutional Networks
Learning  Pixel-level Semantic Affinity with Image-level Supervision for Weakly  Supervised Semantic Segmentation
Deep  End-to-End Time-of-Flight Imaging
Fast and  Accurate Online Video Object Segmentation via Tracking Parts
Fast and  Accurate Online Video Object Segmentation via Tracking Parts
Min-Entropy  Latent Model for Weakly Supervised Object Detection
Future Frame  Prediction for Anomaly Detection  A New Baseline
Face Aging  with Identity-Preserved Conditional Generative Adversarial Networks
Learning to  Compare: Relation Network for Few-Shot Learning
Deep Layer  Aggregation
Deep Layer  Aggregation
Style  Aggregated Network for Facial Landmark Detection
M3:  Multimodal Memory Modelling for Video Captioning
M3:  Multimodal Memory Modelling for Video Captioning
Classification  Driven Dynamic Image Enhancement
Generative  Image Inpainting with Contextual Attention
Iterative  Visual Reasoning Beyond Convolutions
Iterative  Visual Reasoning Beyond Convolutions
Dual  Attention Matching Network for Context-Aware Feature Sequence based Person  Re-Identification
Textbook  Question Answering under Teacher Guidance with Memory Networks
Textbook  Question Answering under Teacher Guidance with Memory Networks
Multi-Level  Factorisation Net for Person Re-Identification
Functional  Map of the World
Functional  Map of the World
A Two-Step  Disentanglement Method
Towards  Faster Training of Global Covariance Pooling Networks by Iterative Matrix  Square Root Normalization
Can  Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?
Left-Right  Comparative Recurrent Model for Stereo Matching
Left-Right  Comparative Recurrent Model for Stereo Matching
Analytic  Expressions for Probabilistic Moments of PL-DNN with Gaussian Input
Analytic  Expressions for Probabilistic Moments of PL-DNN with Gaussian Input
Zero-Shot  Sketch-Image Hashing
Zero-Shot  Sketch-Image Hashing
Interpretable  Convolutional Neural Networks
Interpretable  Convolutional Neural Networks
Reconstructing  Thin Structures of Manifold Surfaces by Integrating Spatial Curves
Enhancing  the Spatial Resolution of Stereo Images using a Parallax Prior
Anticipating  Traffic Accidents with Adaptive Loss and Large-scale Incident DB
Generating  Synthetic X-ray Images of a Person from the Surface Geometry
Generating  Synthetic X-ray Images of a Person from the Surface Geometry
Attentive  Fashion Grammar Network for Fashion Landmark Detection and Clothing Category  Classification
Unsupervised  CCA
Discovering  Point Lights with Intensity Distance Fields
Universal  Denoising Networks : A Novel CNN-based Network Architecture for Image  Denoising
Easy  Identification from Better Constraints: Multi-Shot Person Re-Identification  from Reference Constraints
Recurrent  Pixel Embedding for Instance Grouping
Recurrent  Pixel Embedding for Instance Grouping
Recurrent  Scene Parsing with Perspective Understanding in the Loop
Learning to  Hash by Discrepancy Minimization
Fast  End-to-End Trainable Guided Filter
Disentangling  Structure and Aesthetics for Content-aware Image Completion
An Analysis  of Scale Invariance in Object Detection - SNIP
An Analysis  of Scale Invariance in Object Detection - SNIP
CSGNet:  Neural Shape Parser for Constructive Solid Geometry
Finding Tiny  Faces in the Wild with Generative Adversarial Network
Finding Tiny  Faces in the Wild with Generative Adversarial Network
SSNet: Scale  Selection Network for Online 3D Action Prediction
SSNet: Scale  Selection Network for Online 3D Action Prediction
Integrated  facial landmark localization and super-resolution of real-world very low  resolution faces in arbitrary poses with GANs
Integrated  facial landmark localization and super-resolution of real-world very low  resolution faces in arbitrary poses with GANs
The Best of  Both Worlds: Combining CNNs and Geometric Constraints for Hierarchical Motion  Segmentation
In-Place  Activated BatchNorm for Memory-Optimized Training of DNNs
Wing Loss  for Robust Facial Landmark Localisation with Convolutional Neural Networks
Deep  Cross-media Knowledge Transfer
Deep  Cross-media Knowledge Transfer
Coupled  End-to-end Transfer Learning with Generalized Fisher Information
Knowledge  Aided Consistency for Weakly Supervised Phrase Grounding
Viewpoint-aware  Attentive Multi-view Inference for Vehicle Re-identification
MatNet:  Modular Attention Network for Referring Expression Comprehension
CBMV: A  Coalesced Bidirectional Matching Volume for Disparity Estimation
NISP:  Pruning Networks using Neuron Importance Score Propagation
NISP:  Pruning Networks using Neuron Importance Score Propagation
Who Let The  Dogs Out? Modeling Dog Behavior From Visual Data
Efficient  Video Object Segmentation via Network Modulation
Learning  Deep Models for Face Anti-Spoofing: Binary or Auxiliary Supervision
Feedback-prop:  Convolutional Neural Network Inference under Partial Evidence
A Memory  Network Approach for Story-based Temporal Summarization of 360?Videos
Improving  Occlusion and Hard Negative Handling for Single-Stage Object Detectors
UV-GAN:  Adversarial Facial UV Map Completion for Pose-invariant Face Recognition
Learning a  Toolchain for Image Restoration
Learning a  Toolchain for Image Restoration
Learning to  Act Properly: Predicting and Explaining Affordances from Images
Learning a  Discriminative Feature Network for Semantic Segmentation
Optimizing  Video Object Detection via a Scale-Time Lattice
ShuffleNet:  An Extremely Efficient Convolutional Neural Network for Mobile Devices
Cascaded  Pyramid Network for Multi-Person Pose Estimation
Seeing  Temporal Modulation of Lights from Standard Cameras
Point-wise  Convolutional Neural Networks
Fine-grained  Video Captioning for Sports Narrative
Fine-grained  Video Captioning for Sports Narrative
Dense 3D  Regression for Hand Pose Estimation
Missing  Slice Recovery for Tensors Using a Low-rank Model in Embedded Space
Learning  Convolutional Networks for Content-weighted Image Compression
Learning  Attentions: Residual Attentional Siamese Network for High Performance Online  Visual Tracking
Deep  Cost-Sensitive and Order-Preserving Feature Learning for Cross-Population Age  Estimation
First-Person  Hand Action Benchmark with RGB-D Videos and 3D Hand Pose Annotations
Hand  PointNet: 3D Hand Pose Estimation using Point Sets
Hand  PointNet: 3D Hand Pose Estimation using Point Sets
Recovering  Realistic Texture in Image Super-resolution by Spatial Feature Modulation
Cube Padding  for Weakly-Supervised Saliency Prediction in 360$^{\circ}$ Videos
A Face to  Face Neural Conversation Model
SurfConv:  Bridging 3D and 2D Convolution for RGBD Images
Dynamic  Video Segmentation Network
Multiple  Granularity Group Interaction Prediction
Visual  Question Reasoning on General Dependency Tree
Visual  Question Reasoning on General Dependency Tree
From  Lifestyle VLOGs to Everyday Interactions
COCO-Stuff:  Thing and Stuff Classes in Context
GANerated  Hands for Real-Time 3D Hand Tracking from Monocular RGB
GANerated  Hands for Real-Time 3D Hand Tracking from Monocular RGB
Non-local  Neural Networks
Zero-shot  Recognition via Semantic Embeddings and Knowledge Graphs
Taskonomy:  Disentangling Task Transfer Learning
Taskonomy:  Disentangling Task Transfer Learning
Embodied  Real-World Active Perception
Embodied  Real-World Active Perception
SfSNet :  Learning Shape, Reflectance and Illuminance of Faces `in the wild'
SfSNet :  Learning Shape, Reflectance and Illuminance of Faces `in the wild'
End-to-end  Recovery of Human Shape and Pose
Factoring  Shape, Pose, and Layout from the 2D Image of a 3D Scene
Multi-view  Consistency as Supervisory Signal for Learning Shape and Pose Prediction
A Fast  Resection-Intersection Method for the Known Rotation Problem
Image  Generation from Scene Graphs
What Makes a  Video a Video: Analyzing Temporal Information in Video Understanding Models  and Datasets
What Makes a  Video a Video: Analyzing Temporal Information in Video Understanding Models  and Datasets
PointFusion:  Deep Sensor Fusion for 3D Bounding Box Estimation
High-Resolution  Image Synthesis and Semantic Manipulation with Conditional GANs
High-Resolution  Image Synthesis and Semantic Manipulation with Conditional GANs
Social GAN:  Socially Acceptable Trajectories with Generative Adversarial Networks
Quantization  and Training of Neural Networks for Efficient Integer-Arithmetic-Only  Inference
Quantization  and Training of Neural Networks for Efficient Integer-Arithmetic-Only  Inference
Finding  It": Weakly-Supervised Reference-Aware Visual Grounding in Instructional  Video"
Finding  It": Weakly-Supervised Reference-Aware Visual Grounding in Instructional  Video"
Unsupervised  Cross-dataset Person Re-identification by Transfer Learning of  Spatio-temporal Patterns
Kernelized  Subspace Pooling for Deep Local Descriptors
Video Rain  Removal By Multiscale Convolutional Sparse Coding
Learning  from Millions of 3D Scans for Large-scale 3D Face Recognition
Referring  Relationships
Improving  Object Localization with Fitness NMS and Bounded IoU Loss
Unsupervised  Feature Learning via Non-Parametric Instance-level Discrimination
Unsupervised  Feature Learning via Non-Parametric Instance-level Discrimination
CVM-Net:  Cross-View Matching Network for Image-Based Ground-to-Aerial Geo-Localization
CVM-Net:  Cross-View Matching Network for Image-Based Ground-to-Aerial Geo-Localization
Visual  Question Generation as Dual Task of Visual Question Answering
Visual  Question Generation as Dual Task of Visual Question Answering
Revisiting  Dilated Convolution: A Simple Approach for Weakly- and Semi- Supervised  Semantic Segmentation
Revisiting  Dilated Convolution: A Simple Approach for Weakly- and Semi- Supervised  Semantic Segmentation
Learning  Dual Convolutional Neural Networks for Low-Level Vision
Deep Video  Super-Resolution Network Using Dynamic Upsampling Filters Without Explicit  Motion Compensation
MegDet: A  Large Mini-Batch Object Detector
MegDet: A  Large Mini-Batch Object Detector
AttnGAN:  Fine-Grained Text to Image Generation with Attentional Generative Adversarial  Networks
TOM-Net:  Learning Transparent Object Matting from a Single Image
TOM-Net:  Learning Transparent Object Matting from a Single Image
End-to-End  Deep Kronecker-Product Matching for Person Re-identification
Semantic  Visual Localization
Joint Cuts  and Matching of Partitions in One Graph
Benchmarking  6DOF Outdoor Visual Localization in Changing Conditions
Benchmarking  6DOF Outdoor Visual Localization in Changing Conditions
Crowd  Counting via Adversarial Cross-Scale Consistency Pursuit
Deep  Group-shuffling Random Walk for Person Re-identification
Learning to  Detect Features in Texture Images
Learning to  Detect Features in Texture Images
Transferable  Joint Attribute-Identity Deep Learning for Unsupervised Person  Re-Identification
CarFusion:  Combining Point Tracking and Part Detection for Dynamic 3D Reconstruction of  Vehicles
Context-aware  Deep Feature Compression for High-speed Visual Tracking
Deep  Material-aware Cross-spectral Stereo Matching
Deep Extreme  Cut: From Extreme Points to Object Segmentation
Label  Denoising Adversarial Network (LDAN) for Inverse Lighting of Face Images
Label  Denoising Adversarial Network (LDAN) for Inverse Lighting of Face Images
Harmonious  Attention Network for Person Re-Identication
Unsupervised  Deep Generative Adversarial Hashing Network
Unsupervised  Deep Generative Adversarial Hashing Network
Pseudo-Mask  Augmented Object Detection
LSTM  stack-based Neural Multi-sequence Alignment TeCHnique (NeuMATCH)
LSTM  stack-based Neural Multi-sequence Alignment TeCHnique (NeuMATCH)
Adversarial  Complementary Learning for Weakly Supervised Object Localization
Unsupervised  Discovery of Object Landmarks as Structural Representations
Unsupervised  Discovery of Object Landmarks as Structural Representations
DeLS-3D:  Deep Localization and Segmentation with a 3D Semantic Map
Monocular  Relative Depth Perception with Web Stereo Data Supervision
Image-Image  Domain Adaptation with Preserved Self-Similarity and Domain-Dissimilarity for  Person Re-identification
Objects as  context for detecting their semantic parts
Camera Style  Adaptation for Person Re-identification
Conditional  Generative Adversarial Network for Structured Domain Adaptation
Rotation-sensitive  Regression for Oriented Scene Text Detection
Residual  Parameter Transfer for Deep Domain Adaptation
SGPN:  Similarity Group Proposal Network for 3D Point Cloud Instance Segmentation
SGPN:  Similarity Group Proposal Network for 3D Point Cloud Instance Segmentation
Weakly  Supervised Instance Segmentation using Class Peak Response
Weakly  Supervised Instance Segmentation using Class Peak Response
Robust  Facial Landmark Detection via a Fully-Convolutional Local-Global Context  Network
Rotation  Averaging and Strong Duality
Rotation  Averaging and Strong Duality
PackNet:  Adding Multiple Tasks to a Single Network by Iterative Pruning
Im2Flow:  Motion Hallucination from Static Images for Action Recognition
Im2Flow:  Motion Hallucination from Static Images for Action Recognition
Feature  Quantization for Defending Against Distortion of Images
End-to-end  weakly-supervised semantic alignment
PointGrid: A  Deep Network for 3D Shape Understanding
PointGrid: A  Deep Network for 3D Shape Understanding
Imagine it  for me: Generative Adversarial Approach for Zero-Shot Learning from Noisy  Texts
A Minimalist  Approach to Type-Agnostic Detection of Quadrics in Point Clouds
A Benchmark  for Articulated Human Pose Estimation and Tracking
Boosting  Self-Supervised Learning via Knowledge Transfer
PPFNet:  Global Context Aware Local Features for Robust 3D Point Matching
PPFNet:  Global Context Aware Local Features for Robust 3D Point Matching
Vision-and-Language  Navigation: Interpreting visually-grounded navigation instructions in real  environments
Vision-and-Language  Navigation: Interpreting visually-grounded navigation instructions in real  environments
Fast Video  Object Segmentation by Reference-Guided Mask Propagation
Fast Video  Object Segmentation by Reference-Guided Mask Propagation
Super-Resolving  Very Low-Resolution Face Images with Supplementary Attributes
Video Person  Re-identification with Competitive Snippet-similarity Aggregation and  Co-attentive Snippet Embedding
One-shot  Action Localization by Sequence Matching Network
Efficient  Subpixel Refinement with Symbolic Linear Predictors
Distort-and-Recover:  Color Enhancement using Deep Reinforcement Learning
Group  Consistent Similarity Learning via Deep CRFs for Person Re-Identification
Group  Consistent Similarity Learning via Deep CRFs for Person Re-Identification
Single Image  Reflection Separation with Perceptual Losses
AVA: A Video  Dataset of Spatio-temporally Localized Atomic Visual Actions
AVA: A Video  Dataset of Spatio-temporally Localized Atomic Visual Actions
Recognize  Actions by Disentangling Components of Dynamics
Zoom and  Learn: Generalizing Deep Stereo Matching to Novel Domains
Attention-aware  Compositional Network for Person Re-Identification
HATS:  Histograms of Averaged Time Surfaces for Robust Event-based Object  Classification
Mask-guided  Contrastive Attention Model for Person Re-Identification
Pose-Guided  Photorealistic Face Rotation
Pose-Guided  Photorealistic Face Rotation
Automatic 3D  Indoor Scene Modeling from Single Panorama
Automatic 3D  Indoor Scene Modeling from Single Panorama
SobolevFusion:  3D Reconstruction of Scenes Undergoing Free Non-rigid Motion
SobolevFusion:  3D Reconstruction of Scenes Undergoing Free Non-rigid Motion
A  Biresolution Spectral framework for Product Quantization
Dynamic  Zoom-in Network for Fast Object Detection in Large Images
On the  Importance of Label Quality for Semantic Segmentation
EPINET: A  Fully-Convolutional Neural Network for Light Field Depth Estimation by Using  Epipolar Geometry
A  Pose-Sensitive Embedding for Person Re-Identification with Expanded Cross  Neighborhood Re-Ranking
Erase or  Fill? Deep Joint Recurrent Rain Removal and Reconstruction in Videos
Scalable and  Effective Deep CCA via Soft Decorrelation
High-order  tensor regularization with application to attribute ranking
3D-RCNN:  Instance-level 3D Scene Understanding via Render-and-Compare
3D-RCNN:  Instance-level 3D Scene Understanding via Render-and-Compare
FoldingNet:  Interpretable Unsupervised Learning on 3D Point Clouds
FoldingNet:  Interpretable Unsupervised Learning on 3D Point Clouds
Defocus Blur  Detection via Multi-Stream Bottom-Top-Bottom Fully Convolutional Network
Decorrelated  Batch Normalization
Unsupervised  Textual Grounding: Linking Words to Image Concepts
Unsupervised  Textual Grounding: Linking Words to Image Concepts
Scale-recurrent  Network for Deep Image Deblurring
Low-Shot  Recognition with Imprinted Weights
Bottom-Up  and Top-Down Attention for Image Captioning and Visual Question Answering
Bottom-Up  and Top-Down Attention for Image Captioning and Visual Question Answering
Cross-Domain  Weakly-Supervised Object Detection through Progressive Domain Adaptation
Facelet-Bank  for Fast Portrait Manipulation
Duplex  Generative Adversarial Network for Unsupervised Domain Adaptation
Quantization  of Fully Convolutional Networks for Accurate Biomedical Image Segmentation
Real-Time  Rotation-Invariant Face Detection with Progressive Calibration Networks
Structure  Preserving Video Prediction
Tagging Like  Humans: Diverse and Distinct Image Annotation
Learning to  Sketch with Shortcut Cycle Consistency
GroupCap:  Group-based Image Captioning with Structured Relevance and Diversity  Constraints
Dynamic  Scene Deblurring Using Spatially Variant Recurrent Neural Networks
Dynamic  Scene Deblurring Using Spatially Variant Recurrent Neural Networks
Hyperparameter  Optimization for Tracking with Continuous Deep Q-Learning
Deep  Unsupervised Saliency Detection: A Multiple Noisy Labeling Perspective
Deep  Unsupervised Saliency Detection: A Multiple Noisy Labeling Perspective
NeuralNetwork-Viterbi:  A Framework for Weakly Supervised Video Learning
NeuralNetwork-Viterbi:  A Framework for Weakly Supervised Video Learning
Detecting  and Recognizing Human-Object Interactions
Detecting  and Recognizing Human-Object Interactions
Augmenting  Crowd-Sourced 3D Reconstructions using Semantic Detections
Visual  Relationship Learning with a Factorization-based Prior
Re-weighted  Adversarial Adaptation Network for Unsupervised Domain Adaptation
Flow Guided  Recurrent Neural Encoder for Video Salient Object Detection
Disentangling  3D Pose in A Dendritic CNN for Unconstrained 2D Face Alignment
Progressive  Attention Guided Recurrent Network for Salient Object Detection
Answer with  Grounding Snippets: Focal Visual-Text Attention for Visual Question Answering
Answer with  Grounding Snippets: Focal Visual-Text Attention for Visual Question Answering
Unsupervised  Learning of Depth and Egomotion from Monocular Video Using 3D Geometric  Constraints
Repulsion  Loss: Detecting Pedestrians in a Crowd
PU-Net:  Point Cloud Upsampling Network
Video Object  Segmentation via Inference in A CNN-Based Higher-Order Spatio-Temporal MRF
Video Object  Segmentation via Inference in A CNN-Based Higher-Order Spatio-Temporal MRF
PiCANet:  Learning Pixel-wise Contextual Attention for Saliency Detection
Gated Fusion  Network for Single Image Dehazing
Interleaved  Structured Sparse Convolutional Neural Networks
Interleaved  Structured Sparse Convolutional Neural Networks
Where and  Why Are They Looking? Jointly Inferring Human Attention and Intentions in  Complex Tasks
End-to-end  Flow Correlation Tracking with Spatial-temporal Attention
Left/Right  Asymmetric Layer Skippable Networks
Context  Contrasted Feature and Gated Multi-scale Aggregation for Scene Segmentation
Context  Contrasted Feature and Gated Multi-scale Aggregation for Scene Segmentation
VITAL:  VIsual Tracking via Adversarial Learning
VITAL:  VIsual Tracking via Adversarial Learning
RotationNet:  Joint Object Categorization and Pose Estimation Using Multiviews from  Unsupervised Viewpoints
Action Sets:  Weakly Supervised Action Segmentation without Ordering Constraints
Action Sets:  Weakly Supervised Action Segmentation without Ordering Constraints
Squeeze-and-Excitation  Networks
Squeeze-and-Excitation  Networks
Edit  Probability for Scene Text Recognition
Bidirectional  Attentive Fusion with Context Gating for Dense Video Captioning
Bidirectional  Attentive Fusion with Context Gating for Dense Video Captioning
Exploit the  Unknown Gradually:~ One-Shot Video-Based Person Re-Identification by Stepwise  Learning
Learning to  Localize Sound Source in Visual Scenes
Dynamic  Few-Shot Visual Learning without Forgetting
Weakly-Supervised  Semantic Segmentation by Iteratively Mining Common Object Features
SINT++:  Robust Visual Tracking via Adversarial Hard Positive Generation
Real-Time  Monocular Depth Estimation using Synthetic Data with Domain Adaptation via  Image Style Transfer
Fast and  Accurate Single Image Super-Resolution via Information Distillation Network
Low-Latency  Video Semantic Segmentation
Low-Latency  Video Semantic Segmentation
Domain  Adaptive Faster R-CNN for Object Detection in the Wild
DoubleFusion:  Real-time Capture of Human Performance with Inner Body Shape from a Single  Depth Sensor
DoubleFusion:  Real-time Capture of Human Performance with Inner Body Shape from a Single  Depth Sensor
Lean  Multiclass Crowdsourcing
Lean  Multiclass Crowdsourcing
Tell Me  Where To Look: Guided Attention Inference Network
Tell Me  Where To Look: Guided Attention Inference Network
Residual  Dense Network for Image Super-Resolution
Residual  Dense Network for Image Super-Resolution
Look at  Boundary: A Boundary-Aware Face Alignment Algorithm
Imagination-IQA:  No-reference Image Quality Assessment via Adversarial Learning
Memory  Matching Networks for One-Shot Image Recognition
3D Human  Pose Estimation in the Wild by Adversarial Learning
Unsupervised  Training for 3D Morphable Model Regression
Unsupervised  Training for 3D Morphable Model Regression
Scalable  Dense Non-rigid Structure-from-Motion: A Grassmannian Perspective
IQA: Visual  Question Answering in Interactive Environments
Learning  Spatial-Temporal Regularized Correlation Filters for Visual Tracking
Low-shot  Learning from Imaginary Data
Low-shot  Learning from Imaginary Data
Deep  Regression Forests for Age Estimation
Partial  Transfer Learning with Selective Adversarial Networks
Partial  Transfer Learning with Selective Adversarial Networks
A  Bi-directional Message Passing Model for Salient Object Detection
Transductive  Unbiased Embedding for Zero-Shot Learning
Scale-Transferrable  Object Detection
Crowd  Counting with Deep Negative Correlation Learning
Deep Cauchy  Hashing for Hamming Space Retrieval
Demo2Vec:  Reasoning Object Affordances from Online Videos
GVCNN:  Group-View Convolutional Neural Networks for 3D Shape Recognition
An  End-to-End TextSpotter with Explicit Alignment and Attention
Stereoscopic  Neural Style Transfer
Bootstrapping  the Performance of Webly Supervised Semantic Segmentation
Learning  Markov Clustering Networks for Scene Text Detection
Collaborative  and Adversarial Network for Unsupervised domain adaptation
Collaborative  and Adversarial Network for Unsupervised domain adaptation
Reflection  Removal for Large-Scale 3D Point Clouds
Pose  Transferrable Person Re-Identification
Learning to  Adapt Structured Output Space for Semantic Segmentation
Learning to  Adapt Structured Output Space for Semantic Segmentation
Efficient  Diverse Ensemble for Discriminative Co-Tracking
Learning a  Single Convolutional Super-Resolution Network for Multiple Degradations
Probabilistic  Plant Modeling via Multi-View Image-to-Image Translation
Learning to  Parse Wireframes in Images of Man-Made Environments
A  Variational U-Net for Conditional Appearance and Shape Generation
A  Variational U-Net for Conditional Appearance and Shape Generation
Learning to  Find Good Correspondences
Learning to  Find Good Correspondences
Actor and  Action Video Segmentation from a Sentence
Actor and  Action Video Segmentation from a Sentence
Towards a  Mathematical Understanding of the Difficulty in Learning with Feedforward  Neural Networks
Weakly-supervised  Deep Convolutional Neural Network Learning for Facial Action Unit Intensity  Estimation
Maximum  Classifier Discrepancy for Unsupervised Domain Adaptation
Maximum  Classifier Discrepancy for Unsupervised Domain Adaptation

由于微信字数限制,没有全部显示,详细list 请查看Amusi整理的

https://github.com/amusi/daily-paper-computer-vision


-END-

专 · 知

人工智能领域主题知识资料查看与加入专知人工智能服务群

【专知AI服务计划】专知AI知识技术服务会员群加入人工智能领域26个主题知识资料全集获取欢迎微信扫一扫加入专知人工智能知识星球群,获取专业知识教程视频资料和与专家交流咨询


请PC登录www.zhuanzhi.ai或者点击阅读原文,注册登录专知,获取更多AI知识资料

请加专知小助手微信(扫一扫如下二维码添加),加入专知主题群(请备注主题类型:AI、NLP、CV、 KG等)交流~

关注专知公众号,获取人工智能的专业知识!

点击“阅读原文”,使用专知

登录查看更多
7

相关内容

Networking:IFIP International Conferences on Networking。 Explanation:国际网络会议。 Publisher:IFIP。 SIT: http://dblp.uni-trier.de/db/conf/networking/index.html
ACL2020接受论文列表公布,571篇长文208篇短文
专知会员服务
66+阅读 · 2020年5月19日
专知会员服务
109+阅读 · 2020年3月12日
近期必读的5篇AI顶会CVPR 2020 GNN (图神经网络) 相关论文
专知会员服务
78+阅读 · 2020年3月3日
抢鲜看!13篇CVPR2020论文链接/开源代码/解读
专知会员服务
49+阅读 · 2020年2月26日
【快讯】CVPR2020结果出炉,1470篇上榜, 你的paper中了吗?
近期必读的5篇 CVPR 2019【图卷积网络】相关论文和代码
专知会员服务
32+阅读 · 2020年1月10日
CVPR2020接收论文开源代码
专知
30+阅读 · 2020年2月29日
NeurIPS2019机器学习顶会接受论文列表!
GAN生成式对抗网络
17+阅读 · 2019年9月6日
CVPR 2019 | 34篇 CVPR 2019 论文实现代码
AI科技评论
21+阅读 · 2019年6月23日
CVPR 2019 | 重磅!34篇 CVPR2019 论文实现代码
AI研习社
11+阅读 · 2019年6月21日
【NIPS2018】接收论文列表
专知
5+阅读 · 2018年9月10日
自然语言处理顶会EMNLP2018接受论文列表!
专知
87+阅读 · 2018年8月26日
人工智能领域顶会IJCAI 2018 接受论文列表
专知
5+阅读 · 2018年5月16日
Interpretable CNNs for Object Classification
Arxiv
20+阅读 · 2020年3月12日
Local Relation Networks for Image Recognition
Arxiv
4+阅读 · 2019年4月25日
Single-frame Regularization for Temporally Stable CNNs
Arxiv
11+阅读 · 2018年5月13日
Arxiv
7+阅读 · 2018年1月21日
Arxiv
4+阅读 · 2017年11月14日
VIP会员
相关VIP内容
ACL2020接受论文列表公布,571篇长文208篇短文
专知会员服务
66+阅读 · 2020年5月19日
专知会员服务
109+阅读 · 2020年3月12日
近期必读的5篇AI顶会CVPR 2020 GNN (图神经网络) 相关论文
专知会员服务
78+阅读 · 2020年3月3日
抢鲜看!13篇CVPR2020论文链接/开源代码/解读
专知会员服务
49+阅读 · 2020年2月26日
【快讯】CVPR2020结果出炉,1470篇上榜, 你的paper中了吗?
近期必读的5篇 CVPR 2019【图卷积网络】相关论文和代码
专知会员服务
32+阅读 · 2020年1月10日
相关资讯
CVPR2020接收论文开源代码
专知
30+阅读 · 2020年2月29日
NeurIPS2019机器学习顶会接受论文列表!
GAN生成式对抗网络
17+阅读 · 2019年9月6日
CVPR 2019 | 34篇 CVPR 2019 论文实现代码
AI科技评论
21+阅读 · 2019年6月23日
CVPR 2019 | 重磅!34篇 CVPR2019 论文实现代码
AI研习社
11+阅读 · 2019年6月21日
【NIPS2018】接收论文列表
专知
5+阅读 · 2018年9月10日
自然语言处理顶会EMNLP2018接受论文列表!
专知
87+阅读 · 2018年8月26日
人工智能领域顶会IJCAI 2018 接受论文列表
专知
5+阅读 · 2018年5月16日
相关论文
Interpretable CNNs for Object Classification
Arxiv
20+阅读 · 2020年3月12日
Local Relation Networks for Image Recognition
Arxiv
4+阅读 · 2019年4月25日
Single-frame Regularization for Temporally Stable CNNs
Arxiv
11+阅读 · 2018年5月13日
Arxiv
7+阅读 · 2018年1月21日
Arxiv
4+阅读 · 2017年11月14日
Top
微信扫码咨询专知VIP会员