CVPR 2018 Oral Collections

3 minute read


Oral Collections (download available, total 50) of CVPR 2018!

DensePose: Multi-Person Dense Human Pose Estimation In The Wild
Context Encoding for Semantic Segmentation
Augmented Skeleton Space Transfer for Depth-based Hand Pose Estimation
Semi-parametric Image Synthesis
Practical Block-wise Neural Network Architecture Generation
Are You Talking to Me? Reasoned Visual Dialog Generation through Adversarial Learning
PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume
Illuminant Spectra-based Source Separation Using Flash Photography
SPLATNet: Sparse Lattice Networks for Point Cloud Processing
Total Capture: A 3D Deformation Model for Tracking Faces, Hands, and Bodies
Deep Layer Aggregation
Left-Right Comparative Recurrent Model for Stereo Matching
Analytic Expressions for Probabilistic Moments of PL-DNN with Gaussian Input
An Analysis of Scale Invariance in Object Detection - SNIP
Finding Tiny Faces in the Wild with Generative Adversarial Network
Taskonomy: Disentangling Task Transfer Learning
High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs
Finding It”: Weakly-Supervised Reference-Aware Visual Grounding in Instructional Video”
Unsupervised Discovery of Object Landmarks as Structural Representations
Rotation Averaging and Strong Duality
Im2Flow: Motion Hallucination from Static Images for Action Recognition
Group Consistent Similarity Learning via Deep CRFs for Person Re-Identification
3D-RCNN: Instance-level 3D Scene Understanding via Render-and-Compare
Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering
Context Contrasted Feature and Gated Multi-scale Aggregation for Scene Segmentation
Squeeze-and-Excitation Networks
DoubleFusion: Real-time Capture of Human Performance with Inner Body Shape from a Single Depth Sensor
Learning to Find Good Correspondences
Actor and Action Video Segmentation from a Sentence
Maximum Classifier Discrepancy for Unsupervised Domain Adaptation
Detail-Preserving Pooling in Deep Networks
Convolutional Neural Networks with Alternately Updated Clique
Deep Learning of Graph Matching
Synthesizing Images of Humans in Unseen Poses
Neural Inverse Kinematics for Unsupervised Motion Retargetting
Direction-aware Spatial Context Features for Shadow Detection
Density Adaptive Point Set Registration
Hybrid Camera Pose Estimation
Relation Networks for Object Detection
Revisiting Salient Object Detection: Simultaneous Detection, Ranking, and Subitizing of Multiple Salient Objects
Im2Pano3D: Extrapolating 360 Structure and Semantics Beyond the Field of View
Polarimetric Dense Monocular SLAM
Wasserstein Introspective Neural Networks
The Perception-Distortion Tradeoff
Discriminative Learning of Latent Features for Zero-Shot Recognition
Photometric Stereo in Participating Media Considering Shape-Dependent Forward Scatter
Fast and Furious: Real Time End-to-End 3D Detection, Tracking and Motion Forecasting with a Single Convolutional Net
Trapping Light for Time of Flight
Feature Space Transfer for Data Augmentation
Self-supervised Multi-level Face Model Learning for Monocular Reconstruction at over 250Hz
CodeSLAM — Learning a Compact, Optimisable Representation for Dense Visual SLAM
FlipDial: A Generative Model for Two-Way Visual Dialogue
OATM: Occlusion Aware Template Matching by Consensus Set Maximization
Surface Networks
VirtualHome: Simulating Household Activities via Programs
Egocentric Activity Recognition on a Budget
Improved Fusion of Visual and Language Representations by Dense Symmetric Co-Attention for Visual Question Answering
Efficient Optimization for Rank-based Loss Functions
MakeupGAN: Makeup Transfer via Cycle-Consistent Adversarial Networks
Revisiting Deep Intrinsic Image Decompositions
StarGAN: Unified Generative Adversarial Networks for Controllable Multi-Domain Image-to-Image Translation
Ordinal Depth Supervision for 3D Human Pose Estimation
Multi-Cell Classification by Convolutional Dictionary Learning with Class Proportion Priors
Accurate and Diverse Sampling of Sequences based on a ``Best of Many’’ Sample Objective
MapNet: An Allocentric Spatial Memory for Mapping Environments
A Globally Optimal Solution to the Non-Minimal Relative Pose Problem
A Volumetric Descriptive Network for 3D Object Synthesis
Learning Face Age Progression: A Pyramid Architecture of GANs

Enjoy It!