ECCV2018 Oral论文集

ECCV 2018 Oral Paper List

今年的ECCV将于9月8号在慕尼黑召开，本文将持续学习记录会议中的优秀文章。Oral部分的论文主要包括了学习、深度、图像、网络等主流的热门，同时也涵盖Aware、视频、移动等关键词。ECCV2018的Oral部分主要分为四天举行，共59个报告，其名称和下载链接见下文所示。

Oral

Convolutional Networks with Adaptive Computation Graphs
Progressive Neural Architecture Search
Diverse Image-to-Image Translation via Disentangled Representations
Lifting Layers: Analysis and Applications
Learning with Biased Complementary Labels
Light Structure from Pin Motion: Simple and Accurate Point Light Calibration for Physics-based Modeling
Programmable Light Curtains
Learning to Separate Object Sounds by Watching Unlabeled Video
Coded Two-Bucket Cameras for Computer Vision & authorr
Materials for Masses: SVBRDF Acquisition with a Single Mobile Phone Image
End-to-End Joint Semantic Segmentation of Actors and Actions in Video
Learning-based Video Motion Magnification
Massively Parallel Video Networks
DeepWrinkles: Accurate and Realistic Clothing Modeling
Learning Discriminative Video Representations Using Adversarial Perturbations

---

Scaling Egocentric Vision: The EPIC-KITCHENS Dataset
Unsupervised Person Re-identification by Deep Learning Tracklet Association
Predicting Gaze in Egocentric Video by Learning Task-dependent Attention Transition
Instance-level Human Parsing via Part Grouping Network
Adversarial Geometry-Aware Human Motion Prediction
Weakly-supervised 3D Hand Pose Estimation from Monocular RGB Images
Audio-Visual Scene Analysis with Self-Supervised Multisensory Features
Jointly Discovering Visual Objects and Spoken Words from Raw Sensory Input
DeepIM: Deep Iterative Matching for 6D Pose Estimation
Implicit 3D Orientation Learning for 6D Object Detection from RGB Images
Direct Sparse Odometry With Rolling Shutter
3D Motion Sensing from 4D Light Field Gradients
A Style-Aware Content Loss for Real-time HD Style Transfer
Scale-Awareness of Light Field Camera based Visual Odometry
Burst Image Deblurring Using Permutation Invariant Convolutional Neural Networks

---

MVSNet: Depth Inference for Unstructured Multi-view Stereo
PlaneMatch: Patch Coplanarity Prediction for Robust RGB-D Registration
Active Stereo Net: End-to-End Self-Supervised Learning for Active Stereo Systems, &website
GAL: Geometric Adversarial Loss for Single-View 3D-Object Reconstruction
Deep Virtual Stereo Odometry: Leveraging Deep Depth Prediction for Monocular Direct Sparse Odometry
Unsupervised Geometry-Aware Representation for 3D Human Pose Estimation
Dual-Agent Deep Reinforcement Learning for Deformable Face Tracking
Deep Autoencoder for Combined Human Pose Estimation and Body Model Upscaling
Occlusion-aware Hand Pose Estimation Using Hierarchical Mixture Density Network
GANimation: Anatomically-aware Facial Animation from a Single Image
Deterministic Consensus Maximization with Biconvex Programming
Robust fitting in computer vision: easy or hard?
Highly-Economized Multi-View Binary Compression for Scalable Image Clustering
Efficient Semantic Scene Completion Network with Spatial Group Convolution
Asynchronous, Photometric Feature Tracking using Events and Frames

---

Group Normalization
Deep Matching Autoencoder
Deep Expander Networks: Efficient Deep Networks from Graph Theory
Towards Realistic Predictors
Learning SO(3) Equivariant Representations with Spherical CNNs
CornerNet: Detecting Objects as Paired Keypoints
RelocNet: Continous Metric Learning Relocalisation using Neural Nets
The Contextual Loss for Image Transformation with Non-Aligned Data
Acquisition of Localization Confidence for Accurate Object Detection
Deep Model-Based 6D Pose Refinement in RGB
DeepTAM: Deep Tracking and Mapping
ContextVP: Fully Context-Aware Video Prediction
Saliency Benchmarking Made Easy: Separating Models, Maps and Metrics
Museum Exhibit Identification Challenge for the Supervised Domain Adaptation.
Multi-Attention Multi-Class Constraint for Fine-grained Image Recognition