ConvNets and ImageNet Beyond Accuracy: Understanding Mistakes and Uncovering Biases
Comments ECCV 2018 camera-ready
期刊&会议
ECCV
European Conference on Computer Vision · 会议 · Computer Vision
Selective Zero-Shot Classification with Augmented Attributes
Comments To appear in ECCV 2018
ArticulatedFusion: Real-time Reconstruction of Motion, Geometry and Segmentation Using a Single Depth Camera
Comments European Conference on Computer Vision 2018
CTAP: Complementary Temporal Action Proposal Generation
Comments ECCV 2018 main conference paper (camera ready version). Code is available in http://www.github.com/jiyanggao/CTAP
Self-supervised Knowledge Distillation Using Singular Value Decomposition
Comments accepted to ECCV 2018
CBAM: Convolutional Block Attention Module
Comments Accepted to ECCV 2018
Unpaired Image Captioning by Language Pivoting
Comments 17 pages, 4 figures, Accepted at ECCV 2018
The Contextual Loss for Image Transformation with Non-Aligned Data
Comments ECCV Oral. Paper web page: http://cgm.technion.ac.il/Computer-Graphics-Multimedia/Software/contextual/
Effective Use of Synthetic Data for Urban Scene Semantic Segmentation
Comments Accepted in European Conference on Computer Vision (ECCV), 2018
MVSNet: Depth Inference for Unstructured Multi-view Stereo
Comments Accepted to European Conference on Computer Vision (ECCV 2018)
Revisiting RCNN: On Awakening the Classification Power of Faster RCNN
Comments ECCV 2018
Statistically Motivated Second Order Pooling
Comments Accepted to ECCV 2018. Camera ready version. 14 page, 5 figures, 3 tables
Zoom-Net: Mining Deep Feature Interactions for Visual Relationship Recognition
Comments 22 pages, 9 figures, accepted by ECCV 2018, the source code will be released on https://github.com/gjyin91/ZoomNet
Image Super-Resolution Using Very Deep Residual Channel Attention Networks
Comments To appear in ECCV 2018
SRDA: Generating Instance Segmentation Annotation Via Scanning, Reasoning And Domain Adaptation
Comments ECCV 2018
A Trilateral Weighted Sparse Coding Scheme for Real-World Image Denoising
Comments Accepted to ECCV 2018. 17 pages, not including supplemental material. Code will be published on https://github.com/csjunxu/TWSC-ECCV2018
Multiresolution Tree Networks for 3D Point Cloud Processing
Comments Accepted to ECCV 2018. 23 pages, including supplemental material
Deep Image Demosaicking using a Cascade of Convolutional Residual Denoising Networks
Comments Camera ready paper to appear in the Proceedings of ECCV 2018
MultiPoseNet: Fast Multi-Person Pose Estimation using Pose Residual Network
Comments to appear in ECCV 2018
Progressive Structure from Motion
Comments Accepted to ECCV 2018
CIRL: Controllable Imitative Reinforcement Learning for Vision-based Self-driving
Comments To appear in ECCV 2018
Fast and Accurate Point Cloud Registration using Trees of Gaussian Mixtures
Comments ECCV 2018
ShapeStacks: Learning Vision-Based Physical Intuition for Generalised Object Stacking
Comments revised version to appear at ECCV 2018
Localization Recall Precision (LRP): A New Performance Metric for Object Detection
Comments to appear in ECCV 2018
Using LIP to Gloss Over Faces in Single-Stage Face Detection Networks
Comments to appear ECCV 2018 (accepted version)
3D Face Reconstruction from Light Field Images: A Model-free Approach
Journal ref European Conference on Computer Vision (ECCV), 2018
Learning 3D Human Pose from Structure and Motion
Comments ECCV 2018. Project page: https://www.cse.iitb.ac.in/~rdabral/3DPose/
Polysemous codes
Comments The final (author) version of our ECCV'16 paper
ARiA: Utilizing Richard's Curve for Controlling the Non-monotonicity of the Activation Function in Deep Neural Nets
Comments Modified version Submitted to ECCV '18
ECO: Efficient Convolutional Network for Online Video Understanding
Comments Submitted to ECCV 2018. 17 pages, 7 figures, Supplementary Material, https://github.com/mzolfaghari/ECO-efficient-video-understanding
