Deep Learning Markov Random Field for Semantic Segmentation
Comments To appear in IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2017. Extended version of our previous ICCV 2015 paper (arXiv:1509.02634)
期刊&会议
ICCV
International Conference on Computer Vision · 会议 · Computer Vision
Training Deep Networks to be Spatially Sensitive
Comments ICCV 2017
MemNet: A Persistent Memory Network for Image Restoration
Comments Accepted by ICCV 2017 (Spotlight presentation)
Self-supervised Learning of Pose Embeddings from Spatiotemporal Relations in Videos
Comments To appear in ICCV 2017
Learning for Active 3D Mapping
Comments ICCV 2017 (oral). See video: https://www.youtube.com/watch?v=KNex0zjeGYE
Learning Uncertain Convolutional Features for Accurate Saliency Detection
Comments Accepted as a poster in ICCV 2017,including 10 pages, 7 figures and 3 tables
Amulet: Aggregating Multi-level Convolutional Features for Salient Object Detection
Comments Accepted as a poster in ICCV 2017, including 10 pages, 5 figures and 2 tables
Identity-Aware Textual-Visual Matching with Latent Co-attention
Comments Accepted to ICCV 2017
PPR-FCN: Weakly Supervised Visual Relation Detection via Parallel Pairwise R-FCN
Comments To appear in International Conference on Computer Vision (ICCV) 2017, Venice, Italy
Long Short-Term Memory Kalman Filters:Recurrent Neural Estimators for Pose Regularization
Comments Accepted ICCV 2017
Learning Discriminative Alpha-Beta-divergence for Positive Definite Matrices (Extended Version)
Comments Accepted at the International Conference on Computer Vision (ICCV)
Video Frame Interpolation via Adaptive Separable Convolution
Comments ICCV 2017, http://graphics.cs.pdx.edu/project/sepconv/
Deep Metric Learning with Angular Loss
Comments International Conference on Computer Vision 2017
Query-guided Regression Network with Context Policy for Phrase Grounding
Comments Spotlight in ICCV 2017
3D-PRNN: Generating Shape Primitives with Recurrent Neural Networks
Comments ICCV 2017
Cut, Paste and Learn: Surprisingly Easy Synthesis for Instance Detection
Comments To appear in ICCV 2017
Localizing Moments in Video with Natural Language
Comments ICCV 2017
Benchmarking and Error Diagnosis in Multi-Instance Pose Estimation
Comments Project page available at http://www.vision.caltech.edu/~mronchi/projects/PoseErrorDiagnosis/; Code available at https://github.com/matteorr/coco-analyze; published at ICCV 17
A simple yet effective baseline for 3d human pose estimation
Comments Accepted to ICCV 17
Unsupervised learning of object landmarks by factorized spatial embeddings
Comments To be published in ICCV 2017
Attributes2Classname: A discriminative model for attribute-based unsupervised zero-shot learning
Comments To appear at IEEE Int. Conference on Computer Vision (ICCV) 2017
AMTnet: Action-Micro-Tube Regression by End-to-end Trainable Deep Architecture
Comments Update to version in ICCV 2017 proceedings
DeepCoder: Semi-parametric Variational Autoencoders for Automatic Facial Action Coding
Comments ICCV 2017 - accepted
Towards a Visual Privacy Advisor: Understanding and Predicting Privacy Risks in Images
Comments ICCV 2017. Project page: https://tribhuvanesh.github.io/vpa
Click Here: Human-Localized Keypoints as Guidance for Viewpoint Estimation
Comments To appear in ICCV 2017
Weakly Supervised Object Localization Using Things and Stuff Transfer
Comments ICCV 2017 camera-ready including supplementary material
Recurrent Multimodal Interaction for Referring Image Segmentation
Comments To appear in ICCV 2017. See http://www.cs.jhu.edu/~cxliu/ for code and supplementary material
TURN TAP: Temporal Unit Regression Network for Temporal Action Proposals
Comments ICCV 2017 camera ready
SVDNet for Pedestrian Retrieval
Comments accepted as spotlight to ICCV 2017
Video Frame Synthesis using Deep Voxel Flow
Comments To appear in ICCV 2017 as an oral paper. More details at the project page: https://liuziwei7.github.io/projects/VoxelFlow.html
