ICCV 2017

628 papers

Top Research Directions

Research directions most represented by ICCV 2017 papers.

Preserving Tiny Features Against Spatial Resolution Degradation 14
Eliminating the Optical Flow Bottleneck in Video Understanding 9
The Perceptual Misalignment of Image Quality Metrics 9
Asymmetric Spatiotemporal Decoupling for Video Models 9
Resolving Geometric Symmetry Ambiguity in 3D Pose Estimation 8
Generalizing from Synthetic Data to the Real World 8
Overcoming Regression to the Mean in Image Synthesis 7
Exploiting Temporal Redundancy in Video Neural Networks 7
Reconstructing Complete Geometry from Partial Point Clouds 7
Synthetic Viewpoint Augmentation for Robust Visual Learning 6
Overcoming Self Occlusion in Large Pose Face Alignment 6
Spatial Temporal Reasoning Under Egocentric Camera Instability 6
3D Convolutions for Spatiotemporal Feature Learning 6
The Cross Modal Representation Gap 6
Efficient Single Stage Object Detection for Edge Hardware 5

Top Authors

AuthorPapers
Ming-Hsuan Yang10
Shuicheng YAN10
Xiaogang Wang9
Cordelia Schmid8
Jiaya Jia8
Abhinav Gupta7
Raquel Urtasun7
Sanja Fidler7
Alan Yuille6
Daniel Cremers6
Hongsheng Li6
Luc Van Gool6
Chunhua Shen5
In So Kweon5
Jiashi Feng5
Jimei Yang5
Larry S. Davis5
Li Fei-Fei5
Mubarak Shah5
Vittorio Ferrari5

Impactful Papers

Papers from ICCV 2017 that shaped research clusters.

Foundational

Influential

Papers

Title
The Mapillary Vistas Dataset for Semantic Understanding of Street Scenes
The Pose Knows: Video Forecasting by Generating Pose Futures
The "Something Something" Video Database for Learning and Evaluating Visual Common Sense
ThiNet: A Filter Level Pruning Method for Deep Neural Network Compression
TORNADO: A Spatio-Temporal Convolutional Regression Network for Video Action Proposal
TorontoCity: Seeing the World with a Million Eyes
Toward Perceptually-Consistent Stereo: A Scanline Study
Towards 3D Human Pose Estimation in the Wild: A Weakly-Supervised Approach
Towards a Unified Compositional Model for Visual Pattern Modeling
Towards a Visual Privacy Advisor: Understanding and Predicting Privacy Risks in Images
Towards Context-Aware Interaction Recognition for Visual Relationship Detection
Towards Diverse and Natural Image Descriptions via a Conditional GAN
Towards End-to-End Text Spotting with Convolutional Recurrent Neural Networks
Towards Large-Pose Face Frontalization in the Wild
Towards More Accurate Iris Recognition Using Deeply Learned Spatially Corresponding Features
Tracking as Online Decision-Making: Learning a Policy from Streaming Videos with Reinforcement Learning
Tracking the Untrackable: Learning to Track Multiple Cues with Long-Term Dependencies
Training Deep Networks to be Spatially Sensitive
Transferring Objects: Joint Inference of Container and Human Pose
Transformed Low-Rank Model for Line Pattern Noise Removal
Transitive Invariance for Self-Supervised Visual Representation Learning
Trespassing the Boundaries: Labeling Temporal Bounds for Object Interactions in Egocentric Video
Truncating Wide Networks Using Binary Tree Architectures
Tube Convolutional Neural Network (T-CNN) for Action Detection in Videos
Turning Corners into Cameras: Principles and Methods
TURN TAP: Temporal Unit Regression Network for Temporal Action Proposals
Two-Phase Learning for Weakly Supervised Object Localization
Understanding and Mapping Natural Beauty
Understanding Low- and High-Level Contributions to Fixation Prediction
Unified Deep Supervised Domain Adaptation and Generalization
Universal Adversarial Perturbations Against Semantic Image Segmentation
Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in Vitro
Unmasking the Abnormal Events in Video
Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks
Unrestricted Facial Geometry Reconstruction Using Image-to-Image Translation
Unrolled Memory Inner-Products: An Abstract GPU Operator for Efficient Vision-Related Computations
Unsupervised Action Discovery and Localization in Videos
Unsupervised Adaptation for Deep Stereo
Unsupervised Creation of Parameterized Avatars
Unsupervised Domain Adaptation for Face Recognition in Unlabeled Videos
Unsupervised Learning from Video to Detect Foreground Objects in Single Images
Unsupervised Learning of Important Objects from First-Person Videos
Unsupervised Learning of Object Landmarks by Factorized Spatial Embeddings
Unsupervised Learning of Stereo Matching
Unsupervised Object Segmentation in Video by Efficient Selection of Highly Probable Positive Features
Unsupervised Representation Learning by Sorting Sequences
Unsupervised Video Understanding by Reconciliation of Posture Similarities
Using Sparse Elimination for Solving Minimal Problems in Computer Vision
VegFru: A Domain-Specific Dataset for Fine-Grained Visual Categorization
Video Deblurring via Semantic Segmentation and Pixel-Wise Non-linear Kernel

« prev Page 12/13 next »