cvpaper.challenge in 2016: Futuristic Computer Vision through 1,600 Papers Survey
arXiv:1707.06436
Abstract
The paper gives futuristic challenges disscussed in the cvpaper.challenge. In 2015 and 2016, we thoroughly study 1,600+ papers in several conferences/journals such as CVPR/ICCV/ECCV/NIPS/PAMI/IJCV.
References in corpus (48)
- Two-Stream Convolutional Networks for Action Recognition in Videos
- UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild
- DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
- Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1
- Generating Videos with Scene Dynamics
- Residual Networks Behave Like Ensembles of Relatively Shallow Networks
- Aggregated Residual Transformations for Deep Neural Networks
- Convolutional Two-Stream Network Fusion for Video Action Recognition
- Xception: Deep Learning with Depthwise Separable Convolutions
- Simple Baseline for Visual Question Answering
- Multi-view Convolutional Neural Networks for 3D Shape Recognition
- SoundNet: Learning Sound Representations from Unlabeled Video
- Improving Object Detection with Deep Convolutional Networks via Bayesian Optimization and Structured Prediction
- Basin entropy: a new tool to analyze uncertainty in dynamical systems
- Ask Your Neurons: A Neural-based Approach to Answering Questions about Images
- A Compositional Object-Based Approach to Learning Physical Dynamics
- Learning a Convolutional Neural Network for Non-uniform Motion Blur Removal
- Understanding Image Virality
- Combining Local Appearance and Holistic View: Dual-Source Deep Neural Networks for Human Pose Estimation
- From Captions to Visual Concepts and Back
- A Solution for Multi-Alignment by Transformation Synchronisation
- Deep Learning the City : Quantifying Urban Perception At A Global Scale
- On learning optimized reaction diffusion processes for effective image restoration
- Deep Video Deblurring
- Unsupervised Object Discovery and Localization in the Wild: Part-based Matching with Bottom-up Region Proposals
- Objects2action: Classifying and localizing actions without any video example
- Understanding deep features with computer-generated imagery
- A Discriminative CNN Video Representation for Event Detection
- Going Deeper into First-Person Activity Recognition
- Don't Just Listen, Use Your Imagination: Leveraging Visual Common Sense for Non-Visual Tasks
- InstanceCut: from Edges to Instances with MultiCut
- Localizing and Orienting Street Views Using Overhead Imagery
- Iteratively Reweighted Graph Cut for Multi-label MRFs with Non-convex Priors
- Dense Optical Flow Prediction from a Static Image
- Background Subtraction via Generalized Fused Lasso Foreground Modeling
- Eve: A Gradient Based Optimization Method with Locally and Globally Adaptive Learning Rates
- Deep Convolutional Neural Fields for Depth Estimation from a Single Image
- Grid Loss: Detecting Occluded Faces
- Supervised mid-level features for word image representation
- Oriented Edge Forests for Boundary Detection
- Contextual Visual Similarity
- Learning Multiple Visual Tasks while Discovering their Structure
- Parsing Occluded People by Flexible Compositions
- Predicting the Future Behavior of a Time-Varying Probability Distribution
- Revisiting Kernelized Locality-Sensitive Hashing for Improved Large-Scale Image Retrieval
- Bilinear Random Projections for Locality-Sensitive Binary Codes
- Learning Action Maps of Large Environments via First-Person Vision
- A Multi-Plane Block-Coordinate Frank-Wolfe Algorithm for Training Structural SVMs with a Costly max-Oracle