cvpaper.challenge in 2015 - A review of CVPR2015 and DeepSurvey
arXiv:1605.08247
Abstract
The "cvpaper.challenge" is a group composed of members from AIST, Tokyo Denki Univ. (TDU), and Univ. of Tsukuba that aims to systematically summarize papers on computer vision, pattern recognition, and related fields. For this particular review, we focused on reading the ALL 602 conference papers presented at the CVPR2015, the premier annual computer vision event held in June 2015, in order to grasp the trends in the field. Further, we are proposing "DeepSurvey" as a mechanism embodying the entire process from the reading through all the papers, the generation of ideas, and to the writing of paper.
arXiv commentSurvey Paper
References in corpus (20)
- Two-Stream Convolutional Networks for Action Recognition in Videos
- Improving Object Detection with Deep Convolutional Networks via Bayesian Optimization and Structured Prediction
- 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
- A Solution for Multi-Alignment by Transformation Synchronisation
- Unsupervised Object Discovery and Localization in the Wild: Part-based Matching with Bottom-up Region Proposals
- A Discriminative CNN Video Representation for Event Detection
- Watch and Learn: Semi-Supervised Learning of Object Detectors from Videos
- Background Subtraction via Generalized Fused Lasso Foreground Modeling
- Iteratively Reweighted Graph Cut for Multi-label MRFs with Non-convex Priors
- Deep Convolutional Neural Fields for Depth Estimation from a Single Image
- Supervised mid-level features for word image representation
- Oriented Edge Forests for Boundary Detection
- Learning Multiple Visual Tasks while Discovering their Structure
- Parsing Occluded People by Flexible Compositions
- Predicting the Future Behavior of a Time-Varying Probability Distribution
- Bilinear Random Projections for Locality-Sensitive Binary Codes
- Revisiting Kernelized Locality-Sensitive Hashing for Improved Large-Scale Image Retrieval
- Pooled Motion Features for First-Person Videos