Collaborative Descriptors: Convolutional Maps for Preprocessing

2017-05-10 · Hirokatsu Kataoka, Kaori Abe, Akio Nakamura, Yutaka Satoh

The paper presents a novel concept for collaborative descriptors between deeply learned and hand-crafted features. To achieve this concept, we apply convolutional maps for pre-processing, namely the convovlutional maps are used as input of hand-crafted features. We recorded an increase in the performance rate of +17.06 % (multi-class object recognition) and +24.71 % (car detection) from grayscale input to convolutional maps. Although the framework is straight-forward, the concept should be inherited for an improved representation.

📄 PDF Abstract BibTeX arXiv:1705.03595

Code (0)

등록된 구현이 없습니다.

Tasks

Object Recognition

Image Patch Matching Using Convolutional Descriptors with Euclidean Distance

2017-10-31 · Iaroslav Melekhov, Juho Kannala, Esa Rahtu

In this work we propose a neural network based image descriptor suitable for image patch matching, which is an important task in many computer vision applications. Our approach is influenced by recent success of deep con…

object-detection Object Detection Patch Matching

End-to-End Learning Local Multi-view Descriptors for 3D Point Clouds

2020-03-12 · CVPR 2020 6 · Lei Li, Siyu Zhu, Hongbo Fu, Ping Tan 외

In this work, we propose an end-to-end framework to learn local multi-view descriptors for 3D point clouds. To adopt a similar multi-view representation, existing studies use hand-crafted viewpoints for rendering in a pr…

Point Cloud Registration

Learning a Local Feature Descriptor for 3D LiDAR Scans

2018-09-20 · Ayush Dewan, Tim Caselitz, Wolfram Burgard

Robust data association is necessary for virtually every SLAM system and finding corresponding points is typically a preprocessing step for scan alignment algorithms. Traditionally, handcrafted feature descriptors were u…

Metric Learning

Learning 3D Shapes as Multi-Layered Height-maps using 2D Convolutional Networks

2018-07-23 · ECCV 2018 9 · Kripasindhu Sarkar, Basavaraj Hampiholi, Kiran varanasi, Didier Stricker

We present a novel global representation of 3D shapes, suitable for the application of 2D CNNs. We represent 3D shapes as multi-layered height-maps (MLH) where at each grid location, we store multiple instances of height…

3D Object Classification General Classification

Action Recognition with Trajectory-Pooled Deep-Convolutional Descriptors

2015-05-19 · CVPR 2015 6 · Limin Wang, Yu Qiao, Xiaoou Tang

Visual features are of vital importance for human action understanding in videos. This paper presents a new video representation, called trajectory-pooled deep-convolutional descriptor (TDD), which shares the merits of b…

Action Recognition Action Understanding Activity Recognition In Videos Temporal Action Localization