Object Discovery Using CNN Features in Egocentric Videos

2015 ◽  
pp. 67-74 ◽  
Author(s):  
Marc Bolaños ◽  
Maite Garolera ◽  
Petia Radeva
Keyword(s):  
Object Discovery

scholarly journals Exploiting domain knowledge for Object Discovery

2013 ◽  
Author(s):  
Alvaro Collet ◽  
Bo Xiong ◽  
Corina Gurau ◽  
Martial Hebert ◽  
Siddhartha S. Srinivasa
Keyword(s):  
Domain Knowledge ◽  
Object Discovery

scholarly journals Unsupervised Learning from Videos for Object Discovery in Single Images

Symmetry ◽  
2020 ◽  
Vol 13 (1) ◽  
pp. 38
Author(s):  
Dong Zhao ◽  
Baoqing Ding ◽  
Yulin Wu ◽  
Lei Chen ◽  
Hongchao Zhou
Keyword(s):  
Input Image ◽  
Frame Structure ◽  
Object Discovery ◽  
Spatial Transformations ◽  
Learning Tasks ◽  
Video Frames ◽  
Segmentation Methods ◽  
Feed Forward Network ◽  
Single Input ◽  
Inter Frame

This paper proposes a method for discovering the primary objects in single images by learning from videos in a purely unsupervised manner—the learning process is based on videos, but the generated network is able to discover objects from a single input image. The rough idea is that an image typically consists of multiple object instances (like the foreground and background) that have spatial transformations across video frames and they can be sparsely represented. By exploring the sparsity representation of a video with a neural network, one may learn the features of each object instance without any labels, which can be used to discover, recognize, or distinguish object instances from a single image. In this paper, we consider a relatively simple scenario, where each image roughly consists of a foreground and a background. Our proposed method is based on encoder-decoder structures to sparsely represent the foreground, background, and segmentation mask, which further reconstruct the original images. We apply the feed-forward network trained from videos for object discovery in single images, which is different from the previous co-segmentation methods that require videos or collections of images as the input for inference. The experimental results on various object segmentation benchmarks demonstrate that the proposed method extracts primary objects accurately and robustly, which suggests that unsupervised image learning tasks can benefit from the sparsity of images and the inter-frame structure of videos.

Joint object discovery and segmentation with image-wise reconstruction error

2016 ◽  
Author(s):  
Shuhei Tarashima ◽  
Jingjing Pan ◽  
Go Irie ◽  
Takayuki Kurozumi ◽  
Tetsuya Kinebuchi
Keyword(s):  
Reconstruction Error ◽  
Object Discovery

scholarly journals Joint Video Object Discovery and Segmentation by Coupled Dynamic Markov Networks

2018 ◽  
Vol 27 (12) ◽  
pp. 5840-5853 ◽  
Author(s):  
Ziyi Liu ◽  
Le Wang ◽  
Gang Hua ◽  
Qilin Zhang ◽  
Zhenxing Niu ◽  
...  
Keyword(s):  
Video Object ◽  
Object Discovery ◽  
Markov Networks

scholarly journals Graph-based particular object discovery

2019 ◽  
Vol 30 (2) ◽  
pp. 243-254 ◽  
Author(s):  
Oriane Siméoni ◽  
Ahmet Iscen ◽  
Giorgos Tolias ◽  
Yannis Avrithis ◽  
Ondřej Chum
Keyword(s):  
Object Discovery
Sign in / Sign up

Export Citation Format

Share Document