About: Joint Multi-object Detection and Segmentation from an Untrimmed Video

Facets (new session)
Description
Metadata
Settings
- owl:sameAs
- Inference Rule:

About: Joint Multi-object Detection and Segmentation from an Untrimmed Video Goto Sponge NotDistinct Permalink

An Entity of Type : schema:ScholarlyArticle, within Data Space : wasabi.inria.fr associated with source document(s)

Attributes	Values
type	Academic Article research paper schema:ScholarlyArticle
isDefinedBy	Covid-on-the-Web dataset
has title	Joint Multi-object Detection and Segmentation from an Untrimmed Video
Creator	Wang, Le Zhang, Qilin Zheng, Nanning Hua, Gang Liu, Xinling
Source	PMC
abstract	In this paper, we present a novel method for jointly detecting and segmenting multiple objects from an untrimmed video. Unlike most existing video object segmentation methods that can only handle a trimmed video in which all video frames contain the target objects, we address a more practical and difficult problem, i.e., joint multi-object detection and segmentation from an untrimmed video where the target objects do not always appear per frame. In particular, our method consists of two modules, i.e., object decision module and object segmentation module. The object decision module is used to detect the objects and decide which target objects need to be separated out from video. As there are usually two or more target objects and they do not always appear in the whole video, we introduce the data association into object decision module to identify their correspondences among frames. The object segmentation module aims to separate the target objects identified by object decision module. In order to extensively evaluate the proposed method, we introduce a new dataset named UNVOSeg dataset, in which [Formula: see text] of the video frames do not contain objects. Experimental results on four datasets demonstrate that our method outperforms most of the state-of-the-art approaches.
has issue date	2020-05-06(xsd:dateTime)
bibo:doi	10.1007/978-3-030-49161-1_27
has license	no-cc
sha1sum (hex)	7f765c3f5175aab1f4860a62579cbf9276d9f00f
schema:url	https://doi.org/10.1007/978-3-030-49161-1_27
resource representing a document's title	Joint Multi-object Detection and Segmentation from an Untrimmed Video
has PubMed Central identifier	PMC7256415
schema:publication	Artificial Intelligence Applications and Innovations
resource representing a document's body	covid:7f765c3f5175aab1f4860a62579cbf9276d9f00f#body_text
is schema:about of	named entity 'module' named entity 'dataset' named entity 'extensively' named entity 'objects' named entity 'segmenting' named entity 'trimmed' named entity 'objects' named entity 'segmentation' named entity 'FRAMES' named entity 'ADDRESS' named entity 'FRAME' named entity 'VIDEO OBJECT SEGMENTATION' named entity 'objects' named entity 'identify' named entity 'introduce' named entity 'introduce' named entity 'optical flow' named entity 'object detection' named entity 'detect' named entity 'object' named entity 'objects' named entity 'detection' named entity 'Joint' named entity 'state-of-the-art' named entity 'Experimental results' named entity 'object segmentation' named entity 'Segmentation' named entity 'Untrimmed' named entity 'module' named entity 'dataset' named entity 'pooling layer' named entity 'convolutional networks' named entity 'false positive' named entity 'Markov Networks' named entity 'video gold' named entity 'object segmentation' named entity 'object segmentation' named entity 'object segmentation' named entity 'object segmentation' named entity 'spatial network' named entity 'object segmentation' named entity 'object segmentation' named entity 'MCG' named entity 'object segmentation' named entity 'object segmentation' named entity 'recurrent network' named entity 'object segmentation' named entity 'object segmentation' named entity 'Experimental results' named entity 'action recognition' named entity 'final object' named entity 'probability' named entity 'convolutional neural networks' named entity 'object segmentation' named entity 'object segmentation' named entity 'object segmentation' named entity 'object segmentation' named entity 'bounding box' named entity 'pixel' named entity 'object detection' named entity 'object segmentation' named entity 'object segmentation' named entity 'optical flow' named entity 'CDTS' named entity 'convolutional network' named entity 'object segmentation' named entity 'JOS' named entity 'object detection' named entity 'object segmentation' named entity 'bounding box' named entity 'pixel' named entity 'object detection' named entity 'JOS' named entity 'semi-supervised' named entity 'Object Detection' named entity 'object segmentation' named entity 'contour map' named entity 'object discovery' named entity 'convolutional layer'

Faceted Search & Find service v1.13.91 as of Mar 24 2020

Alternative Linked Data Documents: Sponger | ODE Content Formats:

RDF

ODATA

Microdata

About

OpenLink Virtuoso version 07.20.3229 as of Jul 10 2020, on Linux (x86_64-pc-linux-gnu), Single-Server Edition (94 GB total memory)
Data on this page belongs to its respective rights holders.
Virtuoso Faceted Browser Copyright © 2009-2025 OpenLink Software