Ontology type: schema:Chapter
2018-11-10
AUTHORSYong Wang , Robert Laganière , Daniel Laroche , Ali Osman Ors , Xiaoyin Xu , Changyun Zhu
ABSTRACTIn this paper, we exploit convolutional features extracted from multiple layers of a pre-trained deep convolutional neural network. The outputs of the multiple convolutional layers encode both low-level and high-level information about the targets. The earlier convolutional layers provide accurate positional information while the late convolutional layers are invariant to appearance changes and provide more semantic information. Specifically, each convolutional layer locates a target through correlation filter-based tracking and then traces the target backward. By analyzing the forward and backward tracking results, we evaluate the robustness of the tracker in each layer. The final position is determined by fusing the locations from each layer. A region proposal network (RPN) is employed whenever a backward tracker failure occurs. The new position will be chosen from the proposal candidates generated by the RPN. Extensive experiments have been implemented on several benchmark datasets. Our proposed tracking method achieves favorable results compared to state-of-the-art methods. More... »
PAGES320-331
Advances in Visual Computing
ISBN
978-3-030-03800-7
978-3-030-03801-4
http://scigraph.springernature.com/pub.10.1007/978-3-030-03801-4_29
DOIhttp://dx.doi.org/10.1007/978-3-030-03801-4_29
DIMENSIONShttps://app.dimensions.ai/details/publication/pub.1109840776
JSON-LD is the canonical representation for SciGraph data.
TIP: You can open this SciGraph record using an external JSON-LD service: JSON-LD Playground Google SDTT
[
{
"@context": "https://springernature.github.io/scigraph/jsonld/sgcontext.json",
"about": [
{
"id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/0801",
"inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/",
"name": "Artificial Intelligence and Image Processing",
"type": "DefinedTerm"
},
{
"id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/08",
"inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/",
"name": "Information and Computing Sciences",
"type": "DefinedTerm"
}
],
"author": [
{
"affiliation": {
"alternateName": "University of Ottawa",
"id": "https://www.grid.ac/institutes/grid.28046.38",
"name": [
"School of Electrical Engineering and Computer Science, University of Ottawa, Ottawa, Canada"
],
"type": "Organization"
},
"familyName": "Wang",
"givenName": "Yong",
"id": "sg:person.015433566274.28",
"sameAs": [
"https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.015433566274.28"
],
"type": "Person"
},
{
"affiliation": {
"alternateName": "University of Ottawa",
"id": "https://www.grid.ac/institutes/grid.28046.38",
"name": [
"School of Electrical Engineering and Computer Science, University of Ottawa, Ottawa, Canada"
],
"type": "Organization"
},
"familyName": "Lagani\u00e8re",
"givenName": "Robert",
"id": "sg:person.01144533722.06",
"sameAs": [
"https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01144533722.06"
],
"type": "Person"
},
{
"affiliation": {
"name": [
"NXP Semiconductors, Ottawa, ON, Canada"
],
"type": "Organization"
},
"familyName": "Laroche",
"givenName": "Daniel",
"id": "sg:person.012423533165.31",
"sameAs": [
"https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012423533165.31"
],
"type": "Person"
},
{
"affiliation": {
"name": [
"NXP Semiconductors, Ottawa, ON, Canada"
],
"type": "Organization"
},
"familyName": "Ors",
"givenName": "Ali Osman",
"id": "sg:person.012277754376.04",
"sameAs": [
"https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012277754376.04"
],
"type": "Person"
},
{
"affiliation": {
"name": [
"NXP Semiconductors, Ottawa, ON, Canada"
],
"type": "Organization"
},
"familyName": "Xu",
"givenName": "Xiaoyin",
"id": "sg:person.010705013376.35",
"sameAs": [
"https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010705013376.35"
],
"type": "Person"
},
{
"affiliation": {
"name": [
"NXP Semiconductors, Ottawa, ON, Canada"
],
"type": "Organization"
},
"familyName": "Zhu",
"givenName": "Changyun",
"id": "sg:person.016612504176.76",
"sameAs": [
"https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016612504176.76"
],
"type": "Person"
}
],
"citation": [
{
"id": "sg:pub.10.1007/978-3-319-10599-4_13",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1010891849",
"https://doi.org/10.1007/978-3-319-10599-4_13"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1109/tpami.2011.239",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1061744121"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1109/tpami.2014.2345390",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1061744716"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1109/tpami.2014.2388226",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1061744808"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1109/tpami.2016.2577031",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1061745117"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1109/cvpr.2016.153",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1093726236"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1109/cvpr.2010.5539960",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1093797592"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1109/iccv.2015.352",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1093854374"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1109/cvpr.2012.6247882",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1094211569"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1109/iccvw.2015.80",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1095538227"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1109/iccv.2011.6126251",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1095713809"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1109/cvpr.2016.466",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1095713935"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1109/cvpr.2017.531",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1095846173"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.5244/c.29.185",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1099427236"
],
"type": "CreativeWork"
}
],
"datePublished": "2018-11-10",
"datePublishedReg": "2018-11-10",
"description": "In this paper, we exploit convolutional features extracted from multiple layers of a pre-trained deep convolutional neural network. The outputs of the multiple convolutional layers encode both low-level and high-level information about the targets. The earlier convolutional layers provide accurate positional information while the late convolutional layers are invariant to appearance changes and provide more semantic information. Specifically, each convolutional layer locates a target through correlation filter-based tracking and then traces the target backward. By analyzing the forward and backward tracking results, we evaluate the robustness of the tracker in each layer. The final position is determined by fusing the locations from each layer. A region proposal network (RPN) is employed whenever a backward tracker failure occurs. The new position will be chosen from the proposal candidates generated by the RPN. Extensive experiments have been implemented on several benchmark datasets. Our proposed tracking method achieves favorable results compared to state-of-the-art methods.",
"editor": [
{
"familyName": "Bebis",
"givenName": "George",
"type": "Person"
},
{
"familyName": "Boyle",
"givenName": "Richard",
"type": "Person"
},
{
"familyName": "Parvin",
"givenName": "Bahram",
"type": "Person"
},
{
"familyName": "Koracin",
"givenName": "Darko",
"type": "Person"
},
{
"familyName": "Turek",
"givenName": "Matt",
"type": "Person"
},
{
"familyName": "Ramalingam",
"givenName": "Srikumar",
"type": "Person"
},
{
"familyName": "Xu",
"givenName": "Kai",
"type": "Person"
},
{
"familyName": "Lin",
"givenName": "Stephen",
"type": "Person"
},
{
"familyName": "Alsallakh",
"givenName": "Bilal",
"type": "Person"
},
{
"familyName": "Yang",
"givenName": "Jing",
"type": "Person"
},
{
"familyName": "Cuervo",
"givenName": "Eduardo",
"type": "Person"
},
{
"familyName": "Ventura",
"givenName": "Jonathan",
"type": "Person"
}
],
"genre": "chapter",
"id": "sg:pub.10.1007/978-3-030-03801-4_29",
"inLanguage": [
"en"
],
"isAccessibleForFree": false,
"isPartOf": {
"isbn": [
"978-3-030-03800-7",
"978-3-030-03801-4"
],
"name": "Advances in Visual Computing",
"type": "Book"
},
"name": "Deep Convolutional Correlation Filters for Forward-Backward Visual Tracking",
"pagination": "320-331",
"productId": [
{
"name": "doi",
"type": "PropertyValue",
"value": [
"10.1007/978-3-030-03801-4_29"
]
},
{
"name": "readcube_id",
"type": "PropertyValue",
"value": [
"1072c0009fd00197f7cf386b7b3d8c8693798fedd42610750ef4185a1b4f2ec0"
]
},
{
"name": "dimensions_id",
"type": "PropertyValue",
"value": [
"pub.1109840776"
]
}
],
"publisher": {
"location": "Cham",
"name": "Springer International Publishing",
"type": "Organisation"
},
"sameAs": [
"https://doi.org/10.1007/978-3-030-03801-4_29",
"https://app.dimensions.ai/details/publication/pub.1109840776"
],
"sdDataset": "chapters",
"sdDatePublished": "2019-04-16T04:40",
"sdLicense": "https://scigraph.springernature.com/explorer/license/",
"sdPublisher": {
"name": "Springer Nature - SN SciGraph project",
"type": "Organization"
},
"sdSource": "s3://com-uberresearch-data-dimensions-target-20181106-alternative/cleanup/v134/2549eaecd7973599484d7c17b260dba0a4ecb94b/merge/v9/a6c9fde33151104705d4d7ff012ea9563521a3ce/jats-lookup/v90/0000000322_0000000322/records_64996_00000000.jsonl",
"type": "Chapter",
"url": "https://link.springer.com/10.1007%2F978-3-030-03801-4_29"
}
]Download the RDF metadata as: json-ld nt turtle xml License info
JSON-LD is a popular format for linked data which is fully compatible with JSON.
curl -H 'Accept: application/ld+json' 'https://scigraph.springernature.com/pub.10.1007/978-3-030-03801-4_29'
N-Triples is a line-based linked data format ideal for batch operations.
curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/978-3-030-03801-4_29'
Turtle is a human-readable linked data format.
curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/978-3-030-03801-4_29'
RDF/XML is a standard XML format for linked data.
curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/978-3-030-03801-4_29'
This table displays all metadata directly associated to this object as RDF triples.
206 TRIPLES
23 PREDICATES
40 URIs
19 LITERALS
8 BLANK NODES