The changing fortunes of pattern recognition and computer vision
As someone who had been attending conferences on pattern recognition and computer vision since 1978, I have watched with interest the ups and downs of pattern recognition and computer vision areas and how they have been presented at various conferences such as PRIP, CVPR, ECCV, ICCV, ACCV, ICPR, IJC...
Ausführliche Beschreibung
Gespeichert in:
| Autor*in: |
Chellappa, Rama [verfasserIn] |
|---|
| Format: |
E-Artikel |
|---|---|
| Sprache: |
Englisch |
| Erschienen: |
2016transfer abstract |
|---|
| Umfang: |
3 |
|---|
| Übergeordnetes Werk: |
Enthalten in: Triatoma infestans , to be or not to be autogenic? - Lamattina, D ELSEVIER, 2022, Amsterdam [u.a.] |
|---|---|
| Übergeordnetes Werk: |
volume:55 ; year:2016 ; pages:3-5 ; extent:3 |
| Links: |
|---|
| DOI / URN: |
10.1016/j.imavis.2016.04.005 |
|---|
| Katalog-ID: |
ELV024340367 |
|---|
| LEADER | 01000caa a22002652 4500 | ||
|---|---|---|---|
| 001 | ELV024340367 | ||
| 003 | DE-627 | ||
| 005 | 20230625142653.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 180603s2016 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1016/j.imavis.2016.04.005 |2 doi | |
| 028 | 5 | 2 | |a GBV00000000000049A.pica |
| 035 | |a (DE-627)ELV024340367 | ||
| 035 | |a (ELSEVIER)S0262-8856(16)30066-X | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 082 | 0 | |a 004 | |
| 082 | 0 | 4 | |a 004 |q DE-600 |
| 100 | 1 | |a Chellappa, Rama |e verfasserin |4 aut | |
| 245 | 1 | 4 | |a The changing fortunes of pattern recognition and computer vision |
| 264 | 1 | |c 2016transfer abstract | |
| 300 | |a 3 | ||
| 336 | |a nicht spezifiziert |b zzz |2 rdacontent | ||
| 337 | |a nicht spezifiziert |b z |2 rdamedia | ||
| 338 | |a nicht spezifiziert |b zu |2 rdacarrier | ||
| 520 | |a As someone who had been attending conferences on pattern recognition and computer vision since 1978, I have watched with interest the ups and downs of pattern recognition and computer vision areas and how they have been presented at various conferences such as PRIP, CVPR, ECCV, ICCV, ACCV, ICPR, IJCAI, AAAI, NIPS, ICASSP and ICIP. Given the recent successes of deep learning networks, it appears that the scale is tilting towards pattern recognition as is commonly understood. A good number of papers in recent vision conferences seem to push data through one or other deep learning networks and report improvements over state of the art. While one cannot argue against the remarkable (magical?) performance improvements obtained by deep learning network-based approaches, I worry that five years from now, most students in computer vision will only be aware of software that implements some deep learning network. After all, 2-D based detection and recognition problems for which the deep learning networks have shown their mettle are only a subset of the computer vision field. While enjoying the ride, I would like to caution that understanding of scene and image formation, invariants, interaction between light and matter, human vision, 3D recovery, and emerging concepts like common sense reasoning are too important to ignore for the long-term viability of the computer vision field. It will be a dream come true if we manage to integrate these computer vision concepts into deep learning networks so that more robust performance can be obtained with less data and cheaper computers. | ||
| 520 | |a As someone who had been attending conferences on pattern recognition and computer vision since 1978, I have watched with interest the ups and downs of pattern recognition and computer vision areas and how they have been presented at various conferences such as PRIP, CVPR, ECCV, ICCV, ACCV, ICPR, IJCAI, AAAI, NIPS, ICASSP and ICIP. Given the recent successes of deep learning networks, it appears that the scale is tilting towards pattern recognition as is commonly understood. A good number of papers in recent vision conferences seem to push data through one or other deep learning networks and report improvements over state of the art. While one cannot argue against the remarkable (magical?) performance improvements obtained by deep learning network-based approaches, I worry that five years from now, most students in computer vision will only be aware of software that implements some deep learning network. After all, 2-D based detection and recognition problems for which the deep learning networks have shown their mettle are only a subset of the computer vision field. While enjoying the ride, I would like to caution that understanding of scene and image formation, invariants, interaction between light and matter, human vision, 3D recovery, and emerging concepts like common sense reasoning are too important to ignore for the long-term viability of the computer vision field. It will be a dream come true if we manage to integrate these computer vision concepts into deep learning networks so that more robust performance can be obtained with less data and cheaper computers. | ||
| 773 | 0 | 8 | |i Enthalten in |n Elsevier Science |a Lamattina, D ELSEVIER |t Triatoma infestans , to be or not to be autogenic? |d 2022 |g Amsterdam [u.a.] |w (DE-627)ELV00877899X |
| 773 | 1 | 8 | |g volume:55 |g year:2016 |g pages:3-5 |g extent:3 |
| 856 | 4 | 0 | |u https://doi.org/10.1016/j.imavis.2016.04.005 |3 Volltext |
| 912 | |a GBV_USEFLAG_U | ||
| 912 | |a GBV_ELV | ||
| 912 | |a SYSFLAG_U | ||
| 951 | |a AR | ||
| 952 | |d 55 |j 2016 |h 3-5 |g 3 | ||
| 953 | |2 045F |a 004 | ||
| author_variant |
r c rc |
|---|---|
| matchkey_str |
chellapparama:2016----:hcagnfrueopteneontoad |
| hierarchy_sort_str |
2016transfer abstract |
| publishDate |
2016 |
| allfields |
10.1016/j.imavis.2016.04.005 doi GBV00000000000049A.pica (DE-627)ELV024340367 (ELSEVIER)S0262-8856(16)30066-X DE-627 ger DE-627 rakwb eng 004 004 DE-600 Chellappa, Rama verfasserin aut The changing fortunes of pattern recognition and computer vision 2016transfer abstract 3 nicht spezifiziert zzz rdacontent nicht spezifiziert z rdamedia nicht spezifiziert zu rdacarrier As someone who had been attending conferences on pattern recognition and computer vision since 1978, I have watched with interest the ups and downs of pattern recognition and computer vision areas and how they have been presented at various conferences such as PRIP, CVPR, ECCV, ICCV, ACCV, ICPR, IJCAI, AAAI, NIPS, ICASSP and ICIP. Given the recent successes of deep learning networks, it appears that the scale is tilting towards pattern recognition as is commonly understood. A good number of papers in recent vision conferences seem to push data through one or other deep learning networks and report improvements over state of the art. While one cannot argue against the remarkable (magical?) performance improvements obtained by deep learning network-based approaches, I worry that five years from now, most students in computer vision will only be aware of software that implements some deep learning network. After all, 2-D based detection and recognition problems for which the deep learning networks have shown their mettle are only a subset of the computer vision field. While enjoying the ride, I would like to caution that understanding of scene and image formation, invariants, interaction between light and matter, human vision, 3D recovery, and emerging concepts like common sense reasoning are too important to ignore for the long-term viability of the computer vision field. It will be a dream come true if we manage to integrate these computer vision concepts into deep learning networks so that more robust performance can be obtained with less data and cheaper computers. As someone who had been attending conferences on pattern recognition and computer vision since 1978, I have watched with interest the ups and downs of pattern recognition and computer vision areas and how they have been presented at various conferences such as PRIP, CVPR, ECCV, ICCV, ACCV, ICPR, IJCAI, AAAI, NIPS, ICASSP and ICIP. Given the recent successes of deep learning networks, it appears that the scale is tilting towards pattern recognition as is commonly understood. A good number of papers in recent vision conferences seem to push data through one or other deep learning networks and report improvements over state of the art. While one cannot argue against the remarkable (magical?) performance improvements obtained by deep learning network-based approaches, I worry that five years from now, most students in computer vision will only be aware of software that implements some deep learning network. After all, 2-D based detection and recognition problems for which the deep learning networks have shown their mettle are only a subset of the computer vision field. While enjoying the ride, I would like to caution that understanding of scene and image formation, invariants, interaction between light and matter, human vision, 3D recovery, and emerging concepts like common sense reasoning are too important to ignore for the long-term viability of the computer vision field. It will be a dream come true if we manage to integrate these computer vision concepts into deep learning networks so that more robust performance can be obtained with less data and cheaper computers. Enthalten in Elsevier Science Lamattina, D ELSEVIER Triatoma infestans , to be or not to be autogenic? 2022 Amsterdam [u.a.] (DE-627)ELV00877899X volume:55 year:2016 pages:3-5 extent:3 https://doi.org/10.1016/j.imavis.2016.04.005 Volltext GBV_USEFLAG_U GBV_ELV SYSFLAG_U AR 55 2016 3-5 3 045F 004 |
| spelling |
10.1016/j.imavis.2016.04.005 doi GBV00000000000049A.pica (DE-627)ELV024340367 (ELSEVIER)S0262-8856(16)30066-X DE-627 ger DE-627 rakwb eng 004 004 DE-600 Chellappa, Rama verfasserin aut The changing fortunes of pattern recognition and computer vision 2016transfer abstract 3 nicht spezifiziert zzz rdacontent nicht spezifiziert z rdamedia nicht spezifiziert zu rdacarrier As someone who had been attending conferences on pattern recognition and computer vision since 1978, I have watched with interest the ups and downs of pattern recognition and computer vision areas and how they have been presented at various conferences such as PRIP, CVPR, ECCV, ICCV, ACCV, ICPR, IJCAI, AAAI, NIPS, ICASSP and ICIP. Given the recent successes of deep learning networks, it appears that the scale is tilting towards pattern recognition as is commonly understood. A good number of papers in recent vision conferences seem to push data through one or other deep learning networks and report improvements over state of the art. While one cannot argue against the remarkable (magical?) performance improvements obtained by deep learning network-based approaches, I worry that five years from now, most students in computer vision will only be aware of software that implements some deep learning network. After all, 2-D based detection and recognition problems for which the deep learning networks have shown their mettle are only a subset of the computer vision field. While enjoying the ride, I would like to caution that understanding of scene and image formation, invariants, interaction between light and matter, human vision, 3D recovery, and emerging concepts like common sense reasoning are too important to ignore for the long-term viability of the computer vision field. It will be a dream come true if we manage to integrate these computer vision concepts into deep learning networks so that more robust performance can be obtained with less data and cheaper computers. As someone who had been attending conferences on pattern recognition and computer vision since 1978, I have watched with interest the ups and downs of pattern recognition and computer vision areas and how they have been presented at various conferences such as PRIP, CVPR, ECCV, ICCV, ACCV, ICPR, IJCAI, AAAI, NIPS, ICASSP and ICIP. Given the recent successes of deep learning networks, it appears that the scale is tilting towards pattern recognition as is commonly understood. A good number of papers in recent vision conferences seem to push data through one or other deep learning networks and report improvements over state of the art. While one cannot argue against the remarkable (magical?) performance improvements obtained by deep learning network-based approaches, I worry that five years from now, most students in computer vision will only be aware of software that implements some deep learning network. After all, 2-D based detection and recognition problems for which the deep learning networks have shown their mettle are only a subset of the computer vision field. While enjoying the ride, I would like to caution that understanding of scene and image formation, invariants, interaction between light and matter, human vision, 3D recovery, and emerging concepts like common sense reasoning are too important to ignore for the long-term viability of the computer vision field. It will be a dream come true if we manage to integrate these computer vision concepts into deep learning networks so that more robust performance can be obtained with less data and cheaper computers. Enthalten in Elsevier Science Lamattina, D ELSEVIER Triatoma infestans , to be or not to be autogenic? 2022 Amsterdam [u.a.] (DE-627)ELV00877899X volume:55 year:2016 pages:3-5 extent:3 https://doi.org/10.1016/j.imavis.2016.04.005 Volltext GBV_USEFLAG_U GBV_ELV SYSFLAG_U AR 55 2016 3-5 3 045F 004 |
| allfields_unstemmed |
10.1016/j.imavis.2016.04.005 doi GBV00000000000049A.pica (DE-627)ELV024340367 (ELSEVIER)S0262-8856(16)30066-X DE-627 ger DE-627 rakwb eng 004 004 DE-600 Chellappa, Rama verfasserin aut The changing fortunes of pattern recognition and computer vision 2016transfer abstract 3 nicht spezifiziert zzz rdacontent nicht spezifiziert z rdamedia nicht spezifiziert zu rdacarrier As someone who had been attending conferences on pattern recognition and computer vision since 1978, I have watched with interest the ups and downs of pattern recognition and computer vision areas and how they have been presented at various conferences such as PRIP, CVPR, ECCV, ICCV, ACCV, ICPR, IJCAI, AAAI, NIPS, ICASSP and ICIP. Given the recent successes of deep learning networks, it appears that the scale is tilting towards pattern recognition as is commonly understood. A good number of papers in recent vision conferences seem to push data through one or other deep learning networks and report improvements over state of the art. While one cannot argue against the remarkable (magical?) performance improvements obtained by deep learning network-based approaches, I worry that five years from now, most students in computer vision will only be aware of software that implements some deep learning network. After all, 2-D based detection and recognition problems for which the deep learning networks have shown their mettle are only a subset of the computer vision field. While enjoying the ride, I would like to caution that understanding of scene and image formation, invariants, interaction between light and matter, human vision, 3D recovery, and emerging concepts like common sense reasoning are too important to ignore for the long-term viability of the computer vision field. It will be a dream come true if we manage to integrate these computer vision concepts into deep learning networks so that more robust performance can be obtained with less data and cheaper computers. As someone who had been attending conferences on pattern recognition and computer vision since 1978, I have watched with interest the ups and downs of pattern recognition and computer vision areas and how they have been presented at various conferences such as PRIP, CVPR, ECCV, ICCV, ACCV, ICPR, IJCAI, AAAI, NIPS, ICASSP and ICIP. Given the recent successes of deep learning networks, it appears that the scale is tilting towards pattern recognition as is commonly understood. A good number of papers in recent vision conferences seem to push data through one or other deep learning networks and report improvements over state of the art. While one cannot argue against the remarkable (magical?) performance improvements obtained by deep learning network-based approaches, I worry that five years from now, most students in computer vision will only be aware of software that implements some deep learning network. After all, 2-D based detection and recognition problems for which the deep learning networks have shown their mettle are only a subset of the computer vision field. While enjoying the ride, I would like to caution that understanding of scene and image formation, invariants, interaction between light and matter, human vision, 3D recovery, and emerging concepts like common sense reasoning are too important to ignore for the long-term viability of the computer vision field. It will be a dream come true if we manage to integrate these computer vision concepts into deep learning networks so that more robust performance can be obtained with less data and cheaper computers. Enthalten in Elsevier Science Lamattina, D ELSEVIER Triatoma infestans , to be or not to be autogenic? 2022 Amsterdam [u.a.] (DE-627)ELV00877899X volume:55 year:2016 pages:3-5 extent:3 https://doi.org/10.1016/j.imavis.2016.04.005 Volltext GBV_USEFLAG_U GBV_ELV SYSFLAG_U AR 55 2016 3-5 3 045F 004 |
| allfieldsGer |
10.1016/j.imavis.2016.04.005 doi GBV00000000000049A.pica (DE-627)ELV024340367 (ELSEVIER)S0262-8856(16)30066-X DE-627 ger DE-627 rakwb eng 004 004 DE-600 Chellappa, Rama verfasserin aut The changing fortunes of pattern recognition and computer vision 2016transfer abstract 3 nicht spezifiziert zzz rdacontent nicht spezifiziert z rdamedia nicht spezifiziert zu rdacarrier As someone who had been attending conferences on pattern recognition and computer vision since 1978, I have watched with interest the ups and downs of pattern recognition and computer vision areas and how they have been presented at various conferences such as PRIP, CVPR, ECCV, ICCV, ACCV, ICPR, IJCAI, AAAI, NIPS, ICASSP and ICIP. Given the recent successes of deep learning networks, it appears that the scale is tilting towards pattern recognition as is commonly understood. A good number of papers in recent vision conferences seem to push data through one or other deep learning networks and report improvements over state of the art. While one cannot argue against the remarkable (magical?) performance improvements obtained by deep learning network-based approaches, I worry that five years from now, most students in computer vision will only be aware of software that implements some deep learning network. After all, 2-D based detection and recognition problems for which the deep learning networks have shown their mettle are only a subset of the computer vision field. While enjoying the ride, I would like to caution that understanding of scene and image formation, invariants, interaction between light and matter, human vision, 3D recovery, and emerging concepts like common sense reasoning are too important to ignore for the long-term viability of the computer vision field. It will be a dream come true if we manage to integrate these computer vision concepts into deep learning networks so that more robust performance can be obtained with less data and cheaper computers. As someone who had been attending conferences on pattern recognition and computer vision since 1978, I have watched with interest the ups and downs of pattern recognition and computer vision areas and how they have been presented at various conferences such as PRIP, CVPR, ECCV, ICCV, ACCV, ICPR, IJCAI, AAAI, NIPS, ICASSP and ICIP. Given the recent successes of deep learning networks, it appears that the scale is tilting towards pattern recognition as is commonly understood. A good number of papers in recent vision conferences seem to push data through one or other deep learning networks and report improvements over state of the art. While one cannot argue against the remarkable (magical?) performance improvements obtained by deep learning network-based approaches, I worry that five years from now, most students in computer vision will only be aware of software that implements some deep learning network. After all, 2-D based detection and recognition problems for which the deep learning networks have shown their mettle are only a subset of the computer vision field. While enjoying the ride, I would like to caution that understanding of scene and image formation, invariants, interaction between light and matter, human vision, 3D recovery, and emerging concepts like common sense reasoning are too important to ignore for the long-term viability of the computer vision field. It will be a dream come true if we manage to integrate these computer vision concepts into deep learning networks so that more robust performance can be obtained with less data and cheaper computers. Enthalten in Elsevier Science Lamattina, D ELSEVIER Triatoma infestans , to be or not to be autogenic? 2022 Amsterdam [u.a.] (DE-627)ELV00877899X volume:55 year:2016 pages:3-5 extent:3 https://doi.org/10.1016/j.imavis.2016.04.005 Volltext GBV_USEFLAG_U GBV_ELV SYSFLAG_U AR 55 2016 3-5 3 045F 004 |
| allfieldsSound |
10.1016/j.imavis.2016.04.005 doi GBV00000000000049A.pica (DE-627)ELV024340367 (ELSEVIER)S0262-8856(16)30066-X DE-627 ger DE-627 rakwb eng 004 004 DE-600 Chellappa, Rama verfasserin aut The changing fortunes of pattern recognition and computer vision 2016transfer abstract 3 nicht spezifiziert zzz rdacontent nicht spezifiziert z rdamedia nicht spezifiziert zu rdacarrier As someone who had been attending conferences on pattern recognition and computer vision since 1978, I have watched with interest the ups and downs of pattern recognition and computer vision areas and how they have been presented at various conferences such as PRIP, CVPR, ECCV, ICCV, ACCV, ICPR, IJCAI, AAAI, NIPS, ICASSP and ICIP. Given the recent successes of deep learning networks, it appears that the scale is tilting towards pattern recognition as is commonly understood. A good number of papers in recent vision conferences seem to push data through one or other deep learning networks and report improvements over state of the art. While one cannot argue against the remarkable (magical?) performance improvements obtained by deep learning network-based approaches, I worry that five years from now, most students in computer vision will only be aware of software that implements some deep learning network. After all, 2-D based detection and recognition problems for which the deep learning networks have shown their mettle are only a subset of the computer vision field. While enjoying the ride, I would like to caution that understanding of scene and image formation, invariants, interaction between light and matter, human vision, 3D recovery, and emerging concepts like common sense reasoning are too important to ignore for the long-term viability of the computer vision field. It will be a dream come true if we manage to integrate these computer vision concepts into deep learning networks so that more robust performance can be obtained with less data and cheaper computers. As someone who had been attending conferences on pattern recognition and computer vision since 1978, I have watched with interest the ups and downs of pattern recognition and computer vision areas and how they have been presented at various conferences such as PRIP, CVPR, ECCV, ICCV, ACCV, ICPR, IJCAI, AAAI, NIPS, ICASSP and ICIP. Given the recent successes of deep learning networks, it appears that the scale is tilting towards pattern recognition as is commonly understood. A good number of papers in recent vision conferences seem to push data through one or other deep learning networks and report improvements over state of the art. While one cannot argue against the remarkable (magical?) performance improvements obtained by deep learning network-based approaches, I worry that five years from now, most students in computer vision will only be aware of software that implements some deep learning network. After all, 2-D based detection and recognition problems for which the deep learning networks have shown their mettle are only a subset of the computer vision field. While enjoying the ride, I would like to caution that understanding of scene and image formation, invariants, interaction between light and matter, human vision, 3D recovery, and emerging concepts like common sense reasoning are too important to ignore for the long-term viability of the computer vision field. It will be a dream come true if we manage to integrate these computer vision concepts into deep learning networks so that more robust performance can be obtained with less data and cheaper computers. Enthalten in Elsevier Science Lamattina, D ELSEVIER Triatoma infestans , to be or not to be autogenic? 2022 Amsterdam [u.a.] (DE-627)ELV00877899X volume:55 year:2016 pages:3-5 extent:3 https://doi.org/10.1016/j.imavis.2016.04.005 Volltext GBV_USEFLAG_U GBV_ELV SYSFLAG_U AR 55 2016 3-5 3 045F 004 |
| language |
English |
| source |
Enthalten in Triatoma infestans , to be or not to be autogenic? Amsterdam [u.a.] volume:55 year:2016 pages:3-5 extent:3 |
| sourceStr |
Enthalten in Triatoma infestans , to be or not to be autogenic? Amsterdam [u.a.] volume:55 year:2016 pages:3-5 extent:3 |
| format_phy_str_mv |
Article |
| institution |
findex.gbv.de |
| dewey-raw |
004 |
| isfreeaccess_bool |
false |
| container_title |
Triatoma infestans , to be or not to be autogenic? |
| authorswithroles_txt_mv |
Chellappa, Rama @@aut@@ |
| publishDateDaySort_date |
2016-01-01T00:00:00Z |
| hierarchy_top_id |
ELV00877899X |
| dewey-sort |
14 |
| id |
ELV024340367 |
| language_de |
englisch |
| fullrecord |
<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000caa a22002652 4500</leader><controlfield tag="001">ELV024340367</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230625142653.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">180603s2016 xx |||||o 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1016/j.imavis.2016.04.005</subfield><subfield code="2">doi</subfield></datafield><datafield tag="028" ind1="5" ind2="2"><subfield code="a">GBV00000000000049A.pica</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)ELV024340367</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(ELSEVIER)S0262-8856(16)30066-X</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-627</subfield><subfield code="b">ger</subfield><subfield code="c">DE-627</subfield><subfield code="e">rakwb</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="082" ind1="0" ind2=" "><subfield code="a">004</subfield></datafield><datafield tag="082" ind1="0" ind2="4"><subfield code="a">004</subfield><subfield code="q">DE-600</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Chellappa, Rama</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="4"><subfield code="a">The changing fortunes of pattern recognition and computer vision</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2016transfer abstract</subfield></datafield><datafield tag="300" ind1=" " ind2=" "><subfield code="a">3</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">zzz</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">z</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">zu</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">As someone who had been attending conferences on pattern recognition and computer vision since 1978, I have watched with interest the ups and downs of pattern recognition and computer vision areas and how they have been presented at various conferences such as PRIP, CVPR, ECCV, ICCV, ACCV, ICPR, IJCAI, AAAI, NIPS, ICASSP and ICIP. Given the recent successes of deep learning networks, it appears that the scale is tilting towards pattern recognition as is commonly understood. A good number of papers in recent vision conferences seem to push data through one or other deep learning networks and report improvements over state of the art. While one cannot argue against the remarkable (magical?) performance improvements obtained by deep learning network-based approaches, I worry that five years from now, most students in computer vision will only be aware of software that implements some deep learning network. After all, 2-D based detection and recognition problems for which the deep learning networks have shown their mettle are only a subset of the computer vision field. While enjoying the ride, I would like to caution that understanding of scene and image formation, invariants, interaction between light and matter, human vision, 3D recovery, and emerging concepts like common sense reasoning are too important to ignore for the long-term viability of the computer vision field. It will be a dream come true if we manage to integrate these computer vision concepts into deep learning networks so that more robust performance can be obtained with less data and cheaper computers.</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">As someone who had been attending conferences on pattern recognition and computer vision since 1978, I have watched with interest the ups and downs of pattern recognition and computer vision areas and how they have been presented at various conferences such as PRIP, CVPR, ECCV, ICCV, ACCV, ICPR, IJCAI, AAAI, NIPS, ICASSP and ICIP. Given the recent successes of deep learning networks, it appears that the scale is tilting towards pattern recognition as is commonly understood. A good number of papers in recent vision conferences seem to push data through one or other deep learning networks and report improvements over state of the art. While one cannot argue against the remarkable (magical?) performance improvements obtained by deep learning network-based approaches, I worry that five years from now, most students in computer vision will only be aware of software that implements some deep learning network. After all, 2-D based detection and recognition problems for which the deep learning networks have shown their mettle are only a subset of the computer vision field. While enjoying the ride, I would like to caution that understanding of scene and image formation, invariants, interaction between light and matter, human vision, 3D recovery, and emerging concepts like common sense reasoning are too important to ignore for the long-term viability of the computer vision field. It will be a dream come true if we manage to integrate these computer vision concepts into deep learning networks so that more robust performance can be obtained with less data and cheaper computers.</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="n">Elsevier Science</subfield><subfield code="a">Lamattina, D ELSEVIER</subfield><subfield code="t">Triatoma infestans , to be or not to be autogenic?</subfield><subfield code="d">2022</subfield><subfield code="g">Amsterdam [u.a.]</subfield><subfield code="w">(DE-627)ELV00877899X</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:55</subfield><subfield code="g">year:2016</subfield><subfield code="g">pages:3-5</subfield><subfield code="g">extent:3</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doi.org/10.1016/j.imavis.2016.04.005</subfield><subfield code="3">Volltext</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_U</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ELV</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_U</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">55</subfield><subfield code="j">2016</subfield><subfield code="h">3-5</subfield><subfield code="g">3</subfield></datafield><datafield tag="953" ind1=" " ind2=" "><subfield code="2">045F</subfield><subfield code="a">004</subfield></datafield></record></collection>
|
| author |
Chellappa, Rama |
| spellingShingle |
Chellappa, Rama ddc 004 The changing fortunes of pattern recognition and computer vision |
| authorStr |
Chellappa, Rama |
| ppnlink_with_tag_str_mv |
@@773@@(DE-627)ELV00877899X |
| format |
electronic Article |
| dewey-ones |
004 - Data processing & computer science |
| delete_txt_mv |
keep |
| author_role |
aut |
| collection |
elsevier |
| remote_str |
true |
| illustrated |
Not Illustrated |
| topic_title |
004 004 DE-600 The changing fortunes of pattern recognition and computer vision |
| topic |
ddc 004 |
| topic_unstemmed |
ddc 004 |
| topic_browse |
ddc 004 |
| format_facet |
Elektronische Aufsätze Aufsätze Elektronische Ressource |
| format_main_str_mv |
Text Zeitschrift/Artikel |
| carriertype_str_mv |
zu |
| hierarchy_parent_title |
Triatoma infestans , to be or not to be autogenic? |
| hierarchy_parent_id |
ELV00877899X |
| dewey-tens |
000 - Computer science, knowledge & systems |
| hierarchy_top_title |
Triatoma infestans , to be or not to be autogenic? |
| isfreeaccess_txt |
false |
| familylinks_str_mv |
(DE-627)ELV00877899X |
| title |
The changing fortunes of pattern recognition and computer vision |
| ctrlnum |
(DE-627)ELV024340367 (ELSEVIER)S0262-8856(16)30066-X |
| title_full |
The changing fortunes of pattern recognition and computer vision |
| author_sort |
Chellappa, Rama |
| journal |
Triatoma infestans , to be or not to be autogenic? |
| journalStr |
Triatoma infestans , to be or not to be autogenic? |
| lang_code |
eng |
| isOA_bool |
false |
| dewey-hundreds |
000 - Computer science, information & general works |
| recordtype |
marc |
| publishDateSort |
2016 |
| contenttype_str_mv |
zzz |
| container_start_page |
3 |
| author_browse |
Chellappa, Rama |
| container_volume |
55 |
| physical |
3 |
| class |
004 004 DE-600 |
| format_se |
Elektronische Aufsätze |
| author-letter |
Chellappa, Rama |
| doi_str_mv |
10.1016/j.imavis.2016.04.005 |
| dewey-full |
004 |
| title_sort |
changing fortunes of pattern recognition and computer vision |
| title_auth |
The changing fortunes of pattern recognition and computer vision |
| abstract |
As someone who had been attending conferences on pattern recognition and computer vision since 1978, I have watched with interest the ups and downs of pattern recognition and computer vision areas and how they have been presented at various conferences such as PRIP, CVPR, ECCV, ICCV, ACCV, ICPR, IJCAI, AAAI, NIPS, ICASSP and ICIP. Given the recent successes of deep learning networks, it appears that the scale is tilting towards pattern recognition as is commonly understood. A good number of papers in recent vision conferences seem to push data through one or other deep learning networks and report improvements over state of the art. While one cannot argue against the remarkable (magical?) performance improvements obtained by deep learning network-based approaches, I worry that five years from now, most students in computer vision will only be aware of software that implements some deep learning network. After all, 2-D based detection and recognition problems for which the deep learning networks have shown their mettle are only a subset of the computer vision field. While enjoying the ride, I would like to caution that understanding of scene and image formation, invariants, interaction between light and matter, human vision, 3D recovery, and emerging concepts like common sense reasoning are too important to ignore for the long-term viability of the computer vision field. It will be a dream come true if we manage to integrate these computer vision concepts into deep learning networks so that more robust performance can be obtained with less data and cheaper computers. |
| abstractGer |
As someone who had been attending conferences on pattern recognition and computer vision since 1978, I have watched with interest the ups and downs of pattern recognition and computer vision areas and how they have been presented at various conferences such as PRIP, CVPR, ECCV, ICCV, ACCV, ICPR, IJCAI, AAAI, NIPS, ICASSP and ICIP. Given the recent successes of deep learning networks, it appears that the scale is tilting towards pattern recognition as is commonly understood. A good number of papers in recent vision conferences seem to push data through one or other deep learning networks and report improvements over state of the art. While one cannot argue against the remarkable (magical?) performance improvements obtained by deep learning network-based approaches, I worry that five years from now, most students in computer vision will only be aware of software that implements some deep learning network. After all, 2-D based detection and recognition problems for which the deep learning networks have shown their mettle are only a subset of the computer vision field. While enjoying the ride, I would like to caution that understanding of scene and image formation, invariants, interaction between light and matter, human vision, 3D recovery, and emerging concepts like common sense reasoning are too important to ignore for the long-term viability of the computer vision field. It will be a dream come true if we manage to integrate these computer vision concepts into deep learning networks so that more robust performance can be obtained with less data and cheaper computers. |
| abstract_unstemmed |
As someone who had been attending conferences on pattern recognition and computer vision since 1978, I have watched with interest the ups and downs of pattern recognition and computer vision areas and how they have been presented at various conferences such as PRIP, CVPR, ECCV, ICCV, ACCV, ICPR, IJCAI, AAAI, NIPS, ICASSP and ICIP. Given the recent successes of deep learning networks, it appears that the scale is tilting towards pattern recognition as is commonly understood. A good number of papers in recent vision conferences seem to push data through one or other deep learning networks and report improvements over state of the art. While one cannot argue against the remarkable (magical?) performance improvements obtained by deep learning network-based approaches, I worry that five years from now, most students in computer vision will only be aware of software that implements some deep learning network. After all, 2-D based detection and recognition problems for which the deep learning networks have shown their mettle are only a subset of the computer vision field. While enjoying the ride, I would like to caution that understanding of scene and image formation, invariants, interaction between light and matter, human vision, 3D recovery, and emerging concepts like common sense reasoning are too important to ignore for the long-term viability of the computer vision field. It will be a dream come true if we manage to integrate these computer vision concepts into deep learning networks so that more robust performance can be obtained with less data and cheaper computers. |
| collection_details |
GBV_USEFLAG_U GBV_ELV SYSFLAG_U |
| title_short |
The changing fortunes of pattern recognition and computer vision |
| url |
https://doi.org/10.1016/j.imavis.2016.04.005 |
| remote_bool |
true |
| ppnlink |
ELV00877899X |
| mediatype_str_mv |
z |
| isOA_txt |
false |
| hochschulschrift_bool |
false |
| doi_str |
10.1016/j.imavis.2016.04.005 |
| up_date |
2024-07-06T21:10:17.311Z |
| _version_ |
1803865520669196288 |
| fullrecord_marcxml |
<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000caa a22002652 4500</leader><controlfield tag="001">ELV024340367</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230625142653.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">180603s2016 xx |||||o 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1016/j.imavis.2016.04.005</subfield><subfield code="2">doi</subfield></datafield><datafield tag="028" ind1="5" ind2="2"><subfield code="a">GBV00000000000049A.pica</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)ELV024340367</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(ELSEVIER)S0262-8856(16)30066-X</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-627</subfield><subfield code="b">ger</subfield><subfield code="c">DE-627</subfield><subfield code="e">rakwb</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="082" ind1="0" ind2=" "><subfield code="a">004</subfield></datafield><datafield tag="082" ind1="0" ind2="4"><subfield code="a">004</subfield><subfield code="q">DE-600</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Chellappa, Rama</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="4"><subfield code="a">The changing fortunes of pattern recognition and computer vision</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2016transfer abstract</subfield></datafield><datafield tag="300" ind1=" " ind2=" "><subfield code="a">3</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">zzz</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">z</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">zu</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">As someone who had been attending conferences on pattern recognition and computer vision since 1978, I have watched with interest the ups and downs of pattern recognition and computer vision areas and how they have been presented at various conferences such as PRIP, CVPR, ECCV, ICCV, ACCV, ICPR, IJCAI, AAAI, NIPS, ICASSP and ICIP. Given the recent successes of deep learning networks, it appears that the scale is tilting towards pattern recognition as is commonly understood. A good number of papers in recent vision conferences seem to push data through one or other deep learning networks and report improvements over state of the art. While one cannot argue against the remarkable (magical?) performance improvements obtained by deep learning network-based approaches, I worry that five years from now, most students in computer vision will only be aware of software that implements some deep learning network. After all, 2-D based detection and recognition problems for which the deep learning networks have shown their mettle are only a subset of the computer vision field. While enjoying the ride, I would like to caution that understanding of scene and image formation, invariants, interaction between light and matter, human vision, 3D recovery, and emerging concepts like common sense reasoning are too important to ignore for the long-term viability of the computer vision field. It will be a dream come true if we manage to integrate these computer vision concepts into deep learning networks so that more robust performance can be obtained with less data and cheaper computers.</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">As someone who had been attending conferences on pattern recognition and computer vision since 1978, I have watched with interest the ups and downs of pattern recognition and computer vision areas and how they have been presented at various conferences such as PRIP, CVPR, ECCV, ICCV, ACCV, ICPR, IJCAI, AAAI, NIPS, ICASSP and ICIP. Given the recent successes of deep learning networks, it appears that the scale is tilting towards pattern recognition as is commonly understood. A good number of papers in recent vision conferences seem to push data through one or other deep learning networks and report improvements over state of the art. While one cannot argue against the remarkable (magical?) performance improvements obtained by deep learning network-based approaches, I worry that five years from now, most students in computer vision will only be aware of software that implements some deep learning network. After all, 2-D based detection and recognition problems for which the deep learning networks have shown their mettle are only a subset of the computer vision field. While enjoying the ride, I would like to caution that understanding of scene and image formation, invariants, interaction between light and matter, human vision, 3D recovery, and emerging concepts like common sense reasoning are too important to ignore for the long-term viability of the computer vision field. It will be a dream come true if we manage to integrate these computer vision concepts into deep learning networks so that more robust performance can be obtained with less data and cheaper computers.</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="n">Elsevier Science</subfield><subfield code="a">Lamattina, D ELSEVIER</subfield><subfield code="t">Triatoma infestans , to be or not to be autogenic?</subfield><subfield code="d">2022</subfield><subfield code="g">Amsterdam [u.a.]</subfield><subfield code="w">(DE-627)ELV00877899X</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:55</subfield><subfield code="g">year:2016</subfield><subfield code="g">pages:3-5</subfield><subfield code="g">extent:3</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doi.org/10.1016/j.imavis.2016.04.005</subfield><subfield code="3">Volltext</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_U</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ELV</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_U</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">55</subfield><subfield code="j">2016</subfield><subfield code="h">3-5</subfield><subfield code="g">3</subfield></datafield><datafield tag="953" ind1=" " ind2=" "><subfield code="2">045F</subfield><subfield code="a">004</subfield></datafield></record></collection>
|
| score |
7.3974 |