Tweet
Tweet

Slide 1

Slide 1 text

Computer visionͷۙ೥ͷಈ޲ͷαʔϕΠ ߴ໦ࢤ࿠ 1

Slide 2

Slide 2 text

αʔϕΠͷ໨త 2 Computer vision (CV) ݚڀͷۙ೥ͷಈ޲Λ஌Γ͍ͨʂ • ֶशख๏Λ஌Γ͍ͨ • ωοτϫʔΫͷมભΛ஌Γ͍ͨ ˠ χϡʔϥϧҎ߱ͷ$7ͷมભ΍͜Ε·Ͱͷಈ޲Λ޿͘ઙ͘঺հ

Slide 3

Slide 3 text

ࠓճ͸࿩͞ͳ͍͜ͱ 3 • ը૾/ಈըੜ੒Ұൠ • ఢରతֶश • ൒ڭࢣ͋Γֶश • ࣗݾڭࢣ͋Γֶश • ݹయతͳίϯϐϡʔλʔϏδϣϯ ͳͲͳͲɽɽ

Slide 4

Slide 4 text

ࠓ೔ͷྲྀΕ 4 ̍ɽλεΫඇಛԽϞσϧʢը૾ೝࣝͷϞσϧʣͷಈ޲ ̎ɽ֤λεΫʹಛԽͨ͠Ϟσϧͷಈ޲ ̏ɽ·ͱΊ

Slide 5

Slide 5 text

ͦͷલʹ 5 ɾਆࢿྉ܈ ɾͪ͜ΒͷࢿྉΛେ͍ʹࢀߟʹ͠·ͨ͠ http://xpaperchallenge.org/cv/ https://github.com/hirokatsukataoka16/cvpaper.challenge-summary

Slide 6

Slide 6 text

̍ɽλεΫඇಛԽϞσϧͷಈ޲ 6

Slide 7

Slide 7 text

ΞʔΩςΫνϟɾֶश๏ʢը૾ೝࣝʣ 7

Slide 8

Slide 8 text

࣌ܥྻ 8

Slide 9

Slide 9 text

AlexNet [Krizhevsky+ NeurIPS 2012] 9 • ը૾ೝࣝίϯϖͰ͋ΔILSVRC2012Ͱѹউ • ਂ૚৞ΈࠐΈχϡʔϥϧωοτϫʔΫ(CNN)ͷ࣌୅ͷນ։͚

Slide 10

Slide 10 text

࣌ܥྻ 10

Slide 11

Slide 11 text

ResNet [He+ CVPR 2016] 11 • ILSVRC2015༏উϞσϧ • Skip connectionͷಋೖͰ152૚΋ͷ௒ਂ૚CNNͷֶश͕Մೳʹ • Ҏ߱ͷը૾ೝࣝͷϞσϧ͸جຊతʹResNetͷվྑ

Slide 12

Slide 12 text

࣌ܥྻ 12

Slide 13

Slide 13 text

ResNext [Xie+ CVPR 2017] 13 • ೖྗΛ෼ذͤͯ͞ෳ਺ͷωοτϫʔΫͰॲཧ͠ɼͦͷ݁ՌΛ଍͠߹ΘͤΔ

Slide 14

Slide 14 text

WideResNet [Zagoruyko+ 2017] 14 • ਂ͞Λઙͯ͘͠෯Λ޿ͨ͘͠ResNet

Slide 15

Slide 15 text

࣌ܥྻ 15

Slide 16

Slide 16 text

PyramidNet [Han+ CVPR 2017] 16 • DownsamplingΛ༻͍Δࡍͷٸܹͳ૚෯૿ՃʹΑΔਫ਼౓ྼԽΛ๷͙ͨΊɼ શମͰগͣͭ͠૚ͷ෯Λେ͖͘͢Δ

Slide 17

Slide 17 text

SENet [Hu+ CVPR 2018] 17 • ૚΁ͷೖྗΛѹॖͨ͠΋ͷΛχϡʔϥϧωοτͰม׵͠ɼ͜ΕΛ༻͍ͯ ೖྗΛॏΈ෇͚Δ

Slide 18

Slide 18 text

DenseNet [Huang+ CVPR 2017 (best paper)] 18 • ֤૚͸ͦͷલͷ͢΂ͯͷ૚ͱskip connectionͰͭͳ͕Δ

Slide 19

Slide 19 text

MobileNet v1-3 [Howard+ 2017, Sandler+ 2018, Howard+ 2019] 19 • ۭؒํ޲ͷΈͷ৞ΈࠐΉdepthwise convolutionͱ νϟωϧํ޲ͷΈ৞ΈࠐΉpointwise convolutionͰ৞ΈࠐΈͷܰྔԽ

Slide 20

Slide 20 text

PNASNet [Liu+ 2017] 20 • Neural architecture search (NAS)ͷ݁ՌಘΒΕͨϞσϧ • CNNશମͰ͸ͳ͘ෳ਺ͷCNNϒϩοΫ͔ΒͳΔʮηϧʯΛ୳ࡧ • ୯७ͳ΋ͷ͔Βঃʑʹෳࡶͳ΋ͷ΁ͱ୳ࡧΛߦ͏

Slide 21

Slide 21 text

࣌ܥྻ 21

Slide 22

Slide 22 text

EfficientNet [Tan&Le ICML 2019] 22 • ͜Ε·Ͱͷ༷ʑͳϞσϧͷεέʔϧΞοϓख๏ͷશ෦ͷͤ

Slide 23

Slide 23 text

Noisy Student Training [Xie+ CVPR 2020] 23 • ֶशࡁΈੜెΛڭࢣͱͯ͠ɼॱ࣍େ͖ͳੜెΛֶश͢Δࣗݾڭࢣ͋Γֶश • ੜెʹϊΠζΛ෇Ճ͢Δ͜ͱͰਫ਼౓ʹՃ͑ͯؤ݈ੑ΋޲্

Slide 24

Slide 24 text

BiT [Xie+ Kolesnikov 2019] 24 • ໿10ԯύϥϝʔλͷ௒େن໛ϞσϧͰࣄલֶश • సҠઌͷσʔλ͕গͳͯ͘΋͏·͍͘͘

Slide 25

Slide 25 text

࣌ܥྻ 25

Slide 26

Slide 26 text

Vision Transformer (ViT) [Dosovitskiy+ ICLR 2021] 26 • TransformerͰը૾ೝࣝͷSOTA

Slide 27

Slide 27 text

̎ɽ֤λεΫʹಛԽͨ͠Ϟσϧͷಈ޲ 27

Slide 28

Slide 28 text

෺ମݕग़ 28

Slide 29

Slide 29 text

Ұൠ෺ମݕग़ 29 [https://pjreddie.com/media/files/papers/YOLOv3.pdf] • ը૾தͷ෺ମͷΫϥεͱҐஔΛ౰ͯΔ

Slide 30

Slide 30 text

࣌ܥྻ 30 [Zou+ 2020 Object Detection in 20 Years: A Survey]

Slide 31

Slide 31 text

R-CNN [Girshick+ CVPR 2014] 31 • ΦϒδΣΫτ͕ଘࡏ͢ΔީิྖҬΛ੾Γग़͠CNNͰಛ௃நग़

Slide 32

Slide 32 text

Fast R-CNN [Girshick ICCV 2015] 32 • ·ͣը૾ͷಛ௃ϚοϓΛ࡞੒͠ɼީิྖҬ (ROI) Λಛ௃Ϛοϓ্ʹࣹӨ • ΦϒδΣΫτͷ෼ྨͱό΢ϯσΟϯάϘοΫεͷճؼ΋NNͰߦ͏ • ֤ީิྖҬ͝ͱͰ͸ͳ֤͘ը૾͝ͱʹ৞ΈࠐΊ͹Α͘ͳΓɼߴ଎Խ

Slide 33

Slide 33 text

Faster R-CNN [Ren+ NeurIPS 2015] 33 • ީิྖҬ (ROI) ͷఏҊ·ͰؚΊͯend-to-endʹֶश

Slide 34

Slide 34 text

YOLO v1-4 [Redmon+ CVPR 2016, CVPR 2017, 2018, Bochkovskiy+ 2020] 34 • ෺ମݕग़ͱ෺ମࣝผΛҰؾ௨؏ʹߦ͏one-stageͷख๏ • Ϋϥε֬཰ɼ֬৴౓ɼό΢ϯσΟϯάϘοΫεͷ৘ใΛग़ྗ

Slide 35

Slide 35 text

SSD [Liu+ ECCV 2016] 35 • YOLOಉ༷one-stageͷख๏ • ༧Ίෳ༻ҙͨ͠਺ͷό΢ϯσΟϯάϘοΫεຖʹਪ࿦ • ֤૚ͷಛ௃Ϛοϓ͔Βಛ௃நग़͢Δ͜ͱͰ༷ʑͳεέʔϧͰ෺ମݕग़

Slide 36

Slide 36 text

RetinaNet [Lin+ ICCV 2017] 36 • ForegroundͱbackgroundͷΫϥεෆۉߧ͕one-stage๏͕ੑೳͰtwo- stage๏ʹྼΔཧ༝Ͱ͋Δ͜ͱΛࢦఠ • ΫϥεෆۉߧʹରԠ͢ΔͷͨΊͷFocal LossͷఏҊʹΑΓɼ1-stageͳ ͕Βߴ͍ਫ਼౓ͷ෺ମೝࣝΛ࣮ݱ • ϕʔεͷΞʔΩςΫνϟʔʹޙड़ͷFeature Pyramid NetworkΛ࢖༻

Slide 37

Slide 37 text

FCOS [Tian+ ICCV 2019] 37 • RetinaNetͷվྑ൛ • ෺ମͷத৺ͷਪఆΛ௥ՃͰߦ͍ɼΞϯΧʔϑϦʔͳ෺ମݕग़Λ࣮ݱ

Slide 38

Slide 38 text

Bridging the Gap Between Anchor-based and Anchor-free Detection [Zhang+ 2019] 38 • Anchor-basedͱancho-freeͷҧ͍͸ɼෛྫͱਖ਼ྫͷબ୒ͷҧ͍

Slide 39

Slide 39 text

ηάϝϯςʔγϣϯ 39

Slide 40

Slide 40 text

ηάϝϯςʔγϣϯ 40 [https://arxiv.org/pdf/1706.05587.pdf] • ֤ϐΫηϧຖʹ෺ମͷΫϥε/എܠͷࣝผΛ͢Δ

Slide 41

Slide 41 text

࣌ܥྻ 41 [Minaee+ 2020 Image Segmentation Using Deep Learning: A Survey]

Slide 42

Slide 42 text

FCN [Long+ CVPR 2015] 42 • CNNͷग़ྗ૚΋৞ΈࠐΈ૚ʹ͢Δ͜ͱͰɼώʔτϚοϓΛग़ྗ

Slide 43

Slide 43 text

SegNet [Badrinarayanan+ 2015] 43 • શͯ৞ΈࠐΈ૚ͷΤϯίʔμͱσίʔμ͔ΒͳΔωοτϫʔΫ • σίʔμΛ༻͍Δ͜ͱͰDeconvolution΋ஈ֊తʹߦ͑Δ

Slide 44

Slide 44 text

U-Net [Ronneberger+ MICCAI 2015] 44 • Τϯίʔμͷಛ௃දݱΛskip connectionͰσίʔμʹίϐʔͯ͠౉͢

Slide 45

Slide 45 text

DeepLab v1-3 [Chen+ TPAMI 2017] 45 • Down samplingΛͳ͘͠ɼdilated convolutionͱ૒ઢܗิؒΛ૊Έ߹Θ ͤΔ͜ͱͰߴղ૾౓ͳηάϝϯςʔγϣϯΛ࣮ݱ [Cui+ Remote Sens.2019]

Slide 46

Slide 46 text

FastFCN [Wu+ 2019] 46 • Joint Pyramid Upsampling (JPU) ͷಋೖͰdilated convolutionʹൺ΂ͯ ܭࢉίετΛେ෯ʹ࡟ݮ

Slide 47

Slide 47 text

Mask R-CNN [He+ ICCV 2017] 47 • Bounding boxͷ༧ଌʹՃ͑ͯΫϥεͷϚεΫ΋༧ଌ͢ΔFaster R-CNN • RoIPoolʹ୅ΘΔRoIAlignͷಋೖͰྖҬ෼ׂͳͲ΋Մೳʹ

Slide 48

Slide 48 text

PSPNet [Zhao+ CVPR 2017] 48 • ༷ʑͳεέʔϧͷϓʔϦϯάʹΑΓϚϧνεέʔϧͳಛ௃දݱΛ֫ಘ

Slide 49

Slide 49 text

FPN [Lin+ CVPR 2017] 49 • CNNͷ֊૚ੑΛར༻֤͠֊૚Ͱ༧ଌͯ͠Ϛϧνεέʔϧͳಛ௃Λ֫ಘ • ग़ྗ૚ʹ͍ۙಛ௃Λೖྗ૚ʹ͍ۙଆʹ΋఻͑Δ͜ͱͰɼઙ͍૚Ͱ΋༗ ҙຯͳಛ௃நग़͕Մೳ

Slide 50

Slide 50 text

Visual Question Answering 50

Slide 51

Slide 51 text

Visual Question Answering 51 [https://arxiv.org/pdf/1505.00468.pdf] • ը૾ʹର͢Δ࣭໰จ΁ͷԠ౴

Slide 52

Slide 52 text

࣌ܥྻ 52 [Srivastava+ 2020 Visual Question Answering using Deep Learning: A Survey and Performance Analysis]

Slide 53

Slide 53 text

σʔληοτ 53 [Srivastava+ 2020 Visual Question Answering using Deep Learning: A Survey and Performance Analysis]

Slide 54

Slide 54 text

VQA [Agrawal+ ICCV 2015] 54 • LSTMͰ࣭໰จΛɼCNNͰը૾ΛຒΊࠐΜͰಛ௃දݱΛ࡞੒

Slide 55

Slide 55 text

Stacked Attention Networks [Yang+ CVPR 2016] 55 • CNNಛ௃ྔʹଟஈ֊ͷattentionΛ͔͚ͯஈ֊తʹର৅ΛߜΓࠐΉ

Slide 56

Slide 56 text

Embodied Question Answering [Das+ CVPR 2018] 56 • ࣭໰͕༩͑ΒΕΔͱɼΤʔδΣϯτ͸γϛϡϨʔγϣϯۭؒ಺Ͱߦಈ Λͱͬͯ౴͑Λݟ͚ͭΔ

Slide 57

Slide 57 text

CLEVR [Johnson+ CVPR 2017] 57 • VQAͷͨΊͷσʔληοτ • ࿦ཧతͳਪ࿦͕ඞཁͱ͞ΕΔ

Slide 58

Slide 58 text

ಈըೝࣝ 58

Slide 59

Slide 59 text

࣌ܥྻ 59 [Zhu+ 2020 A Comprehensive Study of Deep Video Action Recognition]

Slide 60

Slide 60 text

σʔληοτ 60 [Zhu+ 2020 A Comprehensive Study of Deep Video Action Recognition]

Slide 61

Slide 61 text

෼ྨ 61 [Zhu+ 2020 A Comprehensive Study of Deep Video Action Recognition]

Slide 62

Slide 62 text

3D CNN (C3D) [Tran+ ICCV 2015] 62 • 3࣍ݩ৞ΈࠐΈΛ༻͍Δ͜ͱͰ࣌ؒํ޲ͷಛ௃΋දݱ

Slide 63

Slide 63 text

(2+1)D CNN [Tran+ CVPR 2018] 63 • Ұͭͷ૚ͰҰؾʹ࣌ؒํ޲·Ͱ৞ΈࠐΉͷͰ͸ͳ͘ɼ·ۭͣؒํ޲ʹ ৞ΈࠐΜͩ͋ͱͰ࣌ؒํ޲ʹ৞ΈࠐΉ

Slide 64

Slide 64 text

I3D [Carreira&Zisserman CVPR 2017] 64 • 3D ConvΛੵΈॏͶͨωοτϫʔΫ

Slide 65

Slide 65 text

Non-local [Wang+ CVPR 2018] 65 • AttentionʹΑΔॏΈ෇͚ͰɼେҬతͳ৘ใΛՃຯ • ͋ΔҐஔͷ஋Λͦͷଞͷ͢΂ͯͷҐஔͷಛ௃ͷॏΈ෇͖࿨Ͱදݱ

Slide 66

Slide 66 text

SlowFast Networks [Feichtenhofer+ ICCV 2019] 66 • ௿ϑϨʔϜϨʔτͰۭؒಛ௃ΛɼߴϑϨʔϜϨʔτͰ࣌ؒಛ௃Λଊ͑Δ

Slide 67

Slide 67 text

࢟੎ਪఆ 67

Slide 68

Slide 68 text

෼ྨ 68 [Chen+ 2020 Monocular Human Pose Estimation: A Survey of Deep Learning-based Methods] [Zheng+ 2020 Deep Learning-Based Human Pose Estimation: A Survey]

Slide 69

Slide 69 text

Convolutional Pose Machines [Wei+ CVPR 2016] 69 • ଟஈ֊ͷ༧ଌʹΑΓɼ֤਎ମ෦Ґͷਪఆਫ਼౓ΛߴΊΔ

Slide 70

Slide 70 text

Part Affinity Fields [Cao+ CVPR 2017] 70 • ࢛ࢶͷҐஔͱ޲͖ΛຒΊࠐΉϕΫτϧ৔Λ༻͍ͨ࢟੎ਪఆ

Slide 71

Slide 71 text

HRNet [Sun+ CVPR 2019] 71 • Sub-networkΛ௥Ճ͢Δ͜ͱͰશମͷղ૾౓Λམͱͣ࢟͞੎ਪఆ͕Մೳ

Slide 72

Slide 72 text

3D 72

Slide 73

Slide 73 text

෼ྨ 73 [Ahmed+ 2020 A survey on Deep Learning Advances on Different 3D Data Representations]

Slide 74

Slide 74 text

3D ఺܈ 74

Slide 75

Slide 75 text

࣌ܥྻ 75 [Guo+ 2020 Deep Learning for 3D Point Clouds: A Survey]

Slide 76

Slide 76 text

෼ྨ 76 [Guo+ 2020 Deep Learning for 3D Point Clouds: A Survey]

Slide 77

Slide 77 text

σʔληοτ 77 [Guo+ 2020 Deep Learning for 3D Point Clouds: A Survey]

Slide 78

Slide 78 text

PointNet [Qi+ CVPR 2017] 78 • ఺܈σʔλΛೖྗͱ͠ɼճస΍ॱংͷม׵ͳͲͷૢ࡞ʹରͯ͠ෆมͳಛ ௃Λग़ྗ͢ΔωοτϫʔΫ

Slide 79

Slide 79 text

PointNet++ [Qi+ NeurIPS 2017] 79 • PointNet͸ہॴతͳ৘ใΛ͏·͘र͍͑ͯͳ͔͕ͬͨɼPointNetΛ֊૚త ʹద༻͢Δ͜ͱͰ͜ΕʹରԠ

Slide 80

Slide 80 text

Dynamic Graph CNN [ACMTG+ 2019] 80 • ֤఺ͱͦͷۙ๣ͷؔ܎Λදݱͨ͠Τοδಛ௃Λͭ͘Δ৞ΈࠐΈͷఏҊ

Slide 81

Slide 81 text

VoxelNet [Zhou+ CVPR 2018] 81 • ఺܈σʔλΛvoxelʹ੾Γ෼͚ɼ֤ϘΫηϧ୯ҐͰಛ௃දݱͷຒΊࠐΈ • 3D఺܈෺ମೝࣝͷਫ਼౓޲্

Slide 82

Slide 82 text

3D ϝογϡ 82

Slide 83

Slide 83 text

Heat Diffusion Equation 83 • ۂ໘ʢϦʔϚϯଟ༷ମʣ্Ͱͷ೤֦ࢄΛߟ͑Δ [Bronstein+ 2016 Geometric deep learning: going beyond Euclidean data]

Slide 84

Slide 84 text

Geodesic CNN [Masci+ ICCV 2015] 84 • ඇϢʔΫϦουଟ༷ମʹ΋ରԠՄೳͳCNNͷఏҊ • ֤఺Ͱۃ࠲ඪΛߟ͑Δ

Slide 85

Slide 85 text

Anisotropic CNN [Boscaini+ NeurIPS 2016] 85 • ඇ౳ํͳ೤ΧʔωϧΛߟ͑Δ͜ͱͰہॴతͳදݱΛΑΓΑ͘நग़ [Bronstein+ 2016 Geometric deep learning: going beyond Euclidean data]

Slide 86

Slide 86 text

Monet [Monti+ CVPR 2017] 86 • ͜Ε·ͰͷඇϢʔΫϦουCNNͷҰൠԽ • ࠲ඪͷҰൠԽ • ݻఆͷΧʔωϧͰ͸ͳֶ͘शՄೳͳΧʔωϧΛ࢖͍ɼΧʔωϧͷҰൠԽ

Slide 87

Slide 87 text

3D ඍ෼ՄೳϨϯμϥʔ 87

Slide 88

Slide 88 text

ඍ෼ՄೳϨϯμϥʔ 88 % % ϨϯμϦϯά

Slide 89

Slide 89 text

Perspective Transformer Nets [Yan+ NeurIPS 2016] 89 • ϘΫηϧͷඍ෼ՄೳϨϯμϥʔ

Slide 90

Slide 90 text

Neural 3D Mesh Renderer [Monti+ CVPR 2017] 90 • ߴਫ਼౓ͳϝογϡͷඍ෼ՄೳϨϯμϥʔ • ϥελϥΠζ෦෼Λඍ෼Մೳʹͨ͜͠ͱͰٯ఻೻Մೳʹ [https://www.slideshare.net/100001653434308/23d-neural-3d-mesh-renderer-cvpr-2018]

Slide 91

Slide 91 text

Transformers/Attention 91

Slide 92

Slide 92 text

࣌ܥྻ 92 [Han+ 2021 A Survey on Visual Transformer]

Slide 93

Slide 93 text

෼ྨ 93 [Han+ 2021 A Survey on Visual Transformer] [Khan+ 2021 Transformers in Vision: A Survey]

Slide 94

Slide 94 text

DETR [Carion+ ECCV 2020] 94 • CNNͰը૾ಛ௃Λநग़ͨ͠ͷͪɼtransformerͰ෺ମೝࣝ

Slide 95

Slide 95 text

iGPT [Chen+ ICML 2020] 95 • ը૾ಛ௃ΛGPT-2Ͱڭࢣͳֶ͠श

Slide 96

Slide 96 text

Vision Transformer (ViT) [Dosovitskiy+ ICLR 2021] 96 • ७ਮͳTransformerͰը૾ೝࣝͷSOTA ࠶ܝ

Slide 97

Slide 97 text

IPT [Chen+ 2020] 97 • ෳ਺ͷλεΫΛಉ࣌ʹߦ͏transformer

Slide 98

Slide 98 text

98 [https://twitter.com/jaguring1/status/1377710003377725441]

Slide 99

Slide 99 text

99 [https://www.slideshare.net/cvpaperchallenge/transformer-247407256]

Slide 100

Slide 100 text

ɽ·ͱΊ 100

Slide 101

Slide 101 text

·ͱΊ 101 • Ϟσϧͷൃల͸ResNetΛϕʔεʹɼෳࡶԽɾେن໛Խɾޮ཰Խ • Vision transformer͕ଓʑొ৔ • جຊతͳcomputer visionͷλεΫʹಛԽͨ͠Ϟσϧ͸ϕϯνϚʔΫ͕ ݻ·͍ͬͯΔ༷ࢠ • 2D → 3DͷྲྀΕ • Ϛϧνεέʔϧͳ৘ใͷ૊ΈࠐΈ͕Α͋͘Δҹ৅ • ࡉ͔͍ςΫχοΫ͕ॏཁͳҹ৅ [https://www.slideshare.net/cvpaperchallenge/cvpr-2020-237139930]

Slide 102

Slide 102 text

ࢀߟࢿྉͳͲ 102

Slide 103

Slide 103 text

ࢀߟࢿྉ 103 • [cvpaper.challenge-summary](https://github.com/hirokatsukataoka16/cvpaper.challenge-summary) • [CVPR 2016 ଎ใ](https://www.slideshare.net/HirokatsuKataoka/cvpr-2016) • [CVPR 2017 ଎ใ](https://www.slideshare.net/cvpaperchallenge/cvpr-2017-78294211) • [CVPR 2018 ଎ใ](https://www.slideshare.net/cvpaperchallenge/cvpr-2018-102878612) • [CVPR 2019 ଎ใ](https://www.slideshare.net/cvpaperchallenge/cvpr-2019) • [CVPR 2020 ଎ใ](https://www.slideshare.net/cvpaperchallenge/cvpr-2020-237139930) • [ಈըೝࣝαʔϕΠv1ʢϝλαʔϕΠ ʣ](https://www.slideshare.net/cvpaperchallenge/v1-232973484) • [Vision and LanguageʢϝλαʔϕΠ ʣ](https://www.slideshare.net/cvpaperchallenge/vision-and-language-232926110) • [৞ΈࠐΈχϡʔϥϧωοτϫʔΫͷݚڀಈ޲](https://www.slideshare.net/ren4yu/ss-84282514) • [ConvNetͷྺ࢙ͱResNetѥछɺ΂ετϓϥΫςΟε](https://www.slideshare.net/ren4yu/convnetresnet) • [৞ΈࠐΈχϡʔϥϧωοτϫʔΫͷߴਫ਼౓Խͱߴ଎Խ](https://www.slideshare.net/ren4yu/ss-145689425) • [࿦จ঺հ: Fast R-CNN&Faster R-CNN](https://www.slideshare.net/takashiabe338/fast-rcnnfaster-rcnn) • [ʲ෺ମݕग़ʳSSD(Single Shot MultiBox Detector)ͷղઆ](https://www.acceluniverse.com/blog/developers/2020/02/SSD.html) • [ʲ෺ମݕग़ख๏ͷྺ࢙ : YOLOͷ঺հʳ](https://qiita.com/cv_carnavi/items/68dcda71e90321574a2b) • [ը૾ೝࣝͱਂ૚ֶश](https://www.slideshare.net/ren4yu/ss-234439652) • [semantic segmentation αʔϕΠ](https://www.slideshare.net/yoheiokawa/semantic-segmentation-141471958) • [Semantic segmentation ৼΓฦΓ](https://speakerdeck.com/motokimura/semantic-segmentation-zhen-rifan-ri) • [[DLྠಡձ]SlowFast Networks for Video Recognition](https://www.slideshare.net/DeepLearningJP2016/dlslowfast-networks-for-video-recognition-202057397) • [ࡾ࣍ݩ఺܈ΛऔΓѻ͏χϡʔϥϧωοτϫʔΫͷαʔϕΠ](https://www.slideshare.net/naoyachiba18/ss-120302579) • [ࡾ࣍ݩ఺܈ΛऔΓѻ͏χϡʔϥϧωοτϫʔΫͷαʔϕΠ Ver. 2](https://speakerdeck.com/nnchiba/point-cloud-deep-learning-survey-ver-2) • [఺܈ਂ૚ֶश Meta-study](https://www.slideshare.net/naoyachiba18/metastudy) • [ୈ̍ճ ࠷৽ͷML,CV,NLP ؔ࿈࿦จಡΈձ PointNet](https://www.slideshare.net/FujimotoKeisuke/point-net) • [ [DLྠಡձ]MeshͱDeep Learning Surface Networks & AtlasNet](https://www.slideshare.net/DeepLearningJP2016/dlmeshdeep-learning-surface-networks-atlasnet) • [࿦จ·ͱΊɿConvolutional Pose Machines](https://qiita.com/masataka46/items/88f1a375ce8a485d9454) • [ίϯϐϡʔλϏδϣϯͷ࠷৽࿦จௐࠪ 2D Human Pose Estimation ฤ](https://engineer.dena.com/posts/2019.11/cv-papers-19-2d-human-pose-estimation/) • [[ୈ2ճ3Dษڧձ ݚڀ঺հ] Neural 3D Mesh Renderer (CVPR 2018)](https://www.slideshare.net/100001653434308/23d-neural-3d-mesh-renderer-cvpr-2018) • [DeepLabʹ୅ΘΓݱࡏͷSOTAͰ͋ΔFastFCN(JPU)ͷ࿦จղઆ](https://qiita.com/kamata1729/items/1b495658a63d76904ac3)

Slide 104

Slide 104 text

104