Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Features
Speaker Deck
PRO
Sign in
Sign up for free
Search
Search
Learning Cross-modal Embeddings for Cooking R...
Search
Leszek Rybicki
August 06, 2017
Research
1
640
Learning Cross-modal Embeddings for Cooking Recipes and Food Images
Review and presentation of the Image to Recipe paper and model
Leszek Rybicki
August 06, 2017
Tweet
Share
More Decks by Leszek Rybicki
See All by Leszek Rybicki
Let's talk about Fakes
lunardog
0
100
How to Patch Image Classifiers
lunardog
0
1.7k
Towards Realistic Predictors - EN
lunardog
0
1.6k
Towards Realistic Predictors
lunardog
1
2k
Deep Learning Hot Dog Detector
lunardog
0
230
Finding beans in burgers: paper reading notes
lunardog
0
1.3k
Kelner: Serve Your Models
lunardog
0
100
Image Analysis at Cookpad
lunardog
1
1.6k
Kelner: serve your models
lunardog
1
330
Other Decks in Research
See All in Research
言語と数理の交差点:テキストの埋め込みと構造のモデル化 (IBIS 2024 チュートリアル)
yukiar
3
730
Zipf 白色化:タイプとトークンの区別がもたらす良質な埋め込み空間と損失関数
eumesy
PRO
5
650
[ECCV2024読み会] 衛星画像からの地上画像生成
elith
1
660
Physics of Language Models: Part 3.1, Knowledge Storage and Extraction
sosk
1
950
機械学習でヒトの行動を変える
hiromu1996
1
300
システムから変える 自分と世界を変えるシステムチェンジの方法論 / Systems Change Approaches
dmattsun
3
860
尺度開発における質的研究アプローチ(自主企画シンポジウム7:認知行動療法における尺度開発のこれから)
litalicolab
0
350
渋谷Well-beingアンケート調査結果
shibuyasmartcityassociation
0
260
marukotenant01/tenant-20240826
marketing2024
0
510
論文読み会 SNLP2024 Instruction-tuned Language Models are Better Knowledge Learners. In: ACL 2024
s_mizuki_nlp
1
350
精度を無視しない推薦多様化の評価指標
kuri8ive
1
240
RSJ2024「基盤モデルの実ロボット応用」チュートリアルA(河原塚)
haraduka
3
640
Featured
See All Featured
Optimising Largest Contentful Paint
csswizardry
33
2.9k
Documentation Writing (for coders)
carmenintech
65
4.4k
[Rails World 2023 - Day 1 Closing Keynote] - The Magic of Rails
eileencodes
33
1.9k
Making Projects Easy
brettharned
115
5.9k
Designing the Hi-DPI Web
ddemaree
280
34k
Teambox: Starting and Learning
jrom
133
8.8k
Docker and Python
trallard
40
3.1k
The Invisible Side of Design
smashingmag
298
50k
Statistics for Hackers
jakevdp
796
220k
Performance Is Good for Brains [We Love Speed 2024]
tammyeverts
6
410
Large-scale JavaScript Application Architecture
addyosmani
510
110k
Building Better People: How to give real-time feedback that sticks.
wjessup
364
19k
Transcript
-FBSOJOH $SPTTNPEBM&NCFEEJOHT GPS$PPLJOH3FDJQFT BOE'PPE*NBHFT 2017.08.06 KantoCV #41
w -FT[FL ϨγΣοΫ w ϙʔϥϯυग़ w ΫοΫύουͷݚڀ։ൃ෦ w ը૾ղੳ
w ϙʔϥϯυͷΫοΫύου Ͱˌ̍ͷϨγϐɿ ͷϐΤϩΪ ࣗݾհ
2VJ[
A D G J B E H K C I
F
A D G J B E H K C I
F
C B A 1 2 3
C B A 1 2 3
C B A 1 2 3
C B A 1 2 3
A B C D E F G
A B C D E F G
w $MBTTJpDBUJPOPGSFDJQFT JT)"3% w *NBHFSFDPHOJUJPOPO GPPEJT)"3% w JOUSBDMBTTWBSJFUZ w JOUFSDMBTTTJNJMBSJUZ
w 5IFFYJTUJOHEBUBTFUT BSF4."-- w 5PPNBOZJOHSFEJFOUT w $VMUVSBMCJBTFT w &YJTUJOHTPMVUJPOTIBWF MPXBDDVSBDZ http://www.robotshop.com/
July 20, 2017
July 20, 2017
July 20, 2017
July 20, 2017
July 20, 2017
July 20, 2017
3FDJQF. %BUBTFU
None
None
https://cookpad.com/recipe/1758645
%BUBTFU w EJ⒎FSFOUTJUFTBTTPVSDF JODM$PPLQBE w NSFDJQFTBOELJNBHFT w PGSFDJQFUJUMFTBSFOPUVOJRVF w
BWFSBHFSFDJQFIBTJOHSFEJFOUT w PGJOHSFEJFOUT JOSFDJQFT w TPNFSFDJQFTBSFPOFTUFQ TPNFDPOUBJOTVCSFDJQFT w TPNFGPPEUZQFTBSFWFSZQPQVMBS DIPDPMBUFDIJQDPPLJFT
&NCFEEJOH
TGEKRGURCEG KOCIGURCEG LQKPVGODGFFKPIURCEG UOQQVJKGU ITCVKPU UWUJK JCODWTIGTU */56*5*0/
.PEFM0WFSWJFX
w XPSEWFDPOJOHSFEJFOUT w UCTQPGPMJWFPJM w PMJWF@PJM CFMM@QFQQFS CMBDL@QFQQFS w CJEJSFDUJPOBM-45.
w TLJQJOTUSVDUJPOT-45.PO-45. w SFDJQFTUBSUBOEFOENBSLFST w DPODBUFOBUFpOBMFODPEJOHXJUIUIF JOHSFEJFOUFODPEJOH
w UFTUFE7((BOE3FT/FU w DMBTTJpDBUJPOˠFNCFEEJOHMBZFS w *NBHF/FUQSFUSBJOFE pOFUVOFE w USBJOFETFQBSBUFMZGSPNUFYU
w NBUDIJOHQBJSTNJYFEQBJST w
w 'PPEDBUFHPSJFTHVFTTFEGSPNSFDJQFUJUMF w FNCFEEJOHˠDBUFHPSZDMBTTJpFS w JGTBNFDBUFHPSZLreg w λ
5PUBMMPTTGVODUJPO
&YQFSJNFOUT
JNBHFˠSFDJQF
SFDJQFˠJNBHF
None
#FUUFSUIBO)VNBO
%&.0 http://wednesday.csail.mit.edu: 4242/
6OJU"DUJWBUJPOT
XPSEWFDNBUI http://www.samyzaf.com/ML/nlp/nlp.html
XPSEWFDNBUI man - king + woman = queen cats -
cat + dog = dogs France - Paris + England = London London - England + Italy = Rome Italy - Rome + Paris = France
.BUIPO3FDJQFT
.BUIPO*NBHFT
$SPTTNPEBM
w 3FDJQF.EBUBTFU w JNBHFˠSFDJQF w SFDJQFˠJNBHF w CFUUFSUIBOIVNBO w JOHSFEJFOUEFUFDUJPO
w SFDJQFBSJUINFUJD http://www.robotshop.com/ ·ͱΊ
Ҏ্