Upgrade to Pro — share decks privately, control downloads, hide ads and more …

Learning 
Cross-modal Embeddings
 for Cooking R...

Avatar for Leszek Rybicki Leszek Rybicki
August 06, 2017
Research
810
1

Learning 
Cross-modal Embeddings
 for Cooking Recipes 
and Food Images

Review and presentation of the Image to Recipe paper and model

Avatar for Leszek Rybicki

Leszek Rybicki

August 06, 2017

More Decks by Leszek Rybicki

See All by Leszek Rybicki
Let's talk about Fakes
Avatar for Leszek Rybicki lunardog
0
180
How to Patch Image Classifiers
Avatar for Leszek Rybicki lunardog
0
2.9k
Towards Realistic Predictors - EN
Avatar for Leszek Rybicki lunardog
0
2.8k
Towards Realistic Predictors
Avatar for Leszek Rybicki lunardog
1
2.6k
Deep Learning Hot Dog Detector
Avatar for Leszek Rybicki lunardog
0
320
Finding beans in burgers: paper reading notes
Avatar for Leszek Rybicki lunardog
0
2k
Kelner: Serve Your Models
Avatar for Leszek Rybicki lunardog
0
160
Image Analysis at Cookpad
Avatar for Leszek Rybicki lunardog
1
2.1k
Kelner: serve your models
Avatar for Leszek Rybicki lunardog
1
430

Other Decks in Research

See All in Research
SoftMatcha 2: 1兆語規模コーパスの超高速かつ柔らかい検索
Avatar for Masataka YONEDA e869120_sub
7
3.7k
AIエージェント時代のLLM-jpモデルのあるべき姿
Avatar for Kouta Nakayama k141303
0
580
VLMの推論を高速化する視覚トークン削減の仕組み
Avatar for tattaka tattaka
2
250
NII S. Koyama's Lab Research Overview AY2026
Avatar for NII S. Koyama's Lab skoyamalab
0
530
ros2-perf-multihost: 分散システムにおける客観的なアーキテクチャ評価フレームワーク
Avatar for takasehideki takasehideki
0
210
Using our influence and power for patient safety
Avatar for Helen Bevan helenbevan
0
390
HAKARI-Bench - 実運用視点での情報検索モデル評価ベンチマーク
Avatar for Yuichi Tateno hotchpotch
1
680
敵対生成プロンプト同時探索による内省型プロンプト最適化
Avatar for Kotaro Inoue kinoue_smarthr
0
370
2025年度秋葉原ウォーカブルプロジェクト調査報告 「アキバらしいウォーカブル」とは何か
Avatar for 日本大学 都市計画研究室（泉山ゼミ） izumiyama_lab
1
180
AIで最適化を解けるか？
Avatar for MIKIO KUBO mickey_kubo
0
150
Scalable dynamic origin-destination demand estimation enhanced by high-resolution satellite imagery data
Avatar for SatAI.challenge satai
3
410
さくらインターネット研究所テックトーク2026春、研究開発Gr.25年度成果26年度方針
Avatar for KIKUCHI Shunsuke kikuzo
0
180

Featured

See All Featured
Learning to Love Humans: Emotional Interface Design
Avatar for Aarron Walter aarron
275
41k
Data-driven link building: lessons from a $708K investment (BrightonSEO talk)
Avatar for Szymon Słowik szymonslowik
1
1.2k
We Are The Robots
Avatar for Honza Javorek honzajavorek
0
300
Why Your Marketing Sucks and What You Can Do About It - Sophie Logan
Avatar for Sophie Logan marketingsoph
0
390
Breaking role norms: Why Content Design is so much more than writing copy - Taylor Woolridge
Avatar for UX Y'all uxyall
0
370
Typedesign – Prime Four
Avatar for Hannes Fritz hannesfritz
42
3.1k
RailsConf & Balkan Ruby 2019: The Past, Present, and Future of Rails at GitHub
Avatar for Eileen M. Uchitelle eileencodes
141
35k
Building Applications with DynamoDB
Avatar for Matt Wood mza
96
7.2k
XXLCSS - How to scale CSS and keep your sanity
Avatar for Zaharenia Atzitzikaki sugarenia
249
1.3M
GraphQLとの向き合い方2022年版
Avatar for Yosuke Kurami quramy
50
15k
Color Theory Basics | Prateek | Gurzu
Avatar for Gurzu gurzu
0
430
HU Berlin: Industrial-Strength Natural Language Processing with spaCy and Prodigy
Avatar for Ines Montani inesmontani
PRO
0
660

Transcript

  1. -FBSOJOH
 $SPTTNPEBM&NCFEEJOHT
 GPS$PPLJOH3FDJQFT
 BOE'PPE*NBHFT 2017.08.06 KantoCV #41

  2. w -FT[FL ϨγΣοΫ  w ϙʔϥϯυग़਎ w ΫοΫύουͷݚڀ։ൃ෦ w ը૾ղੳ

    w ϙʔϥϯυͷΫοΫύου Ͱˌ̍ͷϨγϐɿ
 ๻ͷϐΤϩΪ ࣗݾ঺հ

  3. 2VJ[

  4. A D G J B E H K C I

    F

  5. A D G J B E H K C I

    F

  6. C B A 1 2 3

  7. C B A 1 2 3

  8. C B A 1 2 3

  9. C B A 1 2 3

  10. A B C D E F G

  11. A B C D E F G

  12. 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/

  13. July 20, 2017

  14. July 20, 2017

  15. July 20, 2017

  16. July 20, 2017

  17. July 20, 2017

  18. July 20, 2017

  19. 3FDJQF. %BUBTFU

  20. None
  21. None

  22. https://cookpad.com/recipe/1758645

  23. %BUBTFU w EJ⒎FSFOUTJUFTBTTPVSDF JODM$PPLQBE  w NSFDJQFTBOELJNBHFT w PGSFDJQFUJUMFTBSFOPUVOJRVF w

    BWFSBHFSFDJQFIBTJOHSFEJFOUT w PGJOHSFEJFOUT JOSFDJQFT w TPNFSFDJQFTBSFPOFTUFQ 
 TPNFDPOUBJOTVCSFDJQFT w TPNFGPPEUZQFTBSFWFSZQPQVMBS
 DIPDPMBUFDIJQDPPLJFT

  24. &NCFEEJOH

  25. TGEKRGURCEG KOCIGURCEG LQKPVGODGFFKPIURCEG UOQQVJKGU ITCVKPU UWUJK JCODWTIGTU */56*5*0/

  26. .PEFM0WFSWJFX

  27. w XPSEWFDPOJOHSFEJFOUT w UCTQPGPMJWFPJM w PMJWF@PJM CFMM@QFQQFS CMBDL@QFQQFS w CJEJSFDUJPOBM-45.

  28. w TLJQJOTUSVDUJPOT-45.PO-45. w SFDJQFTUBSUBOEFOENBSLFST w DPODBUFOBUFpOBMFODPEJOHXJUIUIF JOHSFEJFOUFODPEJOH

  29. w UFTUFE7((BOE3FT/FU w DMBTTJpDBUJPOˠFNCFEEJOHMBZFS w *NBHF/FUQSFUSBJOFE pOFUVOFE w USBJOFETFQBSBUFMZGSPNUFYU

  30. w NBUDIJOHQBJSTNJYFEQBJST w 

  31. w 'PPEDBUFHPSJFTHVFTTFEGSPNSFDJQFUJUMF w FNCFEEJOHˠDBUFHPSZDMBTTJpFS w JGTBNFDBUFHPSZLreg  w λ 

  32. 5PUBMMPTTGVODUJPO

  33. &YQFSJNFOUT

  34. JNBHFˠSFDJQF

  35. SFDJQFˠJNBHF

  36. None

  37. #FUUFSUIBO)VNBO

  38. %&.0 http://wednesday.csail.mit.edu: 4242/

  39. 6OJU"DUJWBUJPOT

  40. XPSEWFDNBUI http://www.samyzaf.com/ML/nlp/nlp.html

  41. XPSEWFDNBUI man - king + woman = queen cats -

    cat + dog = dogs France - Paris + England = London London - England + Italy = Rome Italy - Rome + Paris = France

  42. .BUIPO3FDJQFT

  43. .BUIPO*NBHFT

  44. $SPTTNPEBM

  45. w 3FDJQF.EBUBTFU w JNBHFˠSFDJQF w SFDJQFˠJNBHF w CFUUFSUIBOIVNBO w JOHSFEJFOUEFUFDUJPO

    w SFDJQFBSJUINFUJD http://www.robotshop.com/ ·ͱΊ

  46. Ҏ্