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

Learning 
Cross-modal Embeddings
 for Cooking Recipes 
and Food Images

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

More Decks by Leszek Rybicki

Other Decks in Research

Transcript

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

    w ϙʔϥϯυͷΫοΫύου Ͱˌ̍ͷϨγϐɿ
 ๻ͷϐΤϩΪ ࣗݾ঺հ
  2. w $MBTTJpDBUJPOPGSFDJQFT JT)"3% w *NBHFSFDPHOJUJPOPO GPPEJT)"3% w JOUSBDMBTTWBSJFUZ w JOUFSDMBTTTJNJMBSJUZ

    w 5IFFYJTUJOHEBUBTFUT BSF4."-- w 5PPNBOZJOHSFEJFOUT w $VMUVSBMCJBTFT w &YJTUJOHTPMVUJPOTIBWF MPXBDDVSBDZ http://www.robotshop.com/
  3. %BUBTFU w EJ⒎FSFOUTJUFTBTTPVSDF JODM$PPLQBE  w NSFDJQFTBOELJNBHFT w PGSFDJQFUJUMFTBSFOPUVOJRVF w

    BWFSBHFSFDJQFIBTJOHSFEJFOUT w PGJOHSFEJFOUT JOSFDJQFT w TPNFSFDJQFTBSFPOFTUFQ 
 TPNFDPOUBJOTVCSFDJQFT w TPNFGPPEUZQFTBSFWFSZQPQVMBS
 DIPDPMBUFDIJQDPPLJFT
  4. XPSEWFDNBUI man - king + woman = queen cats -

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