Ikibazo gihuza ibibazo · Hagati Urwego
Ikibazo cyanditseho amajwi
Ongera usobanure amajwi n'amajwi yanditse, hamwe na Clotho na AudioCaps, ibisobanuro bya encoder-decoder, isuzuma rya CIDEr, hamwe na Clotho y'umwimerere.
Ikibazo 1 Bya 8
Nigute amajwi yanditseho amajwi atandukanye no kumenya imvugo yikora?
Reba buri kibazo8 ibibazo
Ibisubizo nibisobanuro bigaragara mugihe ufata ikibazo.
- Nigute amajwi yanditseho amajwi atandukanye no kumenya imvugo yikora?
- Cyakora gusa guceceka
- Biratinda ariko birasa mubisohoka
- Irasobanura muri rusange acoustic aho kwandukura amagambo yavuzwe
- Ihindura inyandiko mumajwi
- Which published datasets supply general-audio descriptions for captioning in this guide?
- MNIST and CIFAR only
- Imyenda na AudioCaps
- A mandatory bank-transaction table
- Only a raw network-password list
- What architecture does the cited original Clotho baseline use to produce caption words from audio features?
- Only a fixed filename lookup
- Only a volume meter with no text output
- Only an unchanged grammar rule list
- An encoder-decoder scheme with attention
- Ni ukubera iki kwandika amajwi bifite agaciro kubigeraho?
- Irasobanura amajwi atavuga kubakumva kandi bigoye-kumva
- Yongera amajwi
- Isiba urusaku rwinyuma
- Irabika amajwi
- Which reference-comparison metric does the Clotho paper use among its caption evaluations?
- RGB color values
- CIDEr
- Audio sample rate alone
- Only a decibel reading
- Ni ikihe kibazo gikomeye gikomeje kwandikwa mu majwi?
- Amadosiye yamajwi ni mato cyane kuburyo atayatunganya
- Nta mibare ihari
- Ibisobanuro birashobora kuba ijambo rimwe gusa
- Gutanga ibisobanuro byombi kandi birinda ibisobanuro birambuye
- How many reference captions per audio file does the original Clotho paper report?
- Bitanu
- Imwe
- Fifteen
- Ijana
- How many log-mel-band features form each input frame in the original Clotho baseline described in the paper?
- 8
- 20
- 64
- 256