- OpenAI의 CLIP 신경망을 이용해서 비디오 안의 특정 장면을 검색
ㅤ→ "Road Works", "People crossing the street" "Fire truck" 처럼 영상안의 이미지를 검색
동작방식
1. 유튜브 비디오 다운로드
2. 각 프레임을 추출
3. 모든 프레임을 CLIP으로 인코딩
4. CLIP으로 자연어 검색을 인코딩
5. 자연어 검색으로 특정 씬 찾기
- Google Colab에서 노트북으로 바로 실행가능
ㅤ→ https://colab.research.google.com/github/haltakov/…
댓글에 같은 개발자가 Unsplash 의 이미지 검색도 CLIP 으로 해둔게 있는데, 이것도 무척 유용할듯
- https://github.com/haltakov/natural-language-image-search
- Google Colab : https://colab.research.google.com/github/haltakov/…
Unsplash에 올라온 200만개의 사진중에서 원하는 내용의 사진을 찾아 줍니다.
- "Two dogs playing in the snow", "The word love written on the wall", "The feeling when your program finally works"
Detect language Afrikaans Albanian Amharic Arabic Armenian Azerbaijani Basque Belarusian Bengali Bosnian Bulgarian Catalan Cebuano Chichewa Chinese (Simplified) Chinese (Traditional) Corsican Croatian Czech Danish Dutch English Esperanto Estonian Filipino Finnish French Frisian Galician Georgian German Greek Gujarati Haitian Creole Hausa Hawaiian Hebrew Hindi Hmong Hungarian Icelandic Igbo Indonesian Irish Italian Japanese Javanese Kannada Kazakh Khmer Korean Kurdish Kyrgyz Lao Latin Latvian Lithuanian Luxembourgish Macedonian Malagasy Malay Malayalam Maltese Maori Marathi Mongolian Myanmar (Burmese) Nepali Norwegian Pashto Persian Polish Portuguese Punjabi Romanian Russian Samoan Scots Gaelic Serbian Sesotho Shona Sindhi Sinhala Slovak Slovenian Somali Spanish Sundanese Swahili Swedish Tajik Tamil Telugu Thai Turkish Ukrainian Urdu Uzbek Vietnamese Welsh Xhosa Yiddish Yoruba Zulu
Afrikaans Albanian Amharic Arabic Armenian Azerbaijani Basque Belarusian Bengali Bosnian Bulgarian Catalan Cebuano Chichewa Chinese (Simplified) Chinese (Traditional) Corsican Croatian Czech Danish Dutch English Esperanto Estonian Filipino Finnish French Frisian Galician Georgian German Greek Gujarati Haitian Creole Hausa Hawaiian Hebrew Hindi Hmong Hungarian Icelandic Igbo Indonesian Irish Italian Japanese Javanese Kannada Kazakh Khmer Korean Kurdish Kyrgyz Lao Latin Latvian Lithuanian Luxembourgish Macedonian Malagasy Malay Malayalam Maltese Maori Marathi Mongolian Myanmar (Burmese) Nepali Norwegian Pashto Persian Polish Portuguese Punjabi Romanian Russian Samoan Scots Gaelic Serbian Sesotho Shona Sindhi Sinhala Slovak Slovenian Somali Spanish Sundanese Swahili Swedish Tajik Tamil Telugu Thai Turkish Ukrainian Urdu Uzbek Vietnamese Welsh Xhosa Yiddish Yoruba Zulu
Text-to-speech function is limited to 200 characters