Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
jazzyjackson
36 days ago
|
parent
|
context
|
favorite
| on:
Qwen3-VL can scan two-hour videos and pinpoint nea...
Could you combine it with a classic OCR segmentation process, so that along with the image you also provide box coordinates of each string?
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
