Photos | Collaborating on the Screen
Hubert Wu and Park Hoon-jung discuss their project at DEFCON 18 while surrounded by a crowd of tech enthusiasts.
BLIP-2 Description:
a group of men sitting at a table with a laptopChronologically Adjacent
Note: You can also navigate with your arrow keys or swiping.
Metadata
Capture date:
Original Dimensions:
5616w x 3744h - (download 4k)
Usage
Dominant Color:
machine room cap furniture desk photos/defcon laptop student consumer part child teen summer pc indoors accessories bag jung baseball baseball hat jewelry workshop dc chair glasses building cafeteria hubert wu architecture crowd park backpack mark wa audience classroom manufacturing table canon boy eos restaurant computer handbag school factory headgear hat defcon ii hoon july electronics necklace
iso
1600
metering mode
5
aperture
f/2.8
focal length
70mm
shutter speed
1/100s
camera make
Canon
camera model
lens model
date
2010-07-30T18:17:06.850000-07:00
tzoffset
-25200
tzname
America/Los_Angeles
overall
(57.96%)
curation
(50.00%)
highlight visibility
(4.51%)
behavioral
(90.72%)
failure
(-0.12%)
harmonious color
(-0.77%)
immersiveness
(0.07%)
interaction
(1.00%)
interesting subject
(50.05%)
intrusive object presence
(-18.26%)
lively color
(12.43%)
low light
(11.50%)
noise
(-2.20%)
pleasant camera tilt
(1.90%)
pleasant composition
(-24.68%)
pleasant lighting
(12.10%)
pleasant pattern
(2.54%)
pleasant perspective
(3.64%)
pleasant post processing
(1.60%)
pleasant reflection
(-0.49%)
pleasant symmetry
(0.10%)
sharply focused subject
(11.04%)
tastefully blurred
(64.21%)
well chosen subject
(-30.37%)
well framed subject
(42.58%)
well timed shot
(15.38%)
all
(6.51%)
* NOTE: Amazon Rekognition
detected a celebrity in this image using the
Celebrity Recognition API. The API isn't perfect, but it does give you the MatchConfidence which I display
next to the celebrity's name along with links _↗ to their info.
* WARNING: The title and caption of this image were generated by an AI LLM (gpt-3.5-turbo-0301
from
OpenAI)
based on a
BLIP-2 image-to-text labeling, tags,
location,
people
and album metadata from the image and are
potentially inaccurate, often hilariously so. If you'd like me to adjust anything,
just reach out.