Introducing WISE: Semantic search for Commons (we’d love your feedback)

Vasanth Gopa via WikimediaIndia-l <wikimediaindia-l-RusutVdil2icGmH+5r0DM0B+6BGkLq7r@public.gmane.org> Sun, 3 May 2026 02:09:00 +0200
Newsgroups gmane.org.wikimedia.india,gmane.science.linguistics.wikipedia.technical,gmane.org.wikimedia.foundation,gmane.org.wikimedia.wikidata
Message-ID <CA+GrJMvWbBqbMWSmwUvqqUUVG9BOQRhdcm0rRU6iHRph9b3=Gw@mail.gmail.com>
--===============2102623664736606624==
Content-Type: multipart/alternative; boundary="0000000000001f46330650dea1b2"

--0000000000001f46330650dea1b2
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable

Hello everyone,

We would love to get your feedback on a tool we have been working on:
https://wise.wmcloud.org/

This is a search tool for images and videos on wikimedia. Currently is
searching only on media of the day (approximately 5000 videos). It searches
only the visual content of the file (not on metadata, filename, or
structured data). It also does face detection and recognition.

Please give it a go. Here's some examples:

*Semantic example queries:*
"man at a train station"
"=E0=A4=8F=E0=A4=95 =E0=A4=B5=E0=A5=8D=E0=A4=AF=E0=A4=95=E0=A5=8D=E0=A4=A4=
=E0=A4=BF =E0=A4=B0=E0=A5=87=E0=A4=B2=E0=A4=B5=E0=A5=87 =E0=A4=B8=E0=A5=8D=
=E0=A4=9F=E0=A5=87=E0=A4=B6=E0=A4=A8 =E0=A4=AA=E0=A4=B0" (Hindi)
"horse in an airplane"
"=E0=B0=B5=E0=B0=BF=E0=B0=AE=E0=B0=BE=E0=B0=A8=E0=B0=82=E0=B0=B2=E0=B1=8B =
=E0=B0=97=E0=B1=81=E0=B0=B0=E0=B1=8D=E0=B0=B0=E0=B0=82" (Telugu)
"man with a flower"
"pirate with a pistol"

*Face search (select "Faces"):*

Click the green "Image" button and paste an image URL

Example inputs:
* https://upload.wikimedia.org/wikipedia/commons/0/00/Charlie_Chaplin.jpg
*
https://upload.wikimedia.org/wikipedia/commons/0/0d/Neil_Armstrong_pose.jpg

[warning: some videos are ogv videos and your brownser may not play them,
so watch them on Commons, i.e., after clicking the search result, scroll
down to the media metadata table, and follow the link to commons]

*Key features include:*

* Semantic search using natural language to find relevant images on Commons
from the visual content only (not the structured data or description, only
the image itself)
* Face search: upload or paste a face image, and the tool will try to
identify and locate that person across images and videos, including
timestamps where they appear
* Audio search: search within audio files to find relevant segments
* Multilingual search: supports queries in multiple languages

We are actively improving the tool and would really appreciate any
feedback, suggestions, or ideas from the community. Here's some more
immediate future plans:

* Search on all wikimedia images (instead of only videos / media of the day=
)
* Show similar images when uploading an image to suggest filenames,
categories, and other relevant metadata

More technical details and a place to share feedback at
https://commons.wikimedia.org/wiki/Commons:Wise
* Phabricator: https://phabricator.wikimedia.org/T424092
* Announcement on Village pump:
https://commons.wikimedia.org/wiki/Commons:Village_pump#Introducing_WISE%3A=
_Semantic_search_for_Commons_%28we%E2%80%99d_love_your_feedback%29
Regards,

Gopa Vasanth <https://gopavasanth.github.io/>
Twitter <https://twitter.com/gopavasanth1999> | LinkedIn
<https://www.linkedin.com/in/gopa-vasanth/> | GitHub
<https://github.com/gopavasanth> | Gerrit
<https://gerrit.wikimedia.org/r/#/q/gopavasanth>

=E2=80=9CYesterday is not ours to recover, but tomorrow is ours to win or l=
ose.=E2=80=9D

--0000000000001f46330650dea1b2
Content-Type: text/html; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable

<div dir=3D"ltr"><div><div><p>Hello everyone,<br><br>We would love to get y=
our feedback on a tool we have been working on:=C2=A0<a href=3D"https://wis=
e.wmcloud.org/" target=3D"_blank">https://wise.wmcloud.org/</a><br>=C2=A0 =
=C2=A0<br>This is a search tool for images and videos on wikimedia. Current=
ly is searching only on media of the day (approximately 5000 videos). It se=
arches only the visual content of the file (not on metadata, filename, or s=
tructured data). It also does face detection and recognition.<br><br>Please=
 give it a go. Here&#39;s some examples:=C2=A0<br><br><b>Semantic example q=
ueries:</b><br></p>&quot;man at a train station&quot;<br>&quot;=E0=A4=8F=E0=
=A4=95 =E0=A4=B5=E0=A5=8D=E0=A4=AF=E0=A4=95=E0=A5=8D=E0=A4=A4=E0=A4=BF =E0=
=A4=B0=E0=A5=87=E0=A4=B2=E0=A4=B5=E0=A5=87 =E0=A4=B8=E0=A5=8D=E0=A4=9F=E0=
=A5=87=E0=A4=B6=E0=A4=A8 =E0=A4=AA=E0=A4=B0&quot; (Hindi)<br>&quot;horse in=
 an airplane&quot;<br>&quot;=E0=B0=B5=E0=B0=BF=E0=B0=AE=E0=B0=BE=E0=B0=A8=
=E0=B0=82=E0=B0=B2=E0=B1=8B =E0=B0=97=E0=B1=81=E0=B0=B0=E0=B1=8D=E0=B0=B0=
=E0=B0=82&quot; (Telugu)<br>&quot;man with a flower&quot;<br>&quot;pirate w=
ith a pistol&quot;<br><p><b>Face search (select &quot;Faces&quot;):</b><br>=
<br>Click the green &quot;Image&quot; button and paste an image URL</p><p>E=
xample inputs:<br>*=C2=A0<a href=3D"https://upload.wikimedia.org/wikipedia/=
commons/0/00/Charlie_Chaplin.jpg" target=3D"_blank">https://upload.wikimedi=
a.org/wikipedia/commons/0/00/Charlie_Chaplin.jpg</a><br>*=C2=A0<a href=3D"h=
ttps://upload.wikimedia.org/wikipedia/commons/0/0d/Neil_Armstrong_pose.jpg"=
 target=3D"_blank">https://upload.wikimedia.org/wikipedia/commons/0/0d/Neil=
_Armstrong_pose.jpg</a></p><p>[warning: some videos are ogv videos and your=
 brownser may not play them, so watch them on Commons, i.e., after clicking=
 the search result, scroll down to the media metadata table, and follow the=
 link to commons]</p><p><b>Key features include:</b><br><br>* Semantic sear=
ch using natural language to find relevant images on Commons from the visua=
l content only (not the structured data or description, only the image itse=
lf)<br>* Face search: upload or paste a face image, and the tool will try t=
o identify and locate that person across images and videos, including times=
tamps where they appear<br>* Audio search: search within audio files to fin=
d relevant segments<br>* Multilingual search: supports queries in multiple =
languages<br><br>We are actively improving the tool and would really apprec=
iate any feedback, suggestions, or ideas from the community. Here&#39;s som=
e more immediate future plans:<br><br>* Search on all wikimedia images (ins=
tead of only videos / media of the day)<br>* Show similar images when uploa=
ding an image to suggest filenames, categories, and other relevant metadata=
<span style=3D"box-sizing:border-box;margin:0px;padding:3px 0px 4px;backgro=
und-color:rgb(227,255,199);color:rgb(72,83,101)"><br></span><span style=3D"=
box-sizing:border-box;margin:0px;padding:3px 0px 4px;background-color:rgb(2=
27,255,199);color:rgb(72,83,101)"></span></p><p>More technical details and =
a place to share feedback at=C2=A0<a href=3D"https://commons.wikimedia.org/=
wiki/Commons:Wise" target=3D"_blank">https://commons.wikimedia.org/wiki/Com=
mons:Wise</a><br>* Phabricator:=C2=A0<a href=3D"https://phabricator.wikimed=
ia.org/T424092" target=3D"_blank">https://phabricator.wikimedia.org/T424092=
</a><br>* Announcement on Village pump:=C2=A0<a href=3D"https://commons.wik=
imedia.org/wiki/Commons:Village_pump#Introducing_WISE%3A_Semantic_search_fo=
r_Commons_%28we%E2%80%99d_love_your_feedback%29" target=3D"_blank">https://=
commons.wikimedia.org/wiki/Commons:Village_pump#Introducing_WISE%3A_Semanti=
c_search_for_Commons_%28we%E2%80%99d_love_your_feedback%29</a></p></div></d=
iv><div dir=3D"ltr" class=3D"gmail_signature" data-smartmail=3D"gmail_signa=
ture"><div dir=3D"ltr"><div><div dir=3D"ltr"><div><div dir=3D"ltr"><div><di=
v dir=3D"ltr"><div><div dir=3D"ltr"><div><div dir=3D"ltr"><div dir=3D"ltr">=
<div dir=3D"ltr"><div dir=3D"ltr"><div dir=3D"ltr"><div dir=3D"ltr"><div di=
r=3D"ltr"><div dir=3D"ltr"><div dir=3D"ltr"><div dir=3D"ltr"><div dir=3D"lt=
r"><div dir=3D"ltr"><div dir=3D"ltr"><div dir=3D"ltr"><div dir=3D"ltr"><div=
 dir=3D"ltr"><div dir=3D"ltr"><div dir=3D"ltr"><div dir=3D"ltr"><div dir=3D=
"ltr"><div dir=3D"ltr"><b><span style=3D"background-color:rgb(0,0,0)"></spa=
n></b>Regards,<br><br><a href=3D"https://gopavasanth.github.io/" target=3D"=
_blank">Gopa Vasanth</a></div><div><span style=3D"font-size:12.8px"><a href=
=3D"https://twitter.com/gopavasanth1999" target=3D"_blank">Twitter</a> |=C2=
=A0</span><span style=3D"font-size:12.8px"><a href=3D"https://www.linkedin.=
com/in/gopa-vasanth/" target=3D"_blank">LinkedIn</a> |</span><a href=3D"htt=
ps://github.com/gopavasanth" target=3D"_blank"> GitHub</a>=C2=A0| <a href=
=3D"https://gerrit.wikimedia.org/r/#/q/gopavasanth" target=3D"_blank">Gerri=
t</a>=C2=A0<br><br></div><div style=3D"text-align:left"><blockquote style=
=3D"margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding=
-left:1ex"><div><span style=3D"font-family:monospace,monospace">=E2=80=9C<f=
ont size=3D"2">Yesterday is not ours to recover, but tomorrow is ours to wi=
n or lose.=E2=80=9D</font></span><b><br></b></div></blockquote></div></div>=
</div></div></div></div></div></div></div></div></div></div></div></div></d=
iv></div></div></div></div></div></div></div></div></div></div></div></div>=
</div></div></div></div></div></div>

--0000000000001f46330650dea1b2--

--===============2102623664736606624==
Content-Type: text/plain; charset="us-ascii"
MIME-Version: 1.0
Content-Transfer-Encoding: 7bit
Content-Disposition: inline

_______________________________________________
WikimediaIndia-l mailing list -- wikimediaindia-l-RusutVdil2icGmH+5r0DM0B+6BGkLq7r@public.gmane.org
To unsubscribe send an email to wikimediaindia-l-leave-RusutVdil2icGmH+5r0DM0B+6BGkLq7r@public.gmane.org
To unsubscribe from the list / change mailing preferences visit https://lists.wikimedia.org/postorius/lists/wikimediaindia-l.lists.wikimedia.org/
--===============2102623664736606624==--