VisualAI_UK (@VisualAI_UK) profile picture

Visual AI Program Grant - EPSRC

Joined March 2021
📢 We are seeking 4 Senior Research Associates and 2 Postdoctoral Research Assistants in Computer Vision to join @Oxford_VGG or Biomedical Image Analysis Group, funded by @ERC_Research @EPSRC or Continental AG. Details: 📌 my.corehr.com/pls/uoxrecruit… 📌 my.corehr.com/pls/uoxrecruit…
10
33
Next Thursday I'll teaching computer vision in the #FF21 workshop strand, ably supported by @Oxford_VGG research software engineers.
#FF21 online workshop: "Introduction to visual AI for cultural heritage" Dec. 2 at 16:00 UTC with @ChapBookPro => register: bnf-fr.zoom.us/meeting/regis…
3
2
10
1/4 We'll be presenting our work at @BMVCconf "The Curious Layperson: Fine-Grained Image Recognition without Expert Labels" @subhc4, @irolaina, @chrirupp, Andrea Vedaldi ⏰ Oral: Session 4 Tue 13:00-14:00 UK ⏰ Poster: Session 2 Tue 14:30-15:30 UK 🚩 Page: robots.ox.ac.uk/~vgg/researc…
1
4
18
Excited to present our work at @BMVCconf "Audio-Visual Synchronisation in the Wild" @honglie_Chen, @WeidiXie, @afourast, @NagraniArsha, Andrea Vedaldi and Andrew Zisserman Poster: Session 3, Wed 24th Nov, 16:00-17:00 UK GMT Website: robots.ox.ac.uk/~vgg/researc…
7
21
Congratulations to @subhc4 @irolaina @chrirupp and Andrea Vedaldi on receiving the Best Student Paper Award at @BMVCconf 🎉🎉 Check out the paper: "The Curious Layperson" robots.ox.ac.uk/~vgg/researc…
BEST STUDENT PAPER AWARD The Curious Layperson: Fine-Grained Image Recognition without Expert Labels Subhabrata Choudhury, Iro Laina, Christian Rupprecht and Andrea Vedaldi University of Oxford
7
63
VisualAI_UK retweeted
Check our #BMVC2021 paper "With a little help from my temporal context" Multimodal model w audio/visual input &explicit language model @e_kazakos @huh_jaesung @NagraniArsha arxiv.org/abs/2111.01024 ekazakos.github.io/MTCN-proj… We outperform 3 methods yet to be presented in #Neurips2021
2
8
4
74
Congratulations to @gyunginshin, @WeidiXie and @SamuelAlbanie, who received the best paper award at the ILDAV workshop @ICCV2021 #ICCV2021! Title: “All you need are a few pixels: semantic segmentation with PixelPick” Paper: arxiv.org/pdf/2104.06394.pdf Code: github.com/NoelShin/PixelPic…
2
8
31
Our work Motionformer was accepted as an ORAL at NeurIPS 2021! We present a novel trajectory-focused self-attention block, which essentially tracks space-time patches for video transformers. Work with amazing collaborators @facebookai @Oxford_VGG. Code: facebookresearch.github.io/M…
2
14
3
89
VisualAI_UK retweeted
📖LYON 16ci - A Visually Searchable Database for #Book #Illustrations Printed in #Lyon between 1480 and 1600 (@Biblissima Project "Le Livre Illustré à Lyon 1480-1600") 🔎🔍🔎🔍🔎🔍🔎🔍 🔗 robots.ox.ac.uk/~vgg/researc… @Oxford_VGG
Shout-out from @akpiper for work of @Oxford_VGG on the Image Comparator - robots.ox.ac.uk/~vgg/softwar…, now within the @VisualAI_UK programme
Replying to @_akpiper
.@ChapBookPro doing amazing work on visualizing textual variants, but also asking great questions about "tolerance of variation". How much error can our methods tolerate for historical understanding?
4
8
Terrific new resource for book historians, including @Oxford_VGG visual search software developed under @seebibyte and @VisualAI_UK programmes.
The new Lyon16ci website is online! a collection of 10000 images from the illustrated editions printed in Lyon during the Renaissance. #printedimage #Imagematching #Biblissima #VGG #VeDPH #BML #Oxford #StBenet’sHall #CESR https://nitter.cf/t.co/dB75thxPeA @TramelliBarbara
10
15
The work of @Oxford_VGG in action at @LondonRareBooks - the Image Comparator, first developed under @seebibyte, now for @VisualAI_UK
Featuring in today's "computer vision" sessions by @ChapBookPro: Image Comparator > zeus.robots.ox.ac.uk/imcomp/… > e.g. a 1st and 2nd edition of "Katechismus oder Erklärung der christlichen Lehre zum Gebrauche des Bisthumes #Basel" (both 1796) | #LRBS2021
7
14
VisualAI_UK retweeted
I feel extremely disappointed while reading papers with incomplete literature review. To me, this should be the MOST important thing, as it clearly shows you understand what has been done and what is the remaining challenge and your contribution, instead of over-claiming.
3
1
1
42
Thank you all! The last 7 years at Micron were fantastic. I'll be joining the @VisualAI_UK project which is just across the road in the engineering department, so come visit for a cuppa (after COVID restrictions allow it).
1
5
🥁 Today is the day to submit your paper to #BMVC2021! Hard Deadline: Friday 25 June 23:59 GMT Keep an eye on the time zone 👀 No extensions Good luck authors!
5
1
15
More audiovisual work! "Localizing Visual Sounds the Hard Way" will be presented at #CVPR2021 ⏰ Friday, June 25 6:00 AM – 8:30 AM EDT / 11:00 AM – 1:30 PM BST 🚩 robots.ox.ac.uk/~vgg/researc… by @Honglie_Chen @WeidiXie @afourast @NagraniArsha Andrea Vedaldi and Andrew Zisserman
Check out our CVPR21 paper 'Localizing Visual Sounds the Hard Way' with @WeidiXie, @afourast, @NagraniArsha, Andrea Vedaldi and Andrew Zisserman !
5
19
Congratulations to @e_kazakos, @NagraniArsha, Andrew Zisserman and @dimadamen for winning an Outstanding Paper Award at #ICASSP2021 @ieeeICASSP! Details about the paper can be found here: ekazakos.github.io/auditorys…
Replying to @ieeeICASSP
"Slow-Fast Auditory Streams for Audio Recognition" by Evangelos Kazakos, Arsha Nagrani, Andrew Zisserman, & Dima Damen ieeexplore.ieee.org/document… #ICASSP2021
4
1
28
#CVPR2021 Chalearn Sign Language Workshop: "Sign Segmentation with Changepoint-Modulated Pseudo-Labelling" by Katrin Renz, Nicolaj C. Stache, Neil Fox, @gulvarol, @SamuelAlbanie. arxiv: arxiv.org/abs/2104.13817 github: github.com/RenzKa/sign-segme… website: robots.ox.ac.uk/~vgg/researc…
1
5
15
VisualAI_UK retweeted
WebVid: large scale text-video dataset now available. 2.5mil text-video pairs (10mil coming soon). Pretrain your E2E video-language models. m-bain.github.io/webvid-data… github.com/m-bain/webvid
3
39
2
174