Soumik Mukhopadhyay (@soumikkanad) 's Twitter Profile
Soumik Mukhopadhyay

@soumikkanad

nothing much to say about myself.....

ID: 212424951

calendar_today06-11-2010 01:30:48

129 Tweet

51 Takipçi

53 Takip Edilen

Soumik Mukhopadhyay (@soumikkanad) 's Twitter Profile Photo

We have made the inference code and model public for #Diff2Lip. Code: github.com/soumik-kanad/d… Paper: openaccess.thecvf.com/content/WACV20…

Soumik Mukhopadhyay (@soumikkanad) 's Twitter Profile Photo

Does anybody know why VS Visual Studio Code uses so much RAM on remote servers? Closing local VSC doesn't kill remote node jobs created by it at times. Crashes our submission node when a lot of users use VSC. Using Copilot makes it 2x worse. Anybody know how to solve this at a cluster level?

Soumik Mukhopadhyay (@soumikkanad) 's Twitter Profile Photo

Finally faced racism, after 3.5 years in US. Man opposite me on the bus,not looking at me (with no one around) said "..SAT..something..","bunch of liars","must've stolen my car", "go to your sorry-a** school,couldn't get into a better school", "go f**k a dog". I just smiled. 🙂

Chuong M. Huynh (@ryanhuynh1108) 's Twitter Profile Photo

I am heading to Seattle to attend #CVPR2024 in the next week. Let's check our two posters, "MaGGIe: Masked Guided Gradual Human Instance Matting" is June 19th 10.30AM #358 and "Composing Object Relations and Attributes for Image-Text Matching" is June 20th 10.30AM #455

I am heading to Seattle to attend #CVPR2024 in the next week. Let's check our two posters, "MaGGIe: Masked Guided Gradual Human Instance Matting" is June 19th 10.30AM #358 and  
 "Composing Object Relations and Attributes for Image-Text Matching" is June 20th 10.30AM  #455
Namitha Padmanabhan (@namithap10) 's Twitter Profile Photo

I will be speaking about my work in INRs (namithap10.github.io/xinc/) at the INRV workshop at #CVPR2024. Come see me in Summit 335-336 at 5PM on Tuesday!

Soumik Mukhopadhyay (@soumikkanad) 's Twitter Profile Photo

Unconditional #diffusion pretraining learns discriminative representation; hence are great candidates for Unified Models for #GenAI as well as #recognition. Please join us at our #DiffSSL poster (#101) at #ECCV on 1 Oct 1030AM. European Conference on Computer Vision #ECCV2026

Unconditional #diffusion pretraining learns discriminative representation; hence are great candidates for Unified Models for #GenAI as well as #recognition.
Please join us at our #DiffSSL poster (#101) at #ECCV on 1 Oct 1030AM.
<a href="/eccvconf/">European Conference on Computer Vision #ECCV2026</a>
Mara Levy (@mlevy1221) 's Twitter Profile Photo

How can we make Imitation Leaning generalize? In my latest work we show that a key point based representation can generalize to novel instances of an object and is agnostic to background changes.