Nirat Saini

Waymonaut | PhD @ UMD; Computer vision and Machine Learning

[Nirat Saini @saini_nirat]

🍎 Imagine chopping an apple: each slice, a new shape, a new stats. Now, imagine teaching a computer to recognize each slice & even predict the next! 🤖 How can AI understand the subtle changes from a whole apple to a sliced one, and apply this knowledge universally? 🤔

[UMD Center for Machine Learning @ml_umd]

Researchers @umiacs are teaching computers how to recognize and imagine fruits and vegetables in various forms—even as they’re being peeled, sliced or chopped into pieces.

Their work to advance generative AI will be presented at #ICCV2023.

Learn more: https://t.co/OLbOiQAb9Z

[Nirat Saini @saini_nirat]

Had such a blast organizing WiCV@ECCV24 with such an amazing cohort!
Over the years, I’ve always made meaningful connections and memories with lots of women researchers in CV, I am grateful I was able to be part of creating such experience for others!🙏🏻

@WiCVworkshop @eccvconf

[WiCV @WiCVworkshop]

🌟 Workshop Starting at 2 PM! 🌟

Join #WiCV at @eccvconf in the Panorama Lounge (6th floor). Take the elevator at the end of the workshop hall (above the lunch area) to reach us!

Program: https://t.co/AWTk18jXqf

See you soon! 🇮🇹 #ECCV2024 #Mentorship #Networking #WomenInCV

[WiCV @WiCVworkshop]

Next: Stella X. Yu, a distinguished professor in EECS department at the University of Michigan. She is talking about Unscripted Grounded Visual Learning.

[WiCV @WiCVworkshop]

Fatma Güney @ftm_guney is an Assistant Professor at Koc University in Istanbul. She is presenting her work on "Advancing Perception for Autonomous Driving"

[Hilde Kuehne @HildeKuehne]

Great talk by @dimadamen at the @WiCVworkshop @eccvconf ! Super nice spot and only a few seats left. Drop by if you find us. 🤓

[WiCV @WiCVworkshop]

Dima Damen (@dimadamen) is with us for the first keynote, a Professor in CV at the University of Bristol and Senior Research Scientist at Google DeepMind. Today she is giving a talk on Long-Form **Egocentric** Video Understanding. 🇮🇹 #ECCV2024

[WiCV @WiCVworkshop]

🪗The submission deadline has been extended to July 18th anywhere on earth! 🪗

[Nirat Saini @saini_nirat]

@__JAAF__ Maybe this model needs to Chop & Learn 🔪🍊https://t.co/UFhaOyrb1O: a dataset for chopping fruits and veggies 🍎🍉🍐🥕🥒🥦 #genai

[Nirat Saini @saini_nirat]

Excited to present my work at #CVPR on Open Vocabulary Compositional Learning at 10:30am PT, Arch 4E, Poster #465.

Come say hi if you want to know more about Compositional Learning for Visual Understanding!

[WiCV @WiCVworkshop]

📯Call for Reviewers 📯
We're seeking volunteers from academia or industry eager to help review submissions for the Women in Computer Vision Workshop at @eccvconf 2024 Milan 🇮🇹 #ECCV2024

Self-nomination form: https://t.co/g2xsVA4Fl8

[Dima Damen @dimadamen]

A shout-out to an afternoon session (from 2:30pm) poster Nord25
Chop & Learn: Recognizing and Generating Object-State Compositions
Thanks @saini_nirat for taking the time this morning to tell me more about your work!
work led by @abhi2610

[Nirat Saini @saini_nirat]

Happy to discuss more about our work today around 2:30pm-4:30pm, Poster #25 at Room Nord. @ICCVConference

[Nirat Saini @saini_nirat]

🍎 Imagine chopping an apple: each slice, a new shape, a new stats. Now, imagine teaching a computer to recognize each slice & even predict the next! 🤖 How can AI understand the subtle changes from a whole apple to a sliced one, and apply this knowledge universally? 🤔

[Kamal Gupta @kamalgupta09]

Compositional Generalization is going to be the next big milestone in #GenAI and we need better datasets and benchmarks to make progress.

Checkout our work Chop-N-Learn at #ICCV2023!
https://t.co/5jcm0lXnqY

[Nirat Saini @saini_nirat]

To know more, visit Poster #25 on Friday Oct 6, 2:30pm Poster Session at Paris Nord at #ICCV2023.

Website: https://t.co/UFhaOyrb1O

Joint effort by an awesome team @hywang66, @TweetsArchana, @kamalgupta09, @Bob99170040, @vinojjayand and @abhi2610.

[Nirat Saini @saini_nirat]

🍎 Imagine chopping an apple: each slice, a new shape, a new stats. Now, imagine teaching a computer to recognize each slice & even predict the next! 🤖 How can AI understand the subtle changes from a whole apple to a sliced one, and apply this knowledge universally? 🤔

[UMD Center for Machine Learning @ml_umd]

Researchers @umiacs are teaching computers how to recognize and imagine fruits and vegetables in various forms—even as they’re being peeled, sliced or chopped into pieces.

Their work to advance generative AI will be presented at #ICCV2023.

Learn more: https://t.co/OLbOiQAb9Z

[Nirat Saini @saini_nirat]

🛠️ Beyond these tasks, Chop N Learn opens doors to various applications in image & video domains, focusing on recognizing & generating unseen object-state compositions.

[AI Bites | YouTube Channel @ai_bites]

Chop and learn studies the task of cutting objects in different styles and the resulting object state changes. We propose a new benchmark suite Chop & Learn, to accommodate the needs of learning objects and different cut styles using multiple viewpoints.

Paper: Chop & Learn: Recognizing and Generating Object-State Compositions by @saini_nirat Hanyu Wang and team from @UofMaryland
Link: https://t.co/7u9JIjkteS
Project: https://t.co/O1GpPV2bbf

#vision #GenerativeAI #deeplearning

[Nirat Saini @saini_nirat]

Project Page: https://t.co/4WIXrCYTIX

Paper: https://t.co/4SuRJtllrx

[Nirat Saini @saini_nirat]

Excited to present our work “Disentangling Visual Embeddings for Attributes and Objects” at #CVPR2022 today.
Our talk is at Great Hall A-D (1:30-3pm), followed by Poster 35b in the afternoon session. Drop by to discuss more about this work with @pvkhoi @abhi2610