Mamshad Nayeem Rizve

Applied Scientist @adobe

[VidLLMs CVPR2026 @vidllms]

VideoLLMs are one of the fastest growing areas in computer vision

Presented at the ongoing VideoLLMs workshop at CVPR

Venue: Karl Dean Ballroom A1

[VidLLMs CVPR2026 @vidllms]

Remarks from our chair Prof @ucfmshah kicking off the VideoLLMs workshop @CVPR

#CVPR #CVPR2025 #ComputerVision #AI

[Shashank @shawshank_v]

DoRA received the 'Outstanding paper honorable mentions' at #ICLR24 🥳

Thank you to the a̵c̵a̵d̵e̵m̵y ICLR committee for this honor. Finally, I can have an award section on my resume 😜

Thanks to the super fun & amazing researchers @MamshadR @y_m_asano @joaocarreira @1avr1e

[Astitva Srivastava @sarcastitva]

Computer Vision conference's acceptance criteria these days:
#CVPR2024 #eccc2024 #AI #ComputerVision

[Alex McMillan @UndeniablyAlex]

Yankee Candle's Stages of Abstraction

Level 1: The scent represents a physical object where the object's aroma is one of its distinct properties.

[Shashank @shawshank_v]

Really happy to share that DoRA is accepted as an Oral to @iclr_conf #ICLR2024

Using just “1 video” from our new egocentric dataset - Walking Tours, we develop a new method that outperforms DINO pretrained on ImageNet on image and video downstream tasks.

More details in 🧵👇

[Shashank @shawshank_v]

Hi everyone,
I am graduating early next year with a PhD from @Inria in AI. I am looking for an industrial research position and would appreciate your support.
Thank you in advance for any connections, advice, or opportunities you can offer.

My profile: https://t.co/WJSSeDTQ9R

[Mamshad Nayeem Rizve @MamshadR]

@CopySutra 33 . Use the edit icon to pi km. in, ADD eeee or delete clips. r my kiko na ok k

[Mamshad Nayeem Rizve @MamshadR]

@CopySutra . MMO ln,. 7m.. .. in my I'm c 8 lmmfao I.

[AI Breakdown @agi_breakdown]

🎙️In this episode we discuss the paper PivoTAL: Prior-Driven Supervision for Weakly-Supervised Temporal Action Localization by @MamshadR @mitts1910 Ye Yu, Matthew Hall, Sandra Sajeev, @ucfmshah, Mei Chen. untrimmed videos +video-only supervision #CVPR2023 https://t.co/lziVFrydKa

[Gaurav @mitts1910]

Happy to share that my group, Responsible and Open AI Research (ROAR) at @Microsoft, got 2/3 papers accepted at @CVPR 2023! 🥳🥳🎉🎊

It was a terrific experience driving two papers 😅 Kudos to @Lannnn_w and @MamshadR for making it feel like a walk in the park! 🤩 #CVPR2023

[Lucas Beyer (bl16) @giffmana]

I have never felt this seen

[Gautam Kamath @thegautamkamath]

Zico Kolter (@zicokolter) with the other keynote "Robustness in Machine Learning: A Five-Year Retrospective." Really disappointed to have missed this one at the conference, can't wait to check out the recording!
https://t.co/7ThqQO1oke 2/4

[Jeff Dean @JeffDean]

Excited to share the first of a series of @GoogleAI blog posts summarizing our research work from 2022. This covers language & multimodal models, computer vision, and generative models. We'll have ~7 posts covering other areas over next few weeks!

https://t.co/WuHSZ6qKKu

[Ethan Caballero @ethanCaballero]

new fan-made NeurIPS 2022 trailer:

[Mubarak Shah @ucfmshah]

Happy to share our #ECCV2022 paper "Towards Realistic Semi-Supervised Learning".

We introduce class-distribution-aware pseudo-labeling to simultaneously classify the samples from both known and unknown classes.

🚩 Arxiv: https://t.co/JAhapalApJ. Code coming soon. (1/n)

[Mubarak Shah @ucfmshah]

#ECCV2022 paper OpenLDN: Learning to Discover Novel Classes for Open-World Semi-Supervised Learning
🚩 Arxiv: https://t.co/PwLiLIqhzy.
We propose a bi-level optimization rule to exploit information available in the labeled set, without relying on self-supervised pretraining,

[PHD Comics @PHDcomics]

Finding a new article be like

[arXiv Daily @Arxiv_Daily]

UNICON: Combating Label Noise Through Uniform Selection and Contrastive Learning
https://t.co/3qGEo7IhBV
by @nazmul170 et al. including @MamshadR
#Hyperparameter #DeepLearning

[Delip Rao @deliprao]

We might know about this from recent GNN and geometric learning papers, but it first appeared in ML in the “On Manifold Regularization” paper by Belkin, Niyogi, and Sindhwani. That paper was a milestone in semisupervised learning but now forgotten. https://t.co/pl7WsD5P3O