5 citations · 20 across the 11 of their papers we have counts for
5 papers · 1 filter
Pretrained Encoders are All You Need
Mina Khan, P Srivatsa, Advait Rane +4
Data-efficiency and generalization are key challenges in deep learning and deep reinforcement learning as many models are trained on large-scale, domain-specific, and expensive-to-…
Personalizing Pre-trained Models
Mina Khan, P Srivatsa, Advait Rane +3
Self-supervised or weakly supervised models trained on large-scale datasets have shown sample-efficient transfer to diverse datasets in few-shot settings. We consider how upstream…
Txt2Vid: Ultra-Low Bitrate Compression of Talking-Head Videos via Text
Pulkit Tandon, Shubham Chandak, Pat Pataranutaporn +5
Video represents the majority of internet traffic today, driving a continual race between the generation of higher quality content, transmission of larger file sizes, and the devel…
PAL: Intelligence Augmentation using Egocentric Visual Context Detection
Mina Khan, Pattie Maes
Egocentric visual context detection can support intelligence augmentation applications. We created a wearable system, called PAL, for wearable, personalized, and privacy-preserving…
Uncertainty-Aware Boosted Ensembling in Multi-Modal Settings
Utkarsh Sarawgi, Rishab Khincha, Wazeer Zulfikar +2
Reliability of machine learning (ML) systems is crucial in safety-critical applications such as healthcare, and uncertainty estimation is a widely researched method to highlight th…