Publications
For a complete and up-to-date list of my publications, please see my Google Scholar.
Efficient Model Adaptation
Alfa: Attentive Low-Rank Filter Adaptation for Structure-Aware Cross-Domain Personalized Gaze Estimation
Alfa adapts gaze models to new users and domains with only a few unlabeled samples by reweighting useful spatial patterns already learned in pre-trained filters. The same low-rank adaptation idea also extends to diffusion-based language models for reasoning tasks.
DFT Gaze: Distilled and Fine-Tuned Gaze Estimation for Personalization on Tiny Devices
DFT Gaze combines distillation and fine-tuning into one solution to train a tiny 281K-parameter model for accurate personalized gaze estimation on resource-constrained devices.
Efficient AI Deployment
Generative AI
Computer Vision
One-Shot Action Detection via Attention Zooming In
This work localizes unseen actions in long videos from only one support image by using attention zooming to progressively refine action proposals.
Aggregating Bilateral Attention for Few-Shot Instance Localization
ABA improves few-shot instance localization by aggregating query-support attention, helping models find unseen actions and objects with only a few examples.
Contextual Proposal Network for Action Localization
CPN generates high-quality temporal action proposals by modeling multi-scale temporal context and boundary cues in long untrimmed videos.
Temporal Action Proposal Generation via Deep Feature Enhancement
This work improves temporal action proposal generation by enhancing video segment features and expanding multi-granularity proposal representations.
Notes
* Equal contribution.
More publications are available on my Google Scholar.