5 citations · 13 across the 15 of their papers we have counts for
15 papers
GraphPad: Inference-Time 3D Scene Graph Updates for Embodied Question Answering
Muhammad Qasim Ali, Saeejith Nair, Alexander Wong +2
Structured scene representations are a core component of embodied agents, helping to consolidate raw sensory streams into readable, modular, and searchable formats. Due to their hi…
MetaFood3D: 3D Food Dataset with Nutrition Values
Yuhao Chen, Jiangpeng He, Gautham Vinod +11
Food computing is both important and challenging in computer vision (CV). It significantly contributes to the development of CV algorithms due to its frequent presence in datasets…
NutritionVerse-Real: An Open Access Manually Collected 2D Food Scene Dataset for Dietary Intake Estimation
Chi-en Amy Tai, Saeejith Nair, Olivia Markham +4
Dietary intake estimation plays a crucial role in understanding the nutritional habits of individuals and populations, aiding in the prevention and management of diet-related healt…
NutritionVerse-Synth: An Open Access Synthetically Generated 2D Food Scene Dataset for Dietary Intake Estimation
Saeejith Nair, Chi-en Amy Tai, Yuhao Chen +1
Manually tracking nutritional intake via food diaries is error-prone and burdensome. Automated computer vision techniques show promise for dietary monitoring but require large and…
DARLEI: Deep Accelerated Reinforcement Learning with Evolutionary Intelligence
Saeejith Nair, Mohammad Javad Shafiee, Alexander Wong
We present DARLEI, a framework that combines evolutionary algorithms with parallelized reinforcement learning for efficiently training and evolving populations of UNIMAL agents. Ou…
NAS-NeRF: Generative Neural Architecture Search for Neural Radiance Fields
Saeejith Nair, Yuhao Chen, Mohammad Javad Shafiee +1
Neural radiance fields (NeRFs) enable high-quality novel view synthesis, but their high computational complexity limits deployability. While existing neural-based solutions strive…
NutritionVerse: Empirical Study of Various Dietary Intake Estimation Approaches
Chi-en Amy Tai, Matthew Keller, Saeejith Nair +8
Accurate dietary intake estimation is critical for informing policies and programs to support healthy eating, as malnutrition has been directly linked to decreased quality of life.…
TurboViT: Generating Fast Vision Transformers via Generative Architecture Search
Alexander Wong, Saad Abbasi, Saeejith Nair
Vision transformers have shown unprecedented levels of performance in tackling various visual perception tasks in recent years. However, the architectural and computational complex…
Fast GraspNeXt: A Fast Self-Attention Neural Network Architecture for Multi-task Learning in Computer Vision Tasks for Robotic Grasping on the Edge
Alexander Wong, Yifan Wu, Saad Abbasi +3
Multi-task learning has shown considerable promise for improving the performance of deep learning-driven vision systems for the purpose of robotic grasping. However, high architect…
NutritionVerse-Thin: An Optimized Strategy for Enabling Improved Rendering of 3D Thin Food Models
Chi-en Amy Tai, Jason Li, Sriram Kumar +4
With the growth in capabilities of generative models, there has been growing interest in using photo-realistic renders of common 3D food items to improve downstream tasks such as f…
NutritionVerse-3D: A 3D Food Model Dataset for Nutritional Intake Estimation
Chi-en Amy Tai, Matthew Keller, Mattie Kerrigan +4
77% of adults over 50 want to age in place today, presenting a major challenge to ensuring adequate nutritional intake. It has been reported that one in four older adults that are…
PCBDet: An Efficient Deep Neural Network Object Detection Architecture for Automatic PCB Component Detection on the Edge
Brian Li, Steven Palayew, Francis Li +3
There can be numerous electronic components on a given PCB, making the task of visual inspection to detect defects very time-consuming and prone to error, especially at scale. Ther…
Faster Attention Is What You Need: A Fast Self-Attention Neural Network Backbone Architecture for the Edge via Double-Condensing Attention Condensers
Alexander Wong, Mohammad Javad Shafiee, Saad Abbasi +2
With the growing adoption of deep learning for on-device TinyML applications, there has been an ever-increasing demand for efficient neural network backbones optimized for the edge…
MAPLE-Edge: A Runtime Latency Predictor for Edge Devices
Saeejith Nair, Saad Abbasi, Alexander Wong +1
Neural Architecture Search (NAS) has enabled automatic discovery of more efficient neural network architectures, especially for mobile and embedded vision applications. Although re…
CellDefectNet: A Machine-designed Attention Condenser Network for Electroluminescence-based Photovoltaic Cell Defect Inspection
Carol Xu, Mahmoud Famouri, Gautam Bathla +3
Photovoltaic cells are electronic devices that convert light energy to electricity, forming the backbone of solar energy harvesting systems. An essential step in the manufacturing…