In the past several years there has been an explosion of available models for vision-language (VL) tasks. Unfortunately, the literature still leaves open a number of questions related to best practices in designing and training such models. Additiona...
Computer vision models have known performance disparities across attributes such as gender and skin tone. This means during tasks such as classification and detection, model performance differs for certain classes based on the demographics of the peo...
Contributions from the Indian gravity community have played a significant role in shaping several branches of astronomy and astrophysics. This document reviews some of the most important contributions and presents a vision for gravity research in the...
Multimodal Large Language Models (MLLMs) that integrate text and other modalities (especially vision) have achieved unprecedented performance in various multimodal tasks. However, due to the unsolved adversarial robustness problem of vision models, M...
The growth in the aging population requires caregivers to improve both efficiency and quality of healthcare. In this study, we develop an automatic, vision-based system for monitoring and analyzing the physical and mental well-being of senior citizen...
Deep neural networks (DNNs) have recently achieved impressive success across a wide range of real-world vision and language processing tasks, spanning from image classification to many other downstream vision tasks, such as object detection, tracking...
The existing methods for Vision and Language Navigation in the Continuous Environment (VLN-CE) commonly incorporate a waypoint predictor to discretize the environment. This simplifies the navigation actions into a view selection task and improves nav...
Using cloud-based computer vision services is gaining traction, where developers access AI-powered components through familiar RESTful APIs, not needing to orchestrate large training and inference infrastructures or curate/label training datasets. Ho...
Why are state-of-the-art Vision Transformers (ViTs) not designed to exploit natural geometric symmetries such as 90-degree rotations and reflections? In this paper, we argue that there is no fundamental reason, and what has been missing is an efficie...
Converge Vision, separately marketed as Sky TV (for Metro Manila) and Converge FiberTV (for select areas in key provinces), is a digital Internet Protocol
Vision-Language Navigation (VLN) is a critical task for developing embodied agents that can follow natural language instructions to navigate in complex real-world environments. Recent advances in VLN by large pretrained models have significantly impr...
This article presents a vision where \textit{real-time} digital twins of the physical wireless environments are continuously updated using multi-modal sensing data from the distributed infrastructure and user devices, and are used to make communicati...
In deep learning, test-time adaptation has gained attention as a method for model fine-tuning without the need for labeled data. A prime exemplification is the recently proposed test-time prompt tuning for large-scale vision-language models such as C...