Related papers: Visual Wake Words Dataset
The deployment of Quantized Neural Networks (QNNs) on resource-constrained edge devices, such as microcontrollers (MCUs), introduces fundamental challenges in balancing model performance, computational complexity, and memory constraints.…
Transfer learning has become an essential tool in modern computer vision, allowing practitioners to leverage backbones, pretrained on large datasets, to train successful models from limited annotated data. Choosing the right backbone is…
When building artificial intelligence systems that can reason and answer questions about visual data, we need diagnostic tests to analyze our progress and discover shortcomings. Existing benchmarks for visual question answering can help,…
Images often communicate more than they literally depict: a set of tools can suggest an occupation and a cultural artifact can suggest a tradition. This kind of indirect visual reference, known as visual metonymy, invites viewers to recover…
With the increasing prevalence of voice-activated devices and applications, keyword spotting (KWS) models enable users to interact with technology hands-free, enhancing convenience and accessibility in various contexts. Deploying KWS models…
Visual Question Answering (VQA) is a recent problem in computer vision and natural language processing that has garnered a large amount of interest from the deep learning, computer vision, and natural language processing communities. In…
Despite weakly supervised object detection (WSOD) being a promising step toward evading strong instance-level annotations, its capability is confined to closed-set categories within a single training dataset. In this paper, we propose a…
A coreset (or core-set) of a dataset is its semantic compression with respect to a set of queries, such that querying the (small) coreset provably yields an approximate answer to querying the original (full) dataset. In the last decade,…
Developing IoT, Data Computing and Cloud Computing software requires different programming skills and different programming languages. This cause a problem for many companies and researchers that need to hires many programmers to develop a…
Modern computer vision algorithms typically require expensive data acquisition and accurate manual labeling. In this work, we instead leverage the recent progress in computer graphics to generate fully labeled, dynamic, and photo-realistic…
The majority of IoT devices like smartwatches, smart plugs, HVAC controllers, etc., are powered by hardware with a constrained specification (low memory, clock speed and processor) which is insufficient to accommodate and execute large,…
Action recognition is a vital task in computer vision, and many methods are developed to push it to the limit. However, current action recognition models have huge computational costs, which cannot be deployed to real-world tasks on mobile…
Visual search is an essential part of almost any everyday human goal-directed interaction with the environment. Nowadays, several algorithms are able to predict gaze positions during simple observation, but few models attempt to simulate…
We present a new public dataset with a focus on simulating robotic vision tasks in everyday indoor environments using real imagery. The dataset includes 20,000+ RGB-D images and 50,000+ 2D bounding boxes of object instances densely captured…
Open Set Object Detection has seen rapid development recently, but it continues to pose significant challenges. Language-based methods, grappling with the substantial modal disparity between textual and visual modalities, require extensive…
Tiny machine learning (TinyML) is a fast-growing research area committed to democratizing deep learning for all-pervasive microcontrollers (MCUs). Challenged by the constraints on power, memory, and computation, TinyML has achieved…
This letter introduces an energy-efficient pull-based data collection framework for Internet of Things (IoT) devices that use Tiny Machine Learning (TinyML) to interpret data queries. A TinyML model is transmitted from the edge server to…
With the of advent rich classification models and high computational power visual recognition systems have found many operational applications. Recognition in the real world poses multiple challenges that are not apparent in controlled lab…
It is a common sense that datasets with high-quality data samples play an important role in artificial intelligence (AI), machine learning (ML) and related studies. However, although AI/ML has been introduced in wireless researches long…
Human Activity Recognition (HAR) has recently received remarkable attention in numerous applications such as assisted living and remote monitoring. Existing solutions based on sensors and vision technologies have obtained achievements but…