Zobrazeno 1 - 8
of 8
pro vyhledávání: '"Cao, Bryan Bo"'
Visual navigation takes inspiration from humans, who navigate in previously unseen environments using vision without detailed environment maps. Inspired by this, we introduce a novel no-RL, no-graph, no-odometry approach to visual navigation using fe
Externí odkaz:
http://arxiv.org/abs/2411.09893
We propose Few-Class Arena (FCA), as a unified benchmark with focus on testing efficient image classification models for few classes. A wide variety of benchmark datasets with many classes (80-1000) have been created to assist Computer Vision archite
Externí odkaz:
http://arxiv.org/abs/2411.01099
Edge computing has emerged as an alternative to reduce transmission and processing delay and preserve privacy of the video streams. However, the ever-increasing complexity of Deep Neural Networks (DNNs) used in video-based applications (e.g. object d
Externí odkaz:
http://arxiv.org/abs/2410.11233
Publikováno v:
ICPR 2024
Although accuracy and computation benchmarks are widely available to help choose among neural network models, these are usually trained on datasets with many classes, and do not give a good idea of performance for few (< 10) classes. The conventional
Externí odkaz:
http://arxiv.org/abs/2404.05981
Map representation learned by expert demonstrations has shown promising research value. However, recent advancements in the visual navigation field face challenges due to the lack of human datasets in the real world for efficient supervised represent
Externí odkaz:
http://arxiv.org/abs/2402.14281
Visual navigation follows the intuition that humans can navigate without detailed maps. A common approach is interactive exploration while building a topological graph with images at nodes that can be used for planning. Recent variations learn from p
Externí odkaz:
http://arxiv.org/abs/2402.12498
Autor:
Cao, Bryan Bo, Alali, Abrar, Liu, Hansi, Meegan, Nicholas, Gruteser, Marco, Dana, Kristin, Ashok, Ashwin, Jain, Shubham
Tracking subjects in videos is one of the most widely used functions in camera-based IoT applications such as security surveillance, smart city traffic safety enhancement, vehicle to pedestrian communication and so on. In the computer vision domain,
Externí odkaz:
http://arxiv.org/abs/2310.03140
We examine how the choice of data-side attributes for two important visual tasks of image classification and object detection can aid in the choice or design of lightweight convolutional neural networks. We show by experimentation how four data attri
Externí odkaz:
http://arxiv.org/abs/2308.13057