Clustered object detection in aerial images
Detecting objects in aerial images is challenging for at least two reasons:(1) target objects
like pedestrians are very small in pixels, making them hardly distinguished from surrounding …
like pedestrians are very small in pixels, making them hardly distinguished from surrounding …
A global-local self-adaptive network for drone-view object detection
Directly benefiting from the deep learning methods, object detection has witnessed a great
performance boost in recent years. However, drone-view object detection remains …
performance boost in recent years. However, drone-view object detection remains …
Dynamic zoom-in network for fast object detection in large images
We introduce a generic framework that reduces the computational cost of object detection
while retaining accuracy for scenarios where objects with varied sizes appear in high …
while retaining accuracy for scenarios where objects with varied sizes appear in high …
Deep reinforcement learning of region proposal networks for object detection
A Pirinen, C Sminchisescu - proceedings of the IEEE …, 2018 - openaccess.thecvf.com
We propose drl-RPN, a deep reinforcement learning-based visual recognition model
consisting of a sequential region proposal network (RPN) and an object detector. In contrast …
consisting of a sequential region proposal network (RPN) and an object detector. In contrast …
Visualizing real-time strategy games: The example of starcraft ii
YT Kuan, YS Wang, JH Chuang - 2017 IEEE Conference on …, 2017 - ieeexplore.ieee.org
We present a visualization system for users to examine real-time strategy games, which
have become very popular globally in recent years. Unlike previous systems that focus on …
have become very popular globally in recent years. Unlike previous systems that focus on …
The role of context selection in object detection
We investigate the reasons why context in object detection has limited utility by isolating and
evaluating the predictive power of different context cues under ideal conditions in which …
evaluating the predictive power of different context cues under ideal conditions in which …
Toward efficient object detection in aerial images using extreme scale metric learning
In aerial image object detection, how to efficiently detect different size objects in input
images of different scales and obtain a unified multi-scale representation of the object is an …
images of different scales and obtain a unified multi-scale representation of the object is an …
A Dynamic Data Driven Approach for Explainable Scene Understanding
ZA Daniels, D Metaxas - arXiv preprint arXiv:2206.09089, 2022 - arxiv.org
Scene-understanding is an important topic in the area of Computer Vision, and illustrates
computational challenges with applications to a wide range of domains including remote …
computational challenges with applications to a wide range of domains including remote …
Active object localization in visual situations
MH Quinn, AD Rhodes, M Mitchell - arXiv preprint arXiv:1607.00548, 2016 - arxiv.org
We describe a method for performing active localization of objects in instances of visual
situations. A visual situation is an abstract concept---eg," a boxing match"," a birthday party"," …
situations. A visual situation is an abstract concept---eg," a boxing match"," a birthday party"," …
An improved human-in-the-loop model for fine-grained object recognition with batch-based question answering
Fine-grained object recognition refers to a subordinate level of object recognition such as
recognition of bird species and car models. It has become crucial for recognition of …
recognition of bird species and car models. It has become crucial for recognition of …