Visual recognition with deep nearest centroids
We devise deep nearest centroids (DNC), a conceptually elegant yet surprisingly effective
network for large-scale visual recognition, by revisiting Nearest Centroids, one of the most …
network for large-scale visual recognition, by revisiting Nearest Centroids, one of the most …
Tf-blender: Temporal feature blender for video object detection
Video objection detection is a challenging task because isolated video frames may
encounter appearance deterioration, which introduces great confusion for detection. One of …
encounter appearance deterioration, which introduces great confusion for detection. One of …
Densernet: Weakly supervised visual localization using multi-scale feature aggregation
In this work, we introduce a Denser Feature Network (DenserNet) for visual localization. Our
work provides three principal contributions. First, we develop a convolutional neural network …
work provides three principal contributions. First, we develop a convolutional neural network …
A survey on map-based localization techniques for autonomous vehicles
A Chalvatzaras, I Pratikakis… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
Autonomous vehicles integrate complex software stacks for realizing the necessary iterative
perception, planning, and action operations. One of the foundational layers of such stacks is …
perception, planning, and action operations. One of the foundational layers of such stacks is …
Feature aggregated queries for transformer-based video object detectors
Y Cui - Proceedings of the IEEE/CVF Conference on …, 2023 - openaccess.thecvf.com
Video object detection needs to solve feature degradation situations that rarely happen in
the image domain. One solution is to use the temporal information and fuse the features from …
the image domain. One solution is to use the temporal information and fuse the features from …
Enhanced clustering based routing protocol in vehicular ad‐hoc networks
A Naeem, M Rizwan, S Alsubai… - … Electrical Systems in …, 2023 - Wiley Online Library
A vehicular ad‐hoc network (VANET) is derived from a mobile ad‐hoc network that is a part
of less infrastructure network design. Vehicular communication in VANET can be achieved …
of less infrastructure network design. Vehicular communication in VANET can be achieved …
Trep: Transformer-based evidential prediction for pedestrian intention with uncertainty
With rapid development in hardware (sensors and processors) and AI algorithms, automated
driving techniques have entered the public's daily life and achieved great success in …
driving techniques have entered the public's daily life and achieved great success in …
Dynamic feature aggregation for efficient video object detection
Y Cui - Proceedings of the Asian Conference on Computer …, 2022 - openaccess.thecvf.com
Video object detection is a fundamental yet challenging task in computer vision. One
practical solution is to take advantage of temporal information from the video and apply …
practical solution is to take advantage of temporal information from the video and apply …
Dg-labeler and dgl-mots dataset: Boost the autonomous driving perception
Multi-object tracking and segmentation (MOTS) is a critical task for autonomous driving
applications. The existing MOTS studies face two critical challenges: 1) the published …
applications. The existing MOTS studies face two critical challenges: 1) the published …
A transfer learning framework for proactive ramp metering performance assessment
Transportation agencies need to assess ramp metering performance when deploying or
expanding a ramp metering system. The evaluation of a ramp metering strategy is primarily …
expanding a ramp metering system. The evaluation of a ramp metering strategy is primarily …