Visual recognition with deep nearest centroids

W Wang, C Han, T Zhou, D Liu - arXiv preprint arXiv:2209.07383, 2022 - arxiv.org
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 …

Tf-blender: Temporal feature blender for video object detection

Y Cui, L Yan, Z Cao, D Liu - Proceedings of the IEEE/CVF …, 2021 - openaccess.thecvf.com
Video objection detection is a challenging task because isolated video frames may
encounter appearance deterioration, which introduces great confusion for detection. One of …

Densernet: Weakly supervised visual localization using multi-scale feature aggregation

D Liu, Y Cui, L Yan, C Mousas, B Yang… - Proceedings of the AAAI …, 2021 - ojs.aaai.org
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 …

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 …

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 …

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 …

Trep: Transformer-based evidential prediction for pedestrian intention with uncertainty

Z Zhang, R Tian, Z Ding - Proceedings of the AAAI Conference on …, 2023 - ojs.aaai.org
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 …

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 …

Dg-labeler and dgl-mots dataset: Boost the autonomous driving perception

Y Cui, Z Cao, Y Xie, X Jiang, F Tao… - Proceedings of the …, 2022 - openaccess.thecvf.com
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 …

A transfer learning framework for proactive ramp metering performance assessment

X Ma, A Cottam, MRR Shaon, YJ Wu - arXiv preprint arXiv:2308.03542, 2023 - arxiv.org
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 …