TransVOD: end-to-end video object detection with spatial-temporal transformers

Q Zhou, X Li, L He, Y Yang, G Cheng… - … on Pattern Analysis …, 2022 - ieeexplore.ieee.org
Detection Transformer (DETR) and Deformable DETR have been proposed to eliminate the
need for many hand-designed components in object detection while demonstrating good …

A Survey of Collaborative Perception in Intelligent Vehicles at Intersections

X Gao, X Zhang, Y Lu, Y Huang, L Yang… - IEEE Transactions …, 2024 - ieeexplore.ieee.org
As an important component of intelligent transportation systems, collaborative perception
has made great progress in recent years. In collaborative perception, multiple devices rely …

Position encoding based convolutional neural networks for machine remaining useful life prediction

R Jin, M Wu, K Wu, K Gao, Z Chen… - IEEE/CAA Journal of …, 2022 - ieeexplore.ieee.org
Accurate remaining useful life (RUL) prediction is important in industrial systems. It prevents
machines from working under failure conditions, and ensures that the industrial system …

Objects do not disappear: Video object detection by single-frame object location anticipation

X Liu, FK Nejadasl, JC van Gemert… - Proceedings of the …, 2023 - openaccess.thecvf.com
Abstract Objects in videos are typically characterized by continuous smooth motion. We
exploit continuous smooth motion in three ways. 1) Improved accuracy by using object …

Explore spatio-temporal aggregation for insubstantial object detection: benchmark dataset and baseline

K Zhou, Y Wang, T Lv, Y Li, L Chen… - Proceedings of the …, 2022 - openaccess.thecvf.com
We endeavor on a rarely explored task named Insubstan-tial Object Detection (IOD), which
aims to localize the object with following characteristics:(1) amorphous shape with indistinct …

UDF-GAN: Unsupervised dense optical-flow estimation using cycle Generative Adversarial Networks

X Liu, T Zhang, M Liu - Knowledge-Based Systems, 2023 - Elsevier
In estimating optical flow using convolutional neural networks, a gap in accuracy exists
between supervised and unsupervised training because supervised methods can obtain …

Object Detection Difficulty: Suppressing Over-aggregation for Faster and Better Video Object Detection

B Zhang, S Wang, Y Liu, B Kusy, X Li, J Liu - Proceedings of the 31st …, 2023 - dl.acm.org
Current video object detection (VOD) models often encounter issues with over-aggregation
due to redundant aggregation strategies, which perform feature aggregation on every frame …

Weakly Supervised Fixated Object Detection in Traffic Videos based on Driver's Selective Attention Mechanism

Y Shi, L Qin, S Zhao, K Yang, Y Cui… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Traffic scene perception has a significant impact on driving safety. Inexperienced or
distracted drivers usually do not allocate enough attention to the objects closely related to …

Matching strategy and skip-scale head configuration guideline based traffic object detection

Y Shi, X Zhang, C Xie, J Lu, L Yuan… - Measurement …, 2024 - iopscience.iop.org
The configuration of the detection head has a significant impact on detection performance.
However, when the input resolution or detection scene changes, there is not a clear method …

Context-aware Deformable Alignment for Video Object Segmentation

J Yang, M Xia, X Zhou - 2022 26th International Conference on …, 2022 - ieeexplore.ieee.org
Matching-based Semi-supervised video object segmentation (VOS) either resorts to non-
local matching to retrieve and aggregate the spatiotemporal features of past frames or relies …