TransVOD: end-to-end video object detection with spatial-temporal transformers
Detection Transformer (DETR) and Deformable DETR have been proposed to eliminate the
need for many hand-designed components in object detection while demonstrating good …
need for many hand-designed components in object detection while demonstrating good …
A Survey of Collaborative Perception in Intelligent Vehicles at Intersections
As an important component of intelligent transportation systems, collaborative perception
has made great progress in recent years. In collaborative perception, multiple devices rely …
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
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 …
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
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 …
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
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 …
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 …
between supervised and unsupervised training because supervised methods can obtain …
Object Detection Difficulty: Suppressing Over-aggregation for Faster and Better Video Object Detection
Current video object detection (VOD) models often encounter issues with over-aggregation
due to redundant aggregation strategies, which perform feature aggregation on every frame …
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 …
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 …
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 …
local matching to retrieve and aggregate the spatiotemporal features of past frames or relies …