Topic
Transformer (opens in a new tab)
19 Citations
- Weicheng ShiXiaoqin LyuLei Han
- 2024
Engineering, Computer Science
IEEE Transactions on Power Delivery
A multi-branch dilated convolution module (MDCM), an adaptive attention feature fusion structure (AAFF), and β-CIoU loss are proposed to dynamically optimize the learning rate during bounding box regression, thereby enhancing the detection accuracy of small objects.
- Jianming ZhangYao YiZulou WangFayez AlqahtaniJin Wang
- 2024
Computer Science, Engineering
Journal of Real-Time Image Processing
- Yan GuiYiru OuMin LiangJianming ZhangZhihua Chen
- 2024
Computer Science, Engineering
Pattern Analysis and Applications
- Janani KugarajeevanT. KokulAmirthalingam RamananSubha Fernando
- 2025
Engineering, Computer Science
Expert Syst. Appl.
- Junlin HeTong NieWei Ma
- 2024
Computer Science, Geography
ArXiv
A novel, training-free method that leverages large language models (LLMs) and auxiliary map data from OpenStreetMap to derive geolocation representations (LLMGeovec), which can represent the geographic semantics of city, country, and global scales, which acts as a generic enhancer for spatio-temporal learning.
- Jianming ZhangWentao ChenYufan HeLi-Dan KuangA. K. Sangaiah
- 2024
Computer Science, Engineering
Multim. Syst.
- Zexu LiGongchao Chen Weidong Zhang
- 2024
Environmental Science, Computer Science
Comput. Electr. Eng.
- 4
- Fei YuShuai XuYue LinTing HeChaoran WuHairong Lin
- 2024
Engineering, Physics
Mathematics
The design of chaotic systems with complex dynamic behaviors has always been a key aspect of chaos theory in engineering applications. This study introduces a novel fractional-order system…
- 1
- PDF
- Poonam L RakibeDr. Pramod D Patil
- 2024
Medicine, Computer Science
e-Prime - Advances in Electrical Engineering…
- Jianming ZhangWentao ChenJiangxin DaiJin Zhang
- 2024
Computer Science, Engineering
Appl. Intell.
- 1
...
...
16 References
- Yujie LiJin-Lin CaiQuan ZhouHuimin Lu
- 2023
Computer Science, Engineering
IEEE Transactions on Intelligent Transportation…
A new feature extraction network for segmentation is proposed by adding an encoder-decoder structure, which can extract the multiscale local feature information from the feature map and greatly improves both semantic segmentation and instance segmentation tasks.
- 22
- Huimin LuYadong TengYujie Li
- 2023
Computer Science, Engineering
IEEE Transactions on Intelligent Transportation…
The method jointly optimizes the visual representation model and dynamic model of deformable objects, maps the target nonlinear state to linear latent space which avoids model inference for deformableObjects in infinite-dimensional configuration spaces and achieves substantial performance improvements.
- 15
- Jianming ZhangHaitao HuangXiaokang JinLi-Dan KuangJin Zhang
- 2024
Computer Science
Multim. Tools Appl.
This work proposes a novel Siamese anchor-free network based on criss-cross attention and an improved head network that reduces the impact of background information or distractors and can obtain high-quality bounding boxes, generating more accurate and robust tracking results.
- 28
- Jianming ZhangJuan SunJin WangZongping LiX. Chen
- 2022
Computer Science, Engineering
Comput. Electr. Eng.
- 92
- M. KristanA. Leonardis Ziang Ma
- 2020
Computer Science
ECCV Workshops
A significant novelty is introduction of a new VOT short-term tracking evaluation methodology, and introduction of segmentation ground truth in the VOT-ST2020 challenge – bounding boxes will no longer be used in theVDT challenges.
- 235
- Zhipeng ZhangHouwen Peng
- 2020
Computer Science
ECCV
This paper introduces a feature alignment module to learn an object-aware feature from predicted bounding boxes that can further contribute to the classification of target objects and background and presents a novel tracking framework based on the anchor-free model.
- 552 [PDF]
- Goutam BhatMartin DanelljanL. GoolR. Timofte
- 2020
Computer Science
ECCV
This work proposes a novel tracking architecture which can utilize scene information as dense localized state vectors, which can encode, for example, if the local region is target, background, or distractor and combined with the appearance model output to localize the target.
- 273
- PDF
- Yinda XuZeyu WangZuoxin LiYuan YeGang Yu
- 2020
Computer Science
AAAI
This work proposes a set of practical guidelines of target state estimation for high-performance generic object tracker design and designs the Fully Convolutional Siamese tracker++ (SiamFC++), which achieves state-of-the-art performance on five challenging benchmarks, which proves both the tracking and generalization ability of the tracker.
- 703
- PDF
- Lianghua HuangXin ZhaoKaiqi Huang
- 2021
Computer Science, Environmental Science
IEEE Transactions on Pattern Analysis and Machine…
A large tracking database that offers an unprecedentedly wide coverage of common moving objects in the wild, called GOT-10k, and the first video trajectory dataset that uses the semantic hierarchy of WordNet to guide class population, which ensures a comprehensive and relatively unbiased coverage of diverse moving objects.
- 1,114
- PDF
- I. LoshchilovF. Hutter
- 2019
Computer Science, Mathematics
ICLR
This work proposes a simple modification to recover the original formulation of weight decay regularization by decoupling the weight decay from the optimization steps taken w.r.t. the loss function, and provides empirical evidence that this modification substantially improves Adam's generalization performance.
- 17,480
...
...
Related Papers
Showing 1 through 3 of 0 Related Papers