Zobrazeno 1 - 10
of 307
pro vyhledávání: '"Zhen, Xiantong"'
With the rapid development of intelligent transportation systems and the popularity of smart city infrastructure, Vehicle Re-ID technology has become an important research field. The vehicle Re-ID task faces an important challenge, which is the high
Externí odkaz:
http://arxiv.org/abs/2409.17908
Self-supervised monocular depth estimation has emerged as a promising approach since it does not rely on labeled training data. Most methods combine convolution and Transformer to model long-distance dependencies to estimate depth accurately. However
Externí odkaz:
http://arxiv.org/abs/2409.17895
Autor:
Qiao, Zhi, Ouyang, Hanqiang, Chu, Dongheng, Yuan, Huishu, Zhen, Xiantong, Dong, Pei, Qian, Zhen
For surgical planning and intra-operation imaging, CT reconstruction using X-ray images can potentially be an important alternative when CT imaging is not available or not feasible. In this paper, we aim to use biplanar X-rays to reconstruct a 3D CT
Externí odkaz:
http://arxiv.org/abs/2408.09736
Intraoperative CT imaging serves as a crucial resource for surgical guidance; however, it may not always be readily accessible or practical to implement. In scenarios where CT imaging is not an option, reconstructing CT scans from X-rays can offer a
Externí odkaz:
http://arxiv.org/abs/2408.09731
In light of the inherent entailment relations between images and text, hyperbolic point vector embeddings, leveraging the hierarchical modeling advantages of hyperbolic space, have been utilized for visual semantic representation learning. However, p
Externí odkaz:
http://arxiv.org/abs/2408.09715
Autor:
Liu, Xuhui, Qiao, Zhi, Liu, Runkun, Li, Hong, Zhang, Juan, Zhen, Xiantong, Qian, Zhen, Zhang, Baochang
Computed tomography (CT) is widely utilized in clinical settings because it delivers detailed 3D images of the human body. However, performing CT scans is not always feasible due to radiation exposure and limitations in certain surgical environments.
Externí odkaz:
http://arxiv.org/abs/2407.13545
Fine-tuning pretrained large models to downstream tasks is an important problem, which however suffers from huge memory overhead due to large-scale parameters. This work strives to reduce memory overhead in fine-tuning from perspectives of activation
Externí odkaz:
http://arxiv.org/abs/2406.16282
This paper focuses on the data-insufficiency problem in multi-task learning within an episodic training setup. Specifically, we explore the potential of heterogeneous information across tasks and meta-knowledge among episodes to effectively tackle ea
Externí odkaz:
http://arxiv.org/abs/2310.18713
Deep learning models fail on cross-domain challenges if the model is oversensitive to domain-specific attributes, e.g., lightning, background, camera angle, etc. To alleviate this problem, data augmentation coupled with consistency regularization are
Externí odkaz:
http://arxiv.org/abs/2309.13258
Referring video object segmentation (RVOS), as a supervised learning task, relies on sufficient annotated data for a given scene. However, in more realistic scenarios, only minimal annotations are available for a new scene, which poses significant ch
Externí odkaz:
http://arxiv.org/abs/2309.02041