Zobrazeno 1 - 10
of 254
pro vyhledávání: '"Dong, Weisheng"'
Autor:
Feng, Jie, Zhang, Tianshu, Zhang, Junpeng, Shang, Ronghua, Dong, Weisheng, Shi, Guangming, Jiao, Licheng
Unsupervised domain adaptation techniques, extensively studied in hyperspectral image (HSI) classification, aim to use labeled source domain data and unlabeled target domain data to learn domain invariant features for cross-scene classification. Comp
Externí odkaz:
http://arxiv.org/abs/2408.15263
Band selection plays a crucial role in hyperspectral image classification by removing redundant and noisy bands and retaining discriminative ones. However, most existing deep learning-based methods are aimed at dealing with a specific band selection
Externí odkaz:
http://arxiv.org/abs/2406.07949
Back to the Color: Learning Depth to Specific Color Transformation for Unsupervised Depth Estimation
Autor:
Zhu, Yufan, Ran, Chongzhi, Feng, Mingtao, Wu, Fangfang, Dong, Le, Dong, Weisheng, López, Antonio M., Shi, Guangming
Virtual engines can generate dense depth maps for various synthetic scenes, making them invaluable for training depth estimation models. However, discrepancies between synthetic and real-world colors pose significant challenges for depth estimation i
Externí odkaz:
http://arxiv.org/abs/2406.07741
3D object detection is a fundamental task in scene understanding. Numerous research efforts have been dedicated to better incorporate Hough voting into the 3D object detection pipeline. However, due to the noisy, cluttered, and partial nature of real
Externí odkaz:
http://arxiv.org/abs/2403.14133
Generating realistic 3D scenes is challenging due to the complexity of room layouts and object geometries.We propose a sketch based knowledge enhanced diffusion architecture (SEK) for generating customized, diverse, and plausible 3D scenes. SEK condi
Externí odkaz:
http://arxiv.org/abs/2403.14121
Autor:
Yang, Qitong, Feng, Mingtao, Wu, Zijie, Sun, Shijie, Dong, Weisheng, Wang, Yaonan, Mian, Ajmal
Directly learning to model 4D content, including shape, color and motion, is challenging. Existing methods depend on skeleton-based motion control and offer limited continuity in detail. To address this, we propose a novel framework that generates co
Externí odkaz:
http://arxiv.org/abs/2403.13238
Mainstreamed weakly supervised road extractors rely on highly confident pseudo-labels propagated from scribbles, and their performance often degrades gradually as the image scenes tend various. We argue that such degradation is due to the poor model'
Externí odkaz:
http://arxiv.org/abs/2403.01381
Previous deep learning-based event denoising methods mostly suffer from poor interpretability and difficulty in real-time processing due to their complex architecture designs. In this paper, we propose window-based event denoising, which simultaneous
Externí odkaz:
http://arxiv.org/abs/2402.09270
Publikováno v:
In Neurocomputing 1 October 2024 600
Publikováno v:
In Pattern Recognition September 2024 153