NSTL国家科技图书文献中心

1. Don’t Complete It! Preventing Unhelpful Code Completion for Productive and Sustainable Neural Code Completion Systems NSTL国家科技图书文献中心

ZHENSU SUN | XIAONING DU ... - 《ACM transactions on software engineering and methodology》 - 2025,34(1) - 21.1～21.22 - 共22页

摘要： are widely applied in neural code completion* systems* | generated in state-of-the-art code completion* systems as* | completion. Hence, preventing such unhelpful code | code completion* qualities. The prompts that are* | that the estimator can reject 20% of code completion

关键词： deep learning | code completion | large language model | productivity

2. Completion problems and sparsity for Kemeny's constant NSTL国家科技图书文献中心

Kirkland, Steve - 《Canadian Mathematical Bulletin》 - 2025,68(1) - 1～18 - 共18页

摘要： is well defined, there is a minimizing completion | For a partially specified stochastic matrix | , we consider the problem of completing it so asto | minimize Kemeny's constant. We prove that for any | partially specified stochastic matrix for whichthe problem

关键词： Kemeny's constant | stochastic matrix | matrix completion

3. On completion of principal fuzzy metric spaces NSTL国家科技图书文献中心

Li, Changqing | Zhang, Yanlan - 《Fuzzy sets and systems》 - 2025,505(Apr.1) - 1.1～1.5 - 共5页

摘要：, which is related to completion* of principal fuzzy* | In this note, we answer an open question | metric spaces in the sense of George and Veeramani | , proposed by Gregori et al. (2012) [5]. We give a negative | answer to such a question by means of an example.

关键词： Fuzzy metric space | Completion | Principal fuzzy metric | QUESTIONS

4. A tensor network low rank completion method NSTL国家科技图书文献中心

Bentbib, Abdeslem Ha... | Jbilou, Khalide ... - 《Computational and Applied Mathematics》 - 2025,44(1) - 共19页

摘要：This paper proposes a tensor completion | combining tensor completion* methods with side information* | data completion* challenges. We formulate the missing* | data inference task as a tensor completion* problem* | technique for recovering multidimensional network data. By

关键词： Tensor ring decomposition | Tensor completion | The t-SVT algorithm | The TNCRTR algorithm | Multiplex network

5. OGNI-DC: Robust Depth Completion with Optimization-Guided Neural Iterations NSTL国家科技图书文献中心

Yiming Zuo | Jia Deng - 《Computer Vision - ECCV 2024,Part III》 - European Conference on Computer Vision - 2025, - 78～95 - 共18页

摘要：Depth completion* is the task of generating a* | novel framework for depth completion. The key to our | dense depth map given an image and a sparse depth map | as inputs. In this paper, we present OGNI-DC, a | method is "Optimization-Guided Neural Iterations" (OGNI

关键词： Depth completion | Optimization-inspired design

6. AugUndo: Scaling Up Augmentations for Monocular Depth Completion and Estimation NSTL国家科技图书文献中心

Yangchao Wu | Tian Yu Liu ... - 《Computer Vision - ECCV 2024,Part LXIV》 - European Conference on Computer Vision - 2025, - 274～293 - 共20页

摘要：Unsupervised depth completion* and estimation* | in depth completion* have seen even less use as* | geometric augmentations for unsupervised depth completion | methods are trained by minimizing reconstruction error | . Block artifacts from resampling, intensity saturation

关键词： Depth completion | Monocular depth | Augmentations

7. 2D Semantic-Guided Semantic Scene Completion NSTL国家科技图书文献中心

Liu, Xianzhu | Xie, Haozhe ... - 《International Journal of Computer Vision》 - 2025,133(3) - 1306～1325 - 共20页

摘要：Semantic scene completion* (SSC) aims to* | simultaneously perform scene completion* (SC) and predict* | Semantic Scene Completion* framework, dubbed SG-SSC, which* | semantic categories of a 3D scene from a single depth and | /or RGB image. Most existing SSC methods struggle to

关键词： Semantic scene completion | RGB-D images | Semantic-guided fusion | Volume-guided semantic predictor

8. Sparse Beats Dense: Rethinking Supervision in Radar-Camera Depth Completion NSTL国家科技图书文献中心

Huadong Li | Minhao Jing ... - 《Computer Vision - ECCV 2024,Part XLIV》 - European Conference on Computer Vision - 2025, - 127～143 - 共17页

摘要： depth completion, but the underlying reasons for this | task of radar-camera depth completion* and present a* | LiDAR supervision, depth completion* models usually* | -camera depth completion* framework to address this issue* | It is widely believed that sparse supervision

关键词： Sparse supervision | Radar-camera depth completion

9. Quaternion Tensor Completion via QR Decomposition and Nuclear Norm Minimization NSTL国家科技图书文献中心

Sun, Jian | Liu, Xin ... - 《Numerical linear algebra with applications》 - 2025,32(1) - n/a～n/a - 共19页

摘要：The task of tensor (matrix) completion* has* | image processing, etc. To achieve the completion, the | minimization. However, the real tensor completion* methods* | computational efficiency. In this article, a new completion | the completion* method has been substantially*

关键词： image recovery | nuclear norm | quaternion tensor completion | video inpainting

10. Deep Cost Ray Fusion for Sparse Depth Video Completion NSTL国家科技图书文献中心

Jungeon Kim | Soongjin Kim ... - 《Computer Vision - ECCV 2024,Part XXVI》 - European Conference on Computer Vision - 2025, - 328～346 - 共19页

摘要： framework for sparse depth video completion. Given a | improved depth completion, we introduce a learning-based | Completion benchmark, VOID Depth Completion benchmark, and | In this paper, we present a learning-based | sparse depth map and a color image at a certain

摘要： are widely applied in neural code completion* systems* | generated in state-of-the-art code completion* systems as* | completion. Hence, preventing such unhelpful code | code completion* qualities. The prompts that are* | that the estimator can reject 20% of code completion

关键词： deep learning | code completion | large language model | productivity

摘要： is well defined, there is a minimizing completion | For a partially specified stochastic matrix | , we consider the problem of completing it so asto | minimize Kemeny's constant. We prove that for any | partially specified stochastic matrix for whichthe problem

关键词： Kemeny's constant | stochastic matrix | matrix completion

摘要：, which is related to completion* of principal fuzzy* | In this note, we answer an open question | metric spaces in the sense of George and Veeramani | , proposed by Gregori et al. (2012) [5]. We give a negative | answer to such a question by means of an example.

关键词： Fuzzy metric space | Completion | Principal fuzzy metric | QUESTIONS

摘要：This paper proposes a tensor completion | combining tensor completion* methods with side information* | data completion* challenges. We formulate the missing* | data inference task as a tensor completion* problem* | technique for recovering multidimensional network data. By

关键词： Tensor ring decomposition | Tensor completion | The t-SVT algorithm | The TNCRTR algorithm | Multiplex network

摘要：Depth completion* is the task of generating a* | novel framework for depth completion. The key to our | dense depth map given an image and a sparse depth map | as inputs. In this paper, we present OGNI-DC, a | method is "Optimization-Guided Neural Iterations" (OGNI

关键词： Depth completion | Optimization-inspired design

摘要：Unsupervised depth completion* and estimation* | in depth completion* have seen even less use as* | geometric augmentations for unsupervised depth completion | methods are trained by minimizing reconstruction error | . Block artifacts from resampling, intensity saturation

关键词： Depth completion | Monocular depth | Augmentations

摘要：Semantic scene completion* (SSC) aims to* | simultaneously perform scene completion* (SC) and predict* | Semantic Scene Completion* framework, dubbed SG-SSC, which* | semantic categories of a 3D scene from a single depth and | /or RGB image. Most existing SSC methods struggle to

关键词： Semantic scene completion | RGB-D images | Semantic-guided fusion | Volume-guided semantic predictor

摘要： depth completion, but the underlying reasons for this | task of radar-camera depth completion* and present a* | LiDAR supervision, depth completion* models usually* | -camera depth completion* framework to address this issue* | It is widely believed that sparse supervision

关键词： Sparse supervision | Radar-camera depth completion

摘要：The task of tensor (matrix) completion* has* | image processing, etc. To achieve the completion, the | minimization. However, the real tensor completion* methods* | computational efficiency. In this article, a new completion | the completion* method has been substantially*

关键词： image recovery | nuclear norm | quaternion tensor completion | video inpainting

摘要： framework for sparse depth video completion. Given a | improved depth completion, we introduce a learning-based | Completion benchmark, VOID Depth Completion benchmark, and | In this paper, we present a learning-based | sparse depth map and a color image at a certain

关键词： Depth completion | Cost volume fusion | RGB-D video

4008-161-200 800-990-8900

国家科技图书文献中心

摘要： are widely applied in neural code completion systems | generated in state-of-the-art code completion systems as | completion. Hence, preventing such unhelpful code | code completion qualities. The prompts that are | that the estimator can reject 20% of code completion

关键词： deep learning | code completion | large language model | productivity

摘要： is well defined, there is a minimizing completion | For a partially specified stochastic matrix | , we consider the problem of completing it so asto | minimize Kemeny's constant. We prove that for any | partially specified stochastic matrix for whichthe problem

关键词： Kemeny's constant | stochastic matrix | matrix completion

摘要：, which is related to completion of principal fuzzy | In this note, we answer an open question | metric spaces in the sense of George and Veeramani | , proposed by Gregori et al. (2012) [5]. We give a negative | answer to such a question by means of an example.

关键词： Fuzzy metric space | Completion | Principal fuzzy metric | QUESTIONS

摘要：This paper proposes a tensor completion | combining tensor completion methods with side information | data completion challenges. We formulate the missing | data inference task as a tensor completion problem | technique for recovering multidimensional network data. By

关键词： Tensor ring decomposition | Tensor completion | The t-SVT algorithm | The TNCRTR algorithm | Multiplex network

摘要：Depth completion is the task of generating a | novel framework for depth completion. The key to our | dense depth map given an image and a sparse depth map | as inputs. In this paper, we present OGNI-DC, a | method is "Optimization-Guided Neural Iterations" (OGNI

关键词： Depth completion | Optimization-inspired design

摘要：Unsupervised depth completion and estimation | in depth completion have seen even less use as | geometric augmentations for unsupervised depth completion | methods are trained by minimizing reconstruction error | . Block artifacts from resampling, intensity saturation

关键词： Depth completion | Monocular depth | Augmentations

摘要：Semantic scene completion (SSC) aims to | simultaneously perform scene completion (SC) and predict | Semantic Scene Completion framework, dubbed SG-SSC, which | semantic categories of a 3D scene from a single depth and | /or RGB image. Most existing SSC methods struggle to

关键词： Semantic scene completion | RGB-D images | Semantic-guided fusion | Volume-guided semantic predictor

摘要： depth completion, but the underlying reasons for this | task of radar-camera depth completion and present a | LiDAR supervision, depth completion models usually | -camera depth completion framework to address this issue | It is widely believed that sparse supervision

关键词： Sparse supervision | Radar-camera depth completion

摘要：The task of tensor (matrix) completion has | image processing, etc. To achieve the completion, the | minimization. However, the real tensor completion methods | computational efficiency. In this article, a new completion | the completion method has been substantially

关键词： image recovery | nuclear norm | quaternion tensor completion | video inpainting

摘要： framework for sparse depth video completion. Given a | improved depth completion, we introduce a learning-based | Completion benchmark, VOID Depth Completion benchmark, and | In this paper, we present a learning-based | sparse depth map and a color image at a certain

关键词： Depth completion | Cost volume fusion | RGB-D video

4008-161-200 800-990-8900

国家科技图书文献中心

摘要： are widely applied in neural code completion* systems* | generated in state-of-the-art code completion* systems as* | completion. Hence, preventing such unhelpful code | code completion* qualities. The prompts that are* | that the estimator can reject 20% of code completion

摘要：, which is related to completion* of principal fuzzy* | In this note, we answer an open question | metric spaces in the sense of George and Veeramani | , proposed by Gregori et al. (2012) [5]. We give a negative | answer to such a question by means of an example.

摘要：This paper proposes a tensor completion | combining tensor completion* methods with side information* | data completion* challenges. We formulate the missing* | data inference task as a tensor completion* problem* | technique for recovering multidimensional network data. By

摘要：Depth completion* is the task of generating a* | novel framework for depth completion. The key to our | dense depth map given an image and a sparse depth map | as inputs. In this paper, we present OGNI-DC, a | method is "Optimization-Guided Neural Iterations" (OGNI

摘要：Unsupervised depth completion* and estimation* | in depth completion* have seen even less use as* | geometric augmentations for unsupervised depth completion | methods are trained by minimizing reconstruction error | . Block artifacts from resampling, intensity saturation

摘要：Semantic scene completion* (SSC) aims to* | simultaneously perform scene completion* (SC) and predict* | Semantic Scene Completion* framework, dubbed SG-SSC, which* | semantic categories of a 3D scene from a single depth and | /or RGB image. Most existing SSC methods struggle to

摘要： depth completion, but the underlying reasons for this | task of radar-camera depth completion* and present a* | LiDAR supervision, depth completion* models usually* | -camera depth completion* framework to address this issue* | It is widely believed that sparse supervision

摘要：The task of tensor (matrix) completion* has* | image processing, etc. To achieve the completion, the | minimization. However, the real tensor completion* methods* | computational efficiency. In this article, a new completion | the completion* method has been substantially*