NSTL国家科技图书文献中心

1. Implicit Neural Models to Extract Heart Rate from Video NSTL国家科技图书文献中心

Pradyumna Chari | Anirudh Bindiganaval...... - 《Computer Vision - ECCV 2024,Part LXXXIII》 - European Conference on Computer Vision - 2025, - 157～175 - 共19页

摘要：Scene representation networks, or implicit | neural representations (INR) have seen a range of | success in numerous image and video applications | . However, being universal function fitters, they fit all | variations in videos without any selectivity. This is

关键词： Implicit neural representations | Remote plethysmography

2. PFGS: High Fidelity Point Cloud Rendering via Feature Splatting NSTL国家科技图书文献中心

Jiaxu Wang | Ziyi Zhang ... - 《Computer Vision - ECCV 2024,Part LXXXIII》 - European Conference on Computer Vision - 2025, - 193～209 - 共17页

摘要：Rendering high-fidelity images from sparse | point clouds is still challenging. Existing learning | -based approaches suffer from either hole artifacts | , missing details, or expensive computations. In this | paper, we propose a novel framework to render high

关键词： Point cloud rendering | 3D gaussian splatting

3. EMO: Emote Portrait Alive Generating Expressive Portrait Videos with Audio2Video Diffusion Model Under Weak Conditions NSTL国家科技图书文献中心

Linrui Tian | Qi Wang ... - 《Computer Vision - ECCV 2024,Part LXXXIII》 - European Conference on Computer Vision - 2025, - 244～260 - 共17页

摘要：In this work, we tackle the challenge of | enhancing the realism and expressiveness in talking head | video generation by focusing on the dynamic and | nuanced relationship between audio cues and facial | movements. We identify the limitations of traditional

关键词： Diffusion models | Video generation | Talking head

4. Zero-Shot Adaptation for Approximate Posterior Sampling of Diffusion Models in Inverse Problems NSTL国家科技图书文献中心

Yasar Utku Alcalar | Mehmet Akcakaya - 《Computer Vision - ECCV 2024,Part LXXXIII》 - European Conference on Computer Vision - 2025, - 444～460 - 共17页

摘要：Diffusion models have emerged as powerful | generative techniques for solving inverse problems. Despite | their success in a variety of inverse problems in | imaging, these models require many steps to converge | , leading to slow inference time. Recently, there has been

关键词： Diffusion models | Zero-Shot learning | Inverse problems | Plug-and-Play (PnP) methods | Unrolled networks | Bayesian methods

5. R.A.C.E.: Robust Adversarial Concept Erasure for Secure Text-to-Image Diffusion Model NSTL国家科技图书文献中心

Changhoon Kim | Kyle Min ... - 《Computer Vision - ECCV 2024,Part LXXXIII》 - European Conference on Computer Vision - 2025, - 461～478 - 共18页

摘要：In the evolving landscape of text-to-image | (T2I) diffusion models, the remarkable capability to | generate high-quality images from textual descriptions | faces challenges with the potential misuse of | reproducing sensitive content. To address this critical

关键词： Concept erasure | Responsible image generative models | Secure t2I diffusion models

6. LMT-GP: Combined Latent Mean-Teacher and Gaussian Process for Semi-supervised Low-Light Image Enhancement NSTL国家科技图书文献中心

Ye Yu | Fengxin Chen ... - 《Computer Vision - ECCV 2024,Part LXXXIII》 - European Conference on Computer Vision - 2025, - 261～279 - 共19页

摘要：While recent low-light image enhancement (LLIE | ) methods have made significant advancements, they still | face challenges in terms of low visual quality and | weak generalization ability when applied to complex | scenarios. To address these issues, we propose a semi

关键词： Low-light image enhancement | Mean-teacher | Gaussian process | Semi-supervised

7. Generalized Coverage for More Robust Low-Budget Active Learning NSTL国家科技图书文献中心

Wonho Bae | Junhyug Noh ... - 《Computer Vision - ECCV 2024,Part LXXXIII》 - European Conference on Computer Vision - 2025, - 318～334 - 共17页

摘要：The ProbCover method of Yehuda et al. is a | well-motivated algorithm for active learning in low | -budget regimes, which attempts to "cover" the data | distribution with balls of a given radius at selected data | points. We demonstrate, however, that the performance

关键词： Active learning | Set coverage | Low budget | Kernel herding

8. FedTSA: A Cluster-Based Two-Stage Aggregation Method for Model-Heterogeneous Federated Learning NSTL国家科技图书文献中心

Boyu Fan | Chenrui Wu ... - 《Computer Vision - ECCV 2024,Part LXXXIII》 - European Conference on Computer Vision - 2025, - 370～389 - 共20页

摘要：Despite extensive research into data | heterogeneity in federated learning (FL), system heterogeneity | remains a significant yet often overlooked challenge | . Traditional FL approaches typically assume homogeneous | hardware resources across FL clients, implying that

关键词： Federated learning | Diffusion model | Knowledge distillation

9. E3M: Zero-Shot Spatio-Temporal Video Grounding with Expectation-Maximization Multimodal Modulation NSTL国家科技图书文献中心

Peijun Bao | Zihao Shao ... - 《Computer Vision - ECCV 2024,Part LXXXIII》 - European Conference on Computer Vision - 2025, - 227～243 - 共17页

摘要：Spatio-temporal video grounding aims to | localize the spatio-temporal tube in a video according to | the given language query. To eliminate the | annotation costs, we make a first exploration to tackle | spatio-temporal video grounding in a zero-shot manner

关键词： Video grounding | Zero-shot learning | Vision-language model

10. Integration of Global and Local Representations for Fine-Grained Cross-Modal Alignment NSTL国家科技图书文献中心

Seungwan Jin | Hoyoung Choi ... - 《Computer Vision - ECCV 2024,Part LXXXIII》 - European Conference on Computer Vision - 2025, - 53～70 - 共18页

摘要：Fashion is one of the representative domains | of fine-grained Vision-Language Pre-training (VLP | ) involving a large number of images and text. Previous | fashion VLP research has proposed various pre-training | tasks to account for fine-grained details in

摘要：Scene representation networks, or implicit | neural representations (INR) have seen a range of | success in numerous image and video applications | . However, being universal function fitters, they fit all | variations in videos without any selectivity. This is

关键词： Implicit neural representations | Remote plethysmography

摘要：Rendering high-fidelity images from sparse | point clouds is still challenging. Existing learning | -based approaches suffer from either hole artifacts | , missing details, or expensive computations. In this | paper, we propose a novel framework to render high

关键词： Point cloud rendering | 3D gaussian splatting

摘要：In this work, we tackle the challenge of | enhancing the realism and expressiveness in talking head | video generation by focusing on the dynamic and | nuanced relationship between audio cues and facial | movements. We identify the limitations of traditional

关键词： Diffusion models | Video generation | Talking head

摘要：Diffusion models have emerged as powerful | generative techniques for solving inverse problems. Despite | their success in a variety of inverse problems in | imaging, these models require many steps to converge | , leading to slow inference time. Recently, there has been

关键词： Diffusion models | Zero-Shot learning | Inverse problems | Plug-and-Play (PnP) methods | Unrolled networks | Bayesian methods

摘要：In the evolving landscape of text-to-image | (T2I) diffusion models, the remarkable capability to | generate high-quality images from textual descriptions | faces challenges with the potential misuse of | reproducing sensitive content. To address this critical

关键词： Concept erasure | Responsible image generative models | Secure t2I diffusion models

摘要：While recent low-light image enhancement (LLIE | ) methods have made significant advancements, they still | face challenges in terms of low visual quality and | weak generalization ability when applied to complex | scenarios. To address these issues, we propose a semi

关键词： Low-light image enhancement | Mean-teacher | Gaussian process | Semi-supervised

摘要：The ProbCover method of Yehuda et al. is a | well-motivated algorithm for active learning in low | -budget regimes, which attempts to "cover" the data | distribution with balls of a given radius at selected data | points. We demonstrate, however, that the performance

关键词： Active learning | Set coverage | Low budget | Kernel herding

摘要：Despite extensive research into data | heterogeneity in federated learning (FL), system heterogeneity | remains a significant yet often overlooked challenge | . Traditional FL approaches typically assume homogeneous | hardware resources across FL clients, implying that

关键词： Federated learning | Diffusion model | Knowledge distillation

摘要：Spatio-temporal video grounding aims to | localize the spatio-temporal tube in a video according to | the given language query. To eliminate the | annotation costs, we make a first exploration to tackle | spatio-temporal video grounding in a zero-shot manner

关键词： Video grounding | Zero-shot learning | Vision-language model

摘要：Fashion is one of the representative domains | of fine-grained Vision-Language Pre-training (VLP | ) involving a large number of images and text. Previous | fashion VLP research has proposed various pre-training | tasks to account for fine-grained details in

关键词： Vision-Language pre-training | Fine-grained representation learning | Fashion

4008-161-200 800-990-8900

国家科技图书文献中心