全部 |
  • 全部
  • 题名
  • 作者
  • 机构
  • 关键词
  • NSTL主题词
  • 摘要
检索 二次检索 AI检索
外文文献 中文文献
筛选条件:

1. Open-Vocabulary Camouflaged Object Segmentation NSTL国家科技图书文献中心

Youwei Pang |  Xiaoqi Zhao... -  《Computer Vision - ECCV 2024,Part XLVII》 -  European Conference on Computer Vision - 2025, - 476~495 - 共20页

摘要: for the challenging open-vocabulary dense prediction |  introduce a new task, open-vocabulary camouflaged object |  previous state-of-the-arts of open-vocabulary semantic |  further expand the research on open-vocabulary dense |  the way towards open-world object perception. Many
关键词: Open vocabulary |  Camouflaged object segmentation

2. Diffusion Models for Open-Vocabulary Segmentation NSTL国家科技图书文献中心

Laurynas Karazija |  Iro Laina... -  《Computer Vision - ECCV 2024,Part V》 -  European Conference on Computer Vision - 2025, - 299~317 - 共19页

摘要:Open-vocabulary segmentation is the task of |  significant advances in open-vocabulary segmentation, but at | , making them applicable in an open-vocabulary setting |  diffusion models for unsupervised open-vocabulary |  segmenting anything that can be named in an image. Recently
关键词: Open-vocabulary segmentation |  Vision-language

3. Open Vocabulary Multi-label Video Classification NSTL国家科技图书文献中心

Rohit Gupta |  Mamshad Nayeem Rizve... -  《Computer Vision - ECCV 2024,Part XXXIX》 -  European Conference on Computer Vision - 2025, - 276~293 - 共18页

摘要: enabled significant progress in open vocabulary computer |  focused on extending VLMs to open vocabulary single |  the video in an open vocabulary setting. We |  formulate this problem as open vocabulary multi-label |  open vocabulary performance with two key
关键词: Open vocabulary |  Multi-Modal |  Video understanding

4. Anytime Continual Learning for Open Vocabulary Classification NSTL国家科技图书文献中心

Zhen Zhu |  Yiming Gong... -  《Computer Vision - ECCV 2024,Part VI》 -  European Conference on Computer Vision - 2025, - 269~285 - 共17页

摘要: learning (AnytimeCL) for open vocabulary image |  predictions of a partially fine-tuned model and a fixed open |  vocabulary model that enables continual improvement when | We propose an approach for anytime continual |  classification. The AnytimeCL problem aims to break away from
关键词: Continual learning |  Anytime learning |  Open-vocabulary classification

5. Open-Vocabulary RGB-Thermal Semantic Segmentation NSTL国家科技图书文献中心

Guoqiang Zhao |  Junjie Huang... -  《Computer Vision - ECCV 2024,Part LXXIV》 -  European Conference on Computer Vision - 2025, - 304~320 - 共17页

摘要:. First, they do not have the open-vocabulary |  open-vocabulary segmentation capability. OpenRSS |  the open-vocabulary capability by jointly utilizing |  effective open-vocabulary semantic segmentation ability on |  RGB open-vocabulary semantic segmentation methods on
关键词: Open-vocabulary |  RGB-T semantic segmentation |  Prompt learning

6. Open-Vocabulary Instance Segmentation-Boundary IS-Goal NSTL国家科技图书文献中心

Quan Tang -  《Pattern Recognition and Computer Vision,Part IV》 -  Chinese Conference on Pattern Recognition and Computer Vision - 2025, - 421~436 - 共16页

摘要: boundary detection and open-vocabulary capabilities for |  open-vocabulary instance segmentation tasks on the MS |  instance segmentation and boundary detection under open | -vocabulary. It includes a prompt text encoder, a two-stream |  and boundary detection performance under open
关键词: Instance segmentation |  Boundary detection |  Open-vocabulary |  Multi-modal fusion

7. SLAck: Semantic, Location, and Appearance Aware Open-Vocabulary Tracking NSTL国家科技图书文献中心

Siyuan Li |  Lei Ke... -  《Computer Vision - ECCV 2024,Part XXVII》 -  European Conference on Computer Vision - 2025, - 1~18 - 共18页

摘要:Open-vocabulary Multiple Object Tracking (MOT |  significantly for large-scale open-vocabulary tracking |  the open-vocabulary MOT and TAO TETA benchmarks. Our |  large-vocabulary scenarios and unstable classification | ) aims to generalize trackers to novel categories not
关键词: Open-Vocabulary |  Multiple object tracking

8. O_2V-Mapping: Online Open-Vocabulary Mapping with Neural Implicit Representation NSTL国家科技图书文献中心

Muer Tie |  Julong Wei... -  《Computer Vision - ECCV 2024,Part LXXXVII》 -  European Conference on Computer Vision - 2025, - 318~333 - 共16页

摘要:. However, implementing open-vocabulary scene |  create an open-vocabulary field, thus allowing for | . Extensive experiments on open-vocabulary object | Online construction of open-ended language |  scenes is crucial for robotic applications, where open
关键词: NeRF |  Open-Vocabulary |  Language scene construction

9. Open-Vocabulary Scene Graph Generation via Synonym-Based Predicate Descriptor NSTL国家科技图书文献中心

Yuta Goto |  Satoshi Yamazaki... -  《MultiMedia Modeling,Part III》 -  International Conference on MultiMedia Modeling - 2025, - 142~156 - 共15页

摘要:This paper proposes a class balance-aware open | -vocabulary scene graph generation (SGG) method that |  predicate inference. Existing SGG works address open | -vocabulary relation predictions utilizing vision language | -training and the open world; there are many unseen
关键词: Open-vocabulary scene graph generation

10. Collaborative Vision-Text Representation Optimizing for Open-Vocabulary Segmentation NSTL国家科技图书文献中心

Siyu Jiao |  Hongguang Zhu... -  《Computer Vision - ECCV 2024,Part XXXIII》 -  European Conference on Computer Vision - 2025, - 399~416 - 共18页

摘要: challenging Open-Vocabulary Segmentation (OVS) task |  popular OVS benchmarks. In open-vocabulary semantic | Pre-trained vision-language models, e.g. CLIP | , have been increasingly used to address the | , benefiting from their well-aligned vision-text embedding
关键词: Open-Vocabulary segmentation |  Fine-tuning
检索条件Open vocabulary
  • 检索词扩展

NSTL主题词

  • NSTL学科导航