NSTL国家科技图书文献中心

1. Co-salient object detection with consensus mining and consistency cross-layer interactive decoding NSTL国家科技图书文献中心

Ge, Yanliang | Pan, Jinghuai ... - 《Image and vision computing》 - 2025,154(Feb.) - 1.1～1.11 - 共11页

摘要：The main goal of co-salient object detection | (CoSOD) is to extract a group of notable objects that | appear together in the image. The existing methods face | two major challenges: the first is that in some | complex scenes or in the case of interference by other

关键词： Deep learning | Consensus cue mining | Co-salient object detection | Group consistency modeling | Cross-layer interactive decoding | NETWORK | DEEP

2. Class-discriminative domain generalization for semantic segmentation NSTL国家科技图书文献中心

Liao, Muxin | Tian, Shishun ... - 《Image and vision computing》 - 2025,154(Feb.) - 1.1～1.13 - 共13页

摘要：Existing domain generalization semantic | segmentation methods aim to improve the generalization | ability by learning domain-invariant information for | generalizing well on unseen domains. However, these methods | ignore the class discriminability of models, which may

关键词： Domain generalization | Text embeddings | Dual prototypical contrastive learning | Semantic segmentation

3. De-noising mask transformer for referring image segmentation NSTL国家科技图书文献中心

Wang, Yehui | Lei, Fang ... - 《Image and vision computing》 - 2025,154(Feb.) - 1.1～1.10 - 共10页

摘要：Referring Image Segmentation (RIS) is a | challenging computer vision task that involves identifying | and segmenting specific objects in an image based on | a natural language description. Unlike | conventional segmentation methodologies, RIS needs to bridge

关键词： Referring image segmentation | De-noising mask | Multi-modal fusion | ATTENTION

4. 3D human avatar reconstruction with neural fields: A recent survey NSTL国家科技图书文献中心

Gu, Meiying | Li, Jiahe ... - 《Image and vision computing》 - 2025,154(Feb.) - 1.1～1.27 - 共27页

摘要：3D human avatar reconstruction aims to | reconstruct the 3D geometric shape and appearance of the | human body from various data inputs, such as images | , videos, and depth information, acting as a key | component in human- oriented 3D vision in the metaverse

关键词： 3D human reconstruction | Neural fields | Literature survey | FIDELITY HEAD AVATAR | RADIANCE FIELDS | REPRESENTATION | MESH

5. IFE-Net: Integrated feature enhancement network for image manipulation localization NSTL国家科技图书文献中心

Su L. | Dai C.... - 《Image and vision computing》 - 2025,153(Jan.) - 1.1～1.11 - 共11页

摘要：© 2024 Elsevier B.V.Image tampering techniques | can lead to distorted or misleading information | , which in turn poses a threat in many areas, including | social, legal and commercial. Numerous image tampering | detection algorithms lose important low-level detail

关键词： Attention mechanism | Edge supervision | Tampered localization

6. Infrared and visible image fusion using quantum computing induced edge preserving filter NSTL国家科技图书文献中心

Parida P. | Panda M.K.... - 《Image and vision computing》 - 2025,153(Jan.) - 1.1～1.16 - 共16页

摘要：© 2024 Elsevier B.V.Information fusion by | utilization of visible and thermal images provides a more | comprehensive scene understanding in the resulting image | rather than individual source images. It applies to | wide areas of applications such as navigation

关键词： Edge detail | Image fusion | Infrared | Quantum computing | Visible | Weight map

7. Correlation embedding semantic-enhanced hashing for multimedia retrieval NSTL国家科技图书文献中心

Chen, Yunfei | Long, Yitian ... - 《Image and vision computing》 - 2025,154(Feb.) - 1.1～1.11 - 共11页

摘要：Due to its feature extraction and information | processing advantages, deep hashing has achieved | significant success in multimedia retrieval. Currently | , mainstream unsupervised multimedia hashing methods do not | incorporate associative relationship information as part of

关键词： Multimedia retrieval | Semantic-enhanced similarity | Correlation embedding hashing | Semantic correlation information | RECONSTRUCTION

8. Pixel integration from fine to coarse for lightweight image super-resolution NSTL国家科技图书文献中心

Wu, Yuxiang | Wang, Xiaoyan ... - 《Image and vision computing》 - 2025,154(Feb.) - 1.1～1.12 - 共12页

摘要：Recently, Transformer-based methods have made | significant progress on image super-resolution. They encode | long-range dependencies between image patches through | self-attention mechanism. However, when extracting | all tokens from the entire feature map, the

关键词： Image super-resolution | Lightweight | Pixel integration | Transformer | Retractable attention

9. PAdapter: Adapter combined with prompt for image and video classification NSTL国家科技图书文献中心

Li, Youwei | Ye, Junyong ... - 《Image and vision computing》 - 2025,154(Feb.) - 1.1～1.11 - 共11页

摘要：In computer vision, parameter-efficient | transfer learning has become an extensively used | technology. Adapter is one of the commonly used basic | modules, and its simplicity and efficiency have been | widely proven. In the case of freezing the network

关键词： Computer vision | Parameter-efficient transfer learning | Fine-tune | Plug-and-play

10. Hierarchical spatiotemporal Feature Interaction Network for video saliency prediction NSTL国家科技图书文献中心

Jin, Yingjie | Zhou, Xiaofei ... - 《Image and vision computing》 - 2025,154(Feb.) - 1.1～1.9 - 共9页

摘要：Transformer can build effective long-range | dependency relationships and has been effectively utilized | for video saliency prediction. However, fewer works | have been devoted to the design of Transformer-based | models for video saliency prediction. Furthermore, the

关键词： Video saliency prediction | Multi-scale feature integration | Hierarchical feature enhancement | Semantic-guided saliency prediction | SEGMENTATION