Zobrazeno 1 - 10
of 225
pro vyhledávání: '"Xiu-Shen Wei"'
Publikováno v:
IEEE Transactions on Pattern Analysis and Machine Intelligence. 45:6969-6983
The task of multi-label image recognition is to predict a set of object labels that present in an image. As objects normally co-occur in an image, it is desirable to model label dependencies to improve recognition performance. To capture and explore
Publikováno v:
IEEE Transactions on Multimedia. :1-13
Publikováno v:
Visual Intelligence. 1
Semantic change detection (SCD) and land cover mapping (LCM) are always treated as a dual task in the field of remote sensing. However, due to diverse real-world scenarios, many SCD categories are not easy to be clearly recognized, such as “water-v
Publikováno v:
Proceedings of the AAAI Conference on Artificial Intelligence. 36:2911-2919
The task of few-shot fine-grained recognition is to classify images belonging to subordinate categories merely depending on few examples. Due to the fine-grained nature, it is desirable to capture subtle but discriminative part-level patterns from li
Autor:
Xiu-Shen Wei, Belongie, Serge
Publikováno v:
Synthesis Lectures on Computer Vision; 2023, piv-208, 211p
Publikováno v:
IEEE Transactions on Multimedia. 24:546-557
Labeling objects at a subordinate level typically requires expert knowledge, which is not always available when using random annotators. As such, learning directly from web images for fine-grained recognition has attracted broad attention. However, t
Publikováno v:
IEEE Transactions on Image Processing. 31:3004-3016
The practical task of Automatic Check-Out (ACO) is to accurately predict the presence and count of each product in an arbitrary product combination. Beyond the large-scale and the fine-grained nature of product categories as its main challenges, prod
Publikováno v:
2022 IEEE International Conference on Multimedia and Expo (ICME).
Publikováno v:
Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence.
The task of webly-supervised fine-grained recognition is to boost recognition accuracy of classifying subordinate categories (e.g., different bird species) by utilizing freely available but noisy web data. As the label noises significantly hurt the n
Publikováno v:
Proceedings of the AAAI Conference on Artificial Intelligence. 35:3447-3455
In recent years, visual recognition on challenging long-tailed distributions, where classes often exhibit extremely imbalanced frequencies, has made great progress mostly based on various complex paradigms (e.g., meta learning). Apart from these comp