Výsledky vyhledávání

Report

Semi-Supervised Transfer Boosting (SS-TrBoosting)

Autor: Deng, Lingfei, Zhao, Changming, Du, Zhenbang, Xia, Kun, Wu, Dongrui

Publikováno v: IEEE Trans. on Artificial Intelligence, 5(7):3431-3444, 2024

Semi-supervised domain adaptation (SSDA) aims at training a high-performance model for a target domain using few labeled target data, many unlabeled target data, and plenty of auxiliary data from a source domain. Previous works in SSDA mainly focused

Externí odkaz: http://arxiv.org/abs/2412.03212

Zobrazit plný text záznamu

Report

Diversifying Query: Region-Guided Transformer for Temporal Sentence Grounding

Autor: Sun, Xiaolong, Shi, Liushuai, Wang, Le, Zhou, Sanping, Xia, Kun, Wang, Yabing, Hua, Gang

Temporal sentence grounding is a challenging task that aims to localize the moment spans relevant to a language description. Although recent DETR-based models have achieved notable progress by leveraging multiple learnable moment queries, they suffer

Externí odkaz: http://arxiv.org/abs/2406.00143

Zobrazit plný text záznamu

Report

Learning Discriminative Spatio-temporal Representations for Semi-supervised Action Recognition

Autor: Wang, Yu, Zhou, Sanping, Xia, Kun, Wang, Le

Semi-supervised action recognition aims to improve spatio-temporal reasoning ability with a few labeled data in conjunction with a large amount of unlabeled data. Albeit recent advancements, existing powerful methods are still prone to making ambiguo

Externí odkaz: http://arxiv.org/abs/2404.16416

Zobrazit plný text záznamu

Report

Boosting Semi-Supervised Temporal Action Localization by Learning from Non-Target Classes

Autor: Xia, Kun, Wang, Le, Zhou, Sanping, Hua, Gang, Tang, Wei

The crux of semi-supervised temporal action localization (SS-TAL) lies in excavating valuable information from abundant unlabeled videos. However, current approaches predominantly focus on building models that are robust to the error-prone target cla

Externí odkaz: http://arxiv.org/abs/2403.11189

Zobrazit plný text záznamu

Akademický článek

Ingredients-based Methodology and Fuzzy Logic Combined Short-Duration Heavy Rainfall Short-Range Forecasting: An Improved Scheme.

Autor: TIAN Fu-you¹, XIA Kun² xiakun@lasg.iap.ac.cn, SUN Jian-hua³, ZHENG Yong-guang¹, HUA Shan¹

Publikováno v: Journal of Tropical Meteorology. Sep2024, Vol. 30 Issue 3, p241-256. 16p.

Zobrazit plný text záznamu

Report

Learning to Refactor Action and Co-occurrence Features for Temporal Action Localization

Autor: Xia, Kun, Wang, Le, Zhou, Sanping, Zheng, Nanning, Tang, Wei

The main challenge of Temporal Action Localization is to retrieve subtle human actions from various co-occurring ingredients, e.g., context and background, in an untrimmed video. While prior approaches have achieved substantial progress through devis

Externí odkaz: http://arxiv.org/abs/2206.11493

Zobrazit plný text záznamu