Zobrazeno 1 - 10
of 188
pro vyhledávání: '"Ye, Mang"'
Publikováno v:
International Joint Conference on Artificial Intelligence (IJCAI), 2023
Federated graph learning collaboratively learns a global graph neural network with distributed graphs, where the non-independent and identically distributed property is one of the major challenges. Most relative arts focus on traditional distributed
Externí odkaz:
http://arxiv.org/abs/2406.18937
Multi-modal large language models (MLLMs) have achieved remarkable performance on objective multimodal perception tasks, but their ability to interpret subjective, emotionally nuanced multimodal content remains largely unexplored. Thus, it impedes th
Externí odkaz:
http://arxiv.org/abs/2406.16442
Pre-training has emerged as a simple yet powerful methodology for representation learning across various domains. However, due to the expensive training cost and limited data, pre-training has not yet been extensively studied in correspondence prunin
Externí odkaz:
http://arxiv.org/abs/2406.05773
Federated learning (FL) has emerged as a new paradigm for privacy-preserving collaborative training. Under domain skew, the current FL approaches are biased and face two fairness problems. 1) Parameter Update Conflict: data disparity among clients le
Externí odkaz:
http://arxiv.org/abs/2405.16585
Vertical Federated Learning (VFL) is a privacy-preserving distributed learning paradigm where different parties collaboratively learn models using partitioned features of shared samples, without leaking private data. Recent research has shown promisi
Externí odkaz:
http://arxiv.org/abs/2405.17495
In Re-identification (ReID), recent advancements yield noteworthy progress in both unimodal and cross-modal retrieval tasks. However, the challenge persists in developing a unified framework that could effectively handle varying multimodal data, incl
Externí odkaz:
http://arxiv.org/abs/2405.04741
Text-based person search (TBPS) aims to retrieve images of a specific person from a large image gallery based on a natural language description. Existing methods rely on massive annotated image-text data to achieve satisfactory performance in fully-s
Externí odkaz:
http://arxiv.org/abs/2404.18106
Cross-modal noise-robust learning is a challenging task since noisy correspondence is hard to recognize and rectify. Due to the cumulative and unavoidable negative impact of unresolved noise, existing methods cannot maintain a stable performance when
Externí odkaz:
http://arxiv.org/abs/2312.05777
Federated learning has emerged as a promising paradigm for privacy-preserving collaboration among different parties. Recently, with the popularity of federated learning, an influx of approaches have delivered towards different realistic challenges. I
Externí odkaz:
http://arxiv.org/abs/2311.06750
Recognizing a target of interest from the UAVs is much more challenging than the existing object re-identification tasks across multiple city cameras. The images taken by the UAVs usually suffer from significant size difference when generating the ob
Externí odkaz:
http://arxiv.org/abs/2311.02559