Zobrazeno 1 - 10
of 335
pro vyhledávání: '"Worring, Marcel"'
We propose Set2Seq Transformer, a novel sequential multiple instance architecture, that learns to rank permutation aware set representations of sequences. First, we illustrate that learning temporal position-aware representations of discrete timestep
Externí odkaz:
http://arxiv.org/abs/2408.03404
Autor:
Zheng, Yijia, Worring, Marcel
Hypergraphs are widely employed to represent complex higher-order relationships in real-world applications. Most hypergraph learning research focuses on node- or edge-level tasks. A practically relevant but more challenging task, edge-dependent node
Externí odkaz:
http://arxiv.org/abs/2405.14286
Autor:
Wang, Shuai, Zhang, David W., Huang, Jia-Hong, Rudinac, Stevan, Kackovic, Monika, Wijnberg, Nachoem, Worring, Marcel
Hypergraphs serve as an effective model for depicting complex connections in various real-world scenarios, from social to biological networks. The development of Hypergraph Neural Networks (HGNNs) has emerged as a valuable method to manage the intric
Externí odkaz:
http://arxiv.org/abs/2405.13372
This paper proposes \textit{GO4Align}, a multi-task optimization approach that tackles task imbalance by explicitly aligning the optimization across tasks. To achieve this, we design an adaptive group risk minimization strategy, compromising two cruc
Externí odkaz:
http://arxiv.org/abs/2404.06486
The aim of video summarization is to shorten videos automatically while retaining the key information necessary to convey the overall story. Video summarization methods mainly rely on visual factors, such as visual consecutiveness and diversity, whic
Externí odkaz:
http://arxiv.org/abs/2311.12159
This paper focuses on the data-insufficiency problem in multi-task learning within an episodic training setup. Specifically, we explore the potential of heterogeneous information across tasks and meta-knowledge among episodes to effectively tackle ea
Externí odkaz:
http://arxiv.org/abs/2310.18713
Autor:
Derakhshani, Mohammad Mahdi, Najdenkoska, Ivona, Snoek, Cees G. M., Worring, Marcel, Asano, Yuki M.
We present Self-Context Adaptation (SeCAt), a self-supervised approach that unlocks few-shot abilities for open-ended classification with small visual language models. Our approach imitates image captions in a self-supervised way based on clustering
Externí odkaz:
http://arxiv.org/abs/2310.00500
Autor:
Wang, Shuai, Shen, Jiayi, Efthymiou, Athanasios, Rudinac, Stevan, Kackovic, Monika, Wijnberg, Nachoem, Worring, Marcel
The variety and complexity of relations in multimedia data lead to Heterogeneous Information Networks (HINs). Capturing the semantics from such networks requires approaches capable of utilizing the full richness of the HINs. Existing methods for mode
Externí odkaz:
http://arxiv.org/abs/2309.13092
In high-stakes settings, Machine Learning models that can provide predictions that are interpretable for humans are crucial. This is even more true with the advent of complex deep learning based models with a huge number of tunable parameters. Recent
Externí odkaz:
http://arxiv.org/abs/2309.11155
The way we analyse clinical texts has undergone major changes over the last years. The introduction of language models such as BERT led to adaptations for the (bio)medical domain like PubMedBERT and ClinicalBERT. These models rely on large databases
Externí odkaz:
http://arxiv.org/abs/2309.00917