Zobrazeno 1 - 10
of 86
pro vyhledávání: '"Petrović, Andrija"'
The goal of multi-object tracking is to detect and track all objects in a scene while maintaining unique identifiers for each, by associating their bounding boxes across video frames. This association relies on matching motion and appearance patterns
Externí odkaz:
http://arxiv.org/abs/2407.00738
Traditional tracking-by-detection systems typically employ Kalman filters (KF) for state estimation. However, the KF requires domain-specific design choices and it is ill-suited to handling non-linear motion patterns. To address these limitations, we
Externí odkaz:
http://arxiv.org/abs/2402.09865
We present a method to integrate Large Language Models (LLMs) and traditional tabular data classification techniques, addressing LLMs challenges like data serialization sensitivity and biases. We introduce two strategies utilizing LLMs for ranking ca
Externí odkaz:
http://arxiv.org/abs/2311.11628
Autor:
Zhu, Max, Kobalczyk, Katarzyna, Petrovic, Andrija, Nikolic, Mladen, van der Schaar, Mihaela, Delibasic, Boris, Lio, Petro
Despite the prevalence of tabular datasets, few-shot learning remains under-explored within this domain. Existing few-shot methods are not directly applicable to tabular datasets due to varying column relationships, meanings, and permutational invari
Externí odkaz:
http://arxiv.org/abs/2311.10051
Synthetic data serves as an alternative in training machine learning models, particularly when real-world data is limited or inaccessible. However, ensuring that synthetic data mirrors the complex nuances of real-world data is a challenging task. Thi
Externí odkaz:
http://arxiv.org/abs/2310.16981
Autor:
Bisercic, Aleksa, Nikolic, Mladen, van der Schaar, Mihaela, Delibasic, Boris, Lio, Pietro, Petrovic, Andrija
Tabular data is often hidden in text, particularly in medical diagnostic reports. Traditional machine learning (ML) models designed to work with tabular data, cannot effectively process information in such form. On the other hand, large language mode
Externí odkaz:
http://arxiv.org/abs/2306.05052
With growing awareness of societal impact of artificial intelligence, fairness has become an important aspect of machine learning algorithms. The issue is that human biases towards certain groups of population, defined by sensitive features like race
Externí odkaz:
http://arxiv.org/abs/2011.07495
Autor:
Vasic, Marko, Petrovic, Andrija, Wang, Kaiyuan, Nikolic, Mladen, Singh, Rishabh, Khurshid, Sarfraz
Publikováno v:
Neural Networks, Volume 151, 2022, Pages 34-47
Rapid advancements in deep learning have led to many recent breakthroughs. While deep learning models achieve superior performance, often statistically better than humans, their adoption into safety-critical settings, such as healthcare or self-drivi
Externí odkaz:
http://arxiv.org/abs/1906.06717
Gaussian conditional random fields (GCRF) are a well-known used structured model for continuous outputs that uses multiple unstructured predictors to form its features and at the same time exploits dependence structure among outputs, which is provide
Externí odkaz:
http://arxiv.org/abs/1902.00045
Publikováno v:
In Engineering Applications of Artificial Intelligence March 2023 119
