no code implementations • 15 Feb 2024 • Momir Adžemović, Predrag Tadić, Andrija Petrović, Mladen Nikolić
We further propose a new cost function for associating observations with tracks.
Ranked #2 on Multi-Object Tracking on SportsMOT (using extra training data)
no code implementations • 13 Jun 2022 • Djordje Božić, Predrag Tadić, Mladen Nikolić
Options represent a framework for reasoning across multiple time scales in reinforcement learning (RL).
no code implementations • NeurIPS 2021 • Andreea Deac, Petar Veličković, Ognjen Milinković, Pierre-Luc Bacon, Jian Tang, Mladen Nikolić
We find that prior approaches either assume that the environment is provided in such a tabular form -- which is highly restrictive -- or infer "local neighbourhoods" of states to run value iteration over -- for which we discover an algorithmic bottleneck effect.
no code implementations • 15 Nov 2020 • Andrija Petrović, Mladen Nikolić, Sandro Radovanović, Boris Delibašić, Miloš Jovanović
In this paper we propose a Fair Adversarial Instance Re-weighting (FAIR) method, which uses adversarial training to learn instance weighting function that ensures fair predictions.
no code implementations • 25 Oct 2020 • Andreea Deac, Petar Veličković, Ognjen Milinković, Pierre-Luc Bacon, Jian Tang, Mladen Nikolić
Value Iteration Networks (VINs) have emerged as a popular method to incorporate planning algorithms within deep reinforcement learning, enabling performance improvements on tasks requiring long-range reasoning and understanding of environment dynamics.
no code implementations • 24 Jul 2020 • Stefan Spalević, Petar Veličković, Jovana Kovačević, Mladen Nikolić
Protein function prediction may be framed as predicting subgraphs (with certain closure properties) of a directed acyclic graph describing the hierarchy of protein functions.
no code implementations • 31 Jan 2019 • Andrija Petrović, Mladen Nikolić, Miloš Jovanović, Boris Delibašić
The extended method of local variational approximation of sigmoid function is used for solving empirical Bayes in Bayesian GCRFBCb variant, whereas MAP value of latent variables is the basis for learning and inference in the GCRFBCnb variant.
no code implementations • 8 May 2015 • Mirko Stojadinović, Mladen Nikolić, Filip Marić
However, there is no single solver (nor approach) that performs well on all classes of problems and many portfolio approaches for selecting a suitable solver based on simple syntactic features of the input CSP instance have been developed.