Maksim Lapin — accepted AI-conference papers

2025

Stable Cinemetrics : Structured Taxonomy and Evaluation for Professional Video Generation

Agneet Chatterjee, Rahim Entezari, Maksym Zhuravinskyi, Maksim Lapin, Reshinth Adithyan, Amit Raj +3

NeurIPS 2025poster

Recent advances in video generation have enabled high-fidelity video synthesis from user provided prompts. However, existing models and benchmarks fail to capture the complexity and requirements of professional video generation. Towards that goal, we introduce Stable Cinemetrics, a structured evalua…

Cited by 0 Source ↗Scholar ↗

2016

Loss Functions for Top-k Error: Analysis and Insights

Maksim Lapin, Matthias Hein, Bernt Schiele

CVPR 2016poster

In order to push the performance on realistic computer vision tasks, the number of classes in modern benchmark datasets has significantly increased in recent years. This increase in the number of classes comes along with increased ambiguity between the class labels, raising the question if top-1 err…

Cited by 118 PDF ↗code ↗Scholar ↗

2015

Efficient Output Kernel Learning for Multiple Tasks

Pratik Kumar Jawanpuria, Maksim Lapin, Matthias Hein, Bernt Schiele

NeurIPS 2015poster

The paradigm of multi-task learning is that one can achieve better generalization by learning tasks jointly and thus exploiting the similarity between the tasks rather than learning them independently of each other. While previously the relationship between tasks had to be user-defined in the form o…

Cited by 39 Source ↗PDF ↗Scholar ↗

2015

Top-k Multiclass SVM

Maksim Lapin, Matthias Hein, Bernt Schiele

NeurIPS 2015spotlight

Class ambiguity is typical in image classification problems with a large number of classes. When classes are difficult to discriminate, it makes sense to allow k guesses and evaluate classifiers based on the top-k error instead of the standard zero-one loss. We propose top-k multiclass SVM as a dire…

Cited by 121 Source ↗PDF ↗code ↗Scholar ↗