arXiv subjects

Muhammad Rameez Ur Rahman

Publications and source records attributed to Muhammad Rameez Ur Rahman.

6 recordsLinked to original sources

arXiv2025

Alloy-Driven Verification of Object-Centric Event Data: From Temporal Logic to Knowledge Graphs

Object-centric process mining addresses the limitations of traditional approaches, which often involve the lossy flattening of event data and obscure vital relationships among interacting objects. This paper presents a novel formal framework for Object-centric Event Data (OCED) that ensures the correctness of the meta-model and preserves native object-centric semantics prior to the system implementation. Our approach effectively leverages Alloy for precisely specifying temporal properties and structural relationships between objects and events. This guarantees thorough verification against predefined OCED constraints such as cross-object cardinality bounds and time-aware consistency rules, hence preventing common data integrity issues. We demonstrate the effectiveness of the proposed framework in discovering and validating implicit object dependencies in event logs, particularly when importing data into graph databases like Neo4j. This demonstrates how formal verification can avoid pitfalls that lead to data invisibility and improve knowledge graph creation, enrichment, and querying. To bridge theory and practice, our verified \emph{FOCED} is made accessible through automatically generated Python bindings, empowering industrial users without formal methods expertise. The code is available on GitHub \footnote{https://github.com/sabalati/FOCED}

cs.FL↗

arXiv2025

Object-Centric Analysis of XES Event Logs: Integrating OCED Modeling with SPARQL Queries

Object Centric Event Data (OCED) has gained attention in recent years within the field of process mining. However, there are still many challenges, such as connecting the XES format to object-centric approaches to enable more insightful analysis. It is important for a process miner to understand the insights and dependencies of events in the event log to see what is going on in our processes. In previous standards, the dependencies of event logs are only used to show events, but not their dependencies among each other and actions in detail as described in OCEDO. There is more information in the event log when it is revealed using the OCEDO model. It becomes more understandable and easier to grasp the concepts and deal with the processes. This paper proposes the use of Object-Centric Event Data Ontology (OCEDO) to overcome the limitations of the XES standard in event logs for process mining. We demonstrate how the OCEDO approach, integrated with SPARQL queries, can be applied to the BPIC 2013 dataset to make the relationships between events and objects more explicit. It describes dealing with the meta descriptions of the OCEDO model on a business process challenge as an event log. It improves the completeness and readability of process data, suggesting that object-centric modeling allows for richer analyses than traditional approaches.

cs.DB↗

arXiv2025

ECAM: A Contrastive Learning Approach to Avoid Environmental Collision in Trajectory Forecasting

Human trajectory forecasting is crucial in applications such as autonomous driving, robotics and surveillance. Accurate forecasting requires models to consider various factors, including social interactions, multi-modal predictions, pedestrian intention and environmental context. While existing methods account for these factors, they often overlook the impact of the environment, which leads to collisions with obstacles. This paper introduces ECAM (Environmental Collision Avoidance Module), a contrastive learning-based module to enhance collision avoidance ability with the environment. The proposed module can be integrated into existing trajectory forecasting models, improving their ability to generate collision-free predictions. We evaluate our method on the ETH/UCY dataset and quantitatively and qualitatively demonstrate its collision avoidance capabilities. Our experiments show that state-of-the-art methods significantly reduce (-40/50%) the collision rate when integrated with the proposed module. The code is available at https://github.com/CVML-CFU/ECAM.

cs.CV↗

arXiv2024

OVOSE: Open-Vocabulary Semantic Segmentation in Event-Based Cameras

Event cameras, known for low-latency operation and superior performance in challenging lighting conditions, are suitable for sensitive computer vision tasks such as semantic segmentation in autonomous driving. However, challenges arise due to limited event-based data and the absence of large-scale segmentation benchmarks. Current works are confined to closed-set semantic segmentation, limiting their adaptability to other applications. In this paper, we introduce OVOSE, the first Open-Vocabulary Semantic Segmentation algorithm for Event cameras. OVOSE leverages synthetic event data and knowledge distillation from a pre-trained image-based foundation model to an event-based counterpart, effectively preserving spatial context and transferring open-vocabulary semantic segmentation capabilities. We evaluate the performance of OVOSE on two driving semantic segmentation datasets DDD17, and DSEC-Semantic, comparing it with existing conventional image open-vocabulary models adapted for event-based data. Similarly, we compare OVOSE with state-of-the-art methods designed for closed-set settings in unsupervised domain adaptation for event-based semantic segmentation. OVOSE demonstrates superior performance, showcasing its potential for real-world applications. The code is available at https://github.com/ram95d/OVOSE.

cs.CV↗

arXiv2023

Best Practices for 2-Body Pose Forecasting

The task of collaborative human pose forecasting stands for predicting the future poses of multiple interacting people, given those in previous frames. Predicting two people in interaction, instead of each separately, promises better performance, due to their body-body motion correlations. But the task has remained so far primarily unexplored. In this paper, we review the progress in human pose forecasting and provide an in-depth assessment of the single-person practices that perform best for 2-body collaborative motion forecasting. Our study confirms the positive impact of frequency input representations, space-time separable and fully-learnable interaction adjacencies for the encoding GCN and FC decoding. Other single-person practices do not transfer to 2-body, so the proposed best ones do not include hierarchical body modeling or attention-based interaction encoding. We further contribute a novel initialization procedure for the 2-body spatial interaction parameters of the encoder, which benefits performance and stability. Altogether, our proposed 2-body pose forecasting best practices yield a performance improvement of 21.9% over the state-of-the-art on the most recent ExPI dataset, whereby the novel initialization accounts for 3.5%. See our project page at https://www.pinlab.org/bestpractices2body

cs.CV↗

arXiv2021

Adversarial Branch Architecture Search for Unsupervised Domain Adaptation

Unsupervised Domain Adaptation (UDA) is a key issue in visual recognition, as it allows to bridge different visual domains enabling robust performances in the real world. To date, all proposed approaches rely on human expertise to manually adapt a given UDA method (e.g. DANN) to a specific backbone architecture (e.g. ResNet). This dependency on handcrafted designs limits the applicability of a given approach in time, as old methods need to be constantly adapted to novel backbones. Existing Neural Architecture Search (NAS) approaches cannot be directly applied to mitigate this issue, as they rely on labels that are not available in the UDA setting. Furthermore, most NAS methods search for full architectures, which precludes the use of pre-trained models, essential in a vast range of UDA settings for reaching SOTA results. To the best of our knowledge, no prior work has addressed these aspects in the context of NAS for UDA. Here we tackle both aspects with an Adversarial Branch Architecture Search for UDA (ABAS): i. we address the lack of target labels by a novel data-driven ensemble approach for model selection; and ii. we search for an auxiliary adversarial branch, attached to a pre-trained backbone, which drives the domain alignment. We extensively validate ABAS to improve two modern UDA techniques, DANN and ALDA, on three standard visual recognition datasets (Office31, Office-Home and PACS). In all cases, ABAS robustly finds the adversarial branch architectures and parameters which yield best performances.

cs.CV↗