arXiv subjects

Mayank Patel

Publications and source records attributed to Mayank Patel.

12 recordsLinked to original sources

arXiv2026

MechVerse: Evaluating Physical Motion Consistency in Video Generation Models

Text- and image-conditioned video generation models have achieved strong visual fidelity and temporal coherence, but they often fail to generate motion governed by kinematic and geometric constraints. In these settings, object parts must remain rigid, maintain contact or coupling with neighboring components, and transfer motion consistently across connected parts. These requirements are especially explicit in articulated mechanical assemblies, where motion is constrained by rigid-link geometry, contact/coupling relations, and transmission through kinematic chains. A generated video may therefore appear plausible while violating the intended mechanism, such as rotating a part that should translate, deforming a rigid component, breaking coupling between parts, or failing to move downstream components. To evaluate this gap, We introduce MechVerse, a benchmark for mechanically consistent image-to-video generation. MechVerse contains 21,156 synthetic clips from 1,357 mechanical assemblies across 141 categories, organized into three tiers of increasing kinematic complexity: independent articulation, pairwise coupling, and densely coupled multi-part mechanisms. Each clip is paired with a structured prompt describing part identities, stationary supports, moving components, motion primitives, direction, speed/extent, and inter-part dependencies. We evaluate proprietary, open-source, and fine-tuned image-to-video models using standard video metrics, instruction-following scores, and human judgments of motion correctness and kinematic coupling. Results show that current models can preserve appearance and smoothness while failing to generate mechanically admissible motion, with errors increasing as coupling complexity grows. MechVerse provides a benchmark for measuring and improving mechanism-aware video generation from image and language inputs.

cs.CV↗

arXiv2026

Exploring Vision-Language Models for Open-Vocabulary Zero-Shot Action Segmentation

Temporal Action Segmentation (TAS) requires dividing videos into action segments, yet the vast space of activities and alternative breakdowns makes collecting comprehensive datasets infeasible. Existing methods remain limited to closed vocabularies and fixed label sets. In this work, we explore the largely unexplored problem of Open-Vocabulary Zero-Shot Temporal Action Segmentation (OVTAS) by leveraging the strong zero-shot capabilities of Vision-Language Models (VLMs). We introduce a training-free pipeline that follows a segmentation-by-classification design: Frame-Action Embedding Similarity (FAES) matches video frames to candidate action labels, and Similarity-Matrix Temporal Segmentation (SMTS) enforces temporal consistency. Beyond proposing OVTAS, we present a systematic study across 14 diverse VLMs, providing the first broad analysis of their suitability for open-vocabulary action segmentation. Experiments on standard benchmarks show that OVTAS achieves strong results without task-specific supervision, underscoring the potential of VLMs for structured temporal understanding.

cs.CV↗

arXiv2025

DYNAMO: Dependency-Aware Deep Learning Framework for Articulated Assembly Motion Prediction

Understanding the motion of articulated mechanical assemblies from static geometry remains a core challenge in 3D perception and design automation. Prior work on everyday articulated objects such as doors and laptops typically assumes simplified kinematic structures or relies on joint annotations. However, in mechanical assemblies like gears, motion arises from geometric coupling, through meshing teeth or aligned axes, making it difficult for existing methods to reason about relational motion from geometry alone. To address this gap, we introduce MechBench, a benchmark dataset of 693 diverse synthetic gear assemblies with part-wise ground-truth motion trajectories. MechBench provides a structured setting to study coupled motion, where part dynamics are induced by contact and transmission rather than predefined joints. Building on this, we propose DYNAMO, a dependency-aware neural model that predicts per-part SE(3) motion trajectories directly from segmented CAD point clouds. Experiments show that DYNAMO outperforms strong baselines, achieving accurate and temporally consistent predictions across varied gear configurations. Together, MechBench and DYNAMO establish a novel systematic framework for data-driven learning of coupled mechanical motion in CAD assemblies.

cs.CV↗

arXiv2025

A Study of Anatomical Priors for Deep Learning-Based Segmentation of Pheochromocytoma in Abdominal CT

Accurate segmentation of pheochromocytoma (PCC) in abdominal CT scans is essential for tumor burden estimation, prognosis, and treatment planning. It may also help infer genetic clusters, reducing reliance on expensive testing. This study systematically evaluates anatomical priors to identify configurations that improve deep learning-based PCC segmentation. We employed the nnU-Net framework to evaluate eleven annotation strategies for accurate 3D segmentation of pheochromocytoma, introducing a set of novel multi-class schemes based on organ-specific anatomical priors. These priors were derived from adjacent organs commonly surrounding adrenal tumors (e.g., liver, spleen, kidney, aorta, adrenal gland, and pancreas), and were compared against a broad body-region prior used in previous work. The framework was trained and tested on 105 contrast-enhanced CT scans from 91 patients at the NIH Clinical Center. Performance was measured using Dice Similarity Coefficient (DSC), Normalized Surface Distance (NSD), and instance-wise F1 score. Among all strategies, the Tumor + Kidney + Aorta (TKA) annotation achieved the highest segmentation accuracy, significantly outperforming the previously used Tumor + Body (TB) annotation across DSC (p = 0.0097), NSD (p = 0.0110), and F1 score (25.84% improvement at an IoU threshold of 0.5), measured on a 70-30 train-test split. The TKA model also showed superior tumor burden quantification (R^2 = 0.968) and strong segmentation across all genetic subtypes. In five-fold cross-validation, TKA consistently outperformed TB across IoU thresholds (0.1 to 0.5), reinforcing its robustness and generalizability. These findings highlight the value of incorporating relevant anatomical context into deep learning models to achieve precise PCC segmentation, offering a valuable tool to support clinical assessment and longitudinal disease monitoring in PCC patients.

eess.IV↗

arXiv2025

A Hybrid Heuristic Framework for Resource-Efficient Querying of Scientific Experiments Data

Scientific experiments and modern applications are generating large amounts of data every day. Most organizations utilize In-house servers or Cloud resources to manage application data and workload. The traditional database management system (DBMS) and HTAP systems spend significant time & resources to load the entire dataset into DBMS before starting query execution. On the other hand, in-situ engines may reparse required data multiple times, increasing resource utilization and data processing costs. Additionally, over or under-allocation of resources also increases application running costs. This paper proposes a lightweight Resource Availability &Workload aware Hybrid Framework (RAW-HF) to optimize querying raw data by utilizing existing finite resources efficiently. RAW-HF includes modules that help optimize the resources required to execute a given workload and maximize the utilization of existing resources. The impact of applying RAW-HF to real-world scientific dataset workloads like Sloan Digital Sky Survey (SDSS) and Linked Observation Data (LOD) presented over 90% and 85% reduction in workload execution time (WET) compared to widely used traditional DBMS PostgreSQL. The overall CPU, IO resource utilization, and WET have been reduced by 26%, 25%, and 26%, respectively, while improving memory utilization by 33%, compared to the state-of-the-art workload-aware partial loading technique (WA) proposed for hybrid systems. A comparison of MUAR technique used by RAW-HF with machine learning based resource allocation techniques like PCC is also presented.

cs.DB↗

arXiv2025

Interactive authoring of outcome-oriented lesson plans for immersive Virtual Reality training

Immersive Virtual Reality (iVR) applications have shown immense potential for skill training and learning in manufacturing. However, authoring of such applications requires technical expertise, which makes it difficult for educators to author instructions targeted at desired learning outcomes. We present FlowTrainer, an LLM-assisted interactive system to allow educators to author lesson plans for their iVR instruction based on desired goals. The authoring workflow is supported by Backward design to align the planned lesson based on the desired outcomes. We implemented a welding use case and conducted a user study with welding experts to test the effectiveness of the system in authoring outcome-oriented lesson plans. The study results showed that the system allowed users to plan lesson plans based on desired outcomes while reducing the time and technical expertise required for the authoring process. We believe that such efforts can allow widespread adoption of iVR solutions in manufacturing training to meet the workforce demands in the industry.

cs.HC↗

arXiv2025

Virtual Reality in Manufacturing Education: A Scoping Review Indicating State-of-the-Art, Benefits, and Challenges Across Domains, Levels, and Entities

To address the shortage of a skilled workforce in the U.S. manufacturing industry, immersive Virtual Reality (VR)-based training solutions hold promising potential. To effectively utilize VR to meet workforce demands, it is important to understand the role of VR in manufacturing education. Therefore, we conduct a scoping review in the field. As a first step, we used a 5W1H (What, Where, Who, When, Why, How) formula as a problem-solving approach to define a comprehensive taxonomy that can consider the role of VR from all relevant possibilities. Our taxonomy categorizes VR applications across three key aspects: (1) Domains, (2) Levels, and (3) Entities. Using a systematic literature search and analysis, we reviewed 108 research articles to find the current state, benefits, challenges, and future opportunities of VR in the field. It was found that VR has been explored in a variety of areas and provides numerous benefits to learners. Despite these benefits, its adoption in manufacturing education is limited. This review discusses the identified barriers and provides actionable insights to address them. These insights can enable the widespread usage of immersive technology to nurture and develop a workforce equipped with the skills required to excel in the evolving landscape of manufacturing.

cs.HC↗

arXiv2024

avaTTAR: Table Tennis Stroke Training with On-body and Detached Visualization in Augmented Reality

Table tennis stroke training is a critical aspect of player development. We designed a new augmented reality (AR) system, avaTTAR, for table tennis stroke training. The system provides both "on-body" (first-person view) and "detached" (third-person view) visual cues, enabling users to visualize target strokes and correct their attempts effectively with this dual perspectives setup. By employing a combination of pose estimation algorithms and IMU sensors, avaTTAR captures and reconstructs the 3D body pose and paddle orientation of users during practice, allowing real-time comparison with expert strokes. Through a user study, we affirm avaTTAR's capacity to amplify player experience and training results.

cs.HC↗

arXiv2024

A Comparative Study of Garment Draping Techniques

We present a comparison review that evaluates popular techniques for garment draping for 3D fashion design, virtual try-ons, and animations. A comparative study is performed between various methods for garment draping of clothing over the human body. These include numerous models, such as physics and machine learning based techniques, collision handling, and more. Performance evaluations and trade-offs are discussed to ensure informed decision-making when choosing the most appropriate approach. These methods aim to accurately represent deformations and fine wrinkles of digital garments, considering the factors of data requirements, and efficiency, to produce realistic results. The research can be insightful to researchers, designers, and developers in visualizing dynamic multi-layered 3D clothing.

cs.GR↗

arXiv2024

Weakly Supervised Detection of Pheochromocytomas and Paragangliomas in CT

Pheochromocytomas and Paragangliomas (PPGLs) are rare adrenal and extra-adrenal tumors which have the potential to metastasize. For the management of patients with PPGLs, CT is the preferred modality of choice for precise localization and estimation of their progression. However, due to the myriad variations in size, morphology, and appearance of the tumors in different anatomical regions, radiologists are posed with the challenge of accurate detection of PPGLs. Since clinicians also need to routinely measure their size and track their changes over time across patient visits, manual demarcation of PPGLs is quite a time-consuming and cumbersome process. To ameliorate the manual effort spent for this task, we propose an automated method to detect PPGLs in CT studies via a proxy segmentation task. As only weak annotations for PPGLs in the form of prospectively marked 2D bounding boxes on an axial slice were available, we extended these 2D boxes into weak 3D annotations and trained a 3D full-resolution nnUNet model to directly segment PPGLs. We evaluated our approach on a dataset consisting of chest-abdomen-pelvis CTs of 255 patients with confirmed PPGLs. We obtained a precision of 70% and sensitivity of 64.1% with our proposed approach when tested on 53 CT studies. Our findings highlight the promising nature of detecting PPGLs via segmentation, and furthers the state-of-the-art in this exciting yet challenging area of rare cancer management.

eess.IV↗

arXiv2022

Resource Utilization Monitoring for Raw Data Query Processing

Scientific experiments, simulations, and modern applications generate large amounts of data. Data is stored in raw format to avoid the high loading time of traditional database management systems. Researchers have proposed many techniques to improve query execution time for raw data and reduce data loading time for traditional systems. The core of all the proposed techniques is efficient utilization of resources by processing only required data or reducing operations on data. The processed data caching in the main memory or disk can resolve this issue and avoid repeated processing of data. However, limitations of resources like main memory space, storage IO speeds, and additional storage space requirements on disk need to be considered to provide reliable and scalable solutions for cloud or in-house deployments. This paper presents improvements to the raw data query processing framework by integrating a resource monitoring module. The experiments were performed using a scientific dataset known Sloan Digital Sky Survey (SDSS). Analysis of monitored resources revealed that sampling queries had the lowest resource utilization. The PostgresRAW can answer simple 0-JOIN queries faster than PostgreSQL. While one or more JOIN complex queries need to be answered using PostgreSQL to reduce workload execution time (WET). The results section discusses resource requirements of simple, complex, and sampling type queries. The result analysis of query types and resource utilization patterns assisted in proposing Query Complexity Aware (QCA) and Resource Utilization Aware (RUA) data partitioning techniques for raw engines and DBMS to reduce cost or data to result time.

cs.DB↗

arXiv2022

Query Complexity Based Optimal Processing of Raw Data

The paper aims to find an efficient way for processing large datasets having different types of workload queries with minimal replication. The work first identifies the complexity of queries best suited for the given data processing tool . The paper proposes Query Complexity Aware partitioning technique QCA with a lightweight query identification and partitioning algorithm. Different replication approaches have been studied to cover more use-cases for different application workloads. The technique is demonstrated using a scientific dataset known as Sloan Digital Sky Survey SDSS. The results show workload execution time WET reduced by 94.6% using only 6.7% of the dataset in loaded format compared to the original dataset. The QCA technique also reduced multi-node replication by 5.8x times compared to state-of-the-art workload aware WA techniques. The multi-node and multi-core execution of workload using QCA proposed partitions reduced WET by 42.66% and 25.46% compared to WA.

cs.DB↗