Muhammad Aminul Islam

Muhammad Islam, Tao Huang, Euijoon Ahn et al.

This paper presents an in-depth survey on the use of multimodal Generative Artificial Intelligence (GenAI) and autoregressive Large Language Models (LLMs) for human motion understanding and generation, offering insights into emerging methods, architectures, and their potential to advance realistic and versatile motion synthesis. Focusing exclusively on text and motion modalities, this research investigates how textual descriptions can guide the generation of complex, human-like motion sequences. The paper explores various generative approaches, including autoregressive models, diffusion models, Generative Adversarial Networks (GANs), Variational Autoencoders (VAEs), and transformer-based models, by analyzing their strengths and limitations in terms of motion quality, computational efficiency, and adaptability. It highlights recent advances in text-conditioned motion generation, where textual inputs are used to control and refine motion outputs with greater precision. The integration of LLMs further enhances these models by enabling semantic alignment between instructions and motion, improving coherence and contextual relevance. This systematic survey underscores the transformative potential of text-to-motion GenAI and LLM architectures in applications such as healthcare, humanoids, gaming, animation, and assistive technologies, while addressing ongoing challenges in generating efficient and realistic human motion.

Derek Anderson, Matthew Deardorff, Timothy Havens et al.

The fuzzy integral is a powerful parametric nonlin-ear function with utility in a wide range of applications, from information fusion to classification, regression, decision making,interpolation, metrics, morphology, and beyond. While the fuzzy integral is in general a nonlinear operator, herein we show that it can be represented by a set of contextual linear order statistics(LOS). These operators can be obtained via sampling the fuzzy measure and clustering is used to produce a partitioning of the underlying space of linear convex sums. Benefits of our approach include scalability, improved integral/measure acquisition, generalizability, and explainable/interpretable models. Our methods are both demonstrated on controlled synthetic experiments, and also analyzed and validated with real-world benchmark data sets.

Muhammad Aminul Islam, Bryce Murray, Andrew Buck et al.

While most deep learning architectures are built on convolution, alternative foundations like morphology are being explored for purposes like interpretability and its connection to the analysis and processing of geometric structures. The morphological hit-or-miss operation has the advantage that it takes into account both foreground and background information when evaluating target shape in an image. Herein, we identify limitations in existing hit-or-miss neural definitions and we formulate an optimization problem to learn the transform relative to deeper architectures. To this end, we model the semantically important condition that the intersection of the hit and miss structuring elements (SEs) should be empty and we present a way to express Don't Care (DNC), which is important for denoting regions of an SE that are not relevant to detecting a target pattern. Our analysis shows that convolution, in fact, acts like a hit-miss transform through semantic interpretation of its filter differences. On these premises, we introduce an extension that outperforms conventional convolution on benchmark data. Quantitative experiments are provided on synthetic and benchmark data, showing that the direct encoding hit-or-miss transform provides better interpretability on learned shapes consistent with objects whereas our morphologically inspired generalized convolution yields higher classification accuracy. Last, qualitative hit and miss filter visualizations are provided relative to single morphological layer.

Muhammad Aminul Islam, Derek T. Anderson, Anthony J. Pinar et al.

Information fusion is an essential part of numerous engineering systems and biological functions, e.g., human cognition. Fusion occurs at many levels, ranging from the low-level combination of signals to the high-level aggregation of heterogeneous decision-making processes. While the last decade has witnessed an explosion of research in deep learning, fusion in neural networks has not observed the same revolution. Specifically, most neural fusion approaches are ad hoc, are not understood, are distributed versus localized, and/or explainability is low (if present at all). Herein, we prove that the fuzzy Choquet integral (ChI), a powerful nonlinear aggregation function, can be represented as a multi-layer network, referred to hereafter as ChIMP. We also put forth an improved ChIMP (iChIMP) that leads to a stochastic gradient descent-based optimization in light of the exponential number of ChI inequality constraints. An additional benefit of ChIMP/iChIMP is that it enables eXplainable AI (XAI). Synthetic validation experiments are provided and iChIMP is applied to the fusion of a set of heterogeneous architecture deep models in remote sensing. We show an improvement in model accuracy and our previously established XAI indices shed light on the quality of our data, model, and its decisions.