Related papers: Visualizing Representational Dynamics with Multidi…

In neuroimaging, extensive post-processing of resting-state functional MRI (rfMRI) data is necessary for its application and investigation in relation to brain-behavior associations. Such post-processing is used to derive brain…

The scalability of a particular visualization approach is limited by the ability for people to discern differences between plots made with different datasets. Ideally, when the data changes, the visualization changes in perceptible ways.…

Human Motion Segmentation (HMS), which aims to partition a video into non-overlapping segments corresponding to different human motions, has recently attracted increasing research attention. Existing HMS approaches are predominantly based…

Multimodal sentiment analysis (MSA) is a fundamental complex research problem due to the heterogeneity gap between different modalities and the ambiguity of human emotional expression. Although there have been many successful attempts to…

The recent success of implicit neural scene representations has presented a viable new method for how we capture and store 3D scenes. Unlike conventional 3D representations, such as point clouds, which explicitly store scene properties in…

Latent representations learned by neural networks often exhibit semantic structure, where concept similarity is reflected by geometric proximity in embedding space. However, comparing such spaces across models remains difficult: changes in…

Most contemporary robots have depth sensors, and research on semantic segmentation with RGBD images has shown that depth images boost the accuracy of segmentation. Since it is time-consuming to annotate images with semantic labels per…

Dimensionality reduction techniques play important roles in the analysis of big data. Traditional dimensionality reduction approaches, such as principal component analysis (PCA) and linear discriminant analysis (LDA), have been studied…

Remote sensing image segmentation faces persistent challenges in distinguishing morphologically similar categories and adapting to diverse scene variations. While existing methods rely on implicit representation learning paradigms, they…

Deep predictive coding networks are neuroscience-inspired unsupervised learning models that learn to predict future sensory states. We build upon the PredNet implementation by Lotter, Kreiman, and Cox (2016) to investigate if predictive…

Data stream clustering reveals patterns within continuously arriving, potentially unbounded data sequences. Numerous data stream algorithms have been proposed to cluster data streams. The existing data stream clustering algorithms still…

High-dimensional datasets are well-approximated by low-dimensional structures. Over the past decade, this empirical observation motivated the investigation of detection, measurement, and modeling techniques to exploit these low-dimensional…

This paper investigates robust representation learning in offline goal-conditioned reinforcement learning (GCRL). Particularly in sparse reward scenarios, learning representations that align state and goal latents is a challenge that…

Large-scale electrophysiological recordings now allow simultaneous monitoring of thousands of neurons across multiple brain regions, revealing structured variability in neural population activity. Understanding how these collective patterns…

The bundle of geometry and appearance in computer vision has proven to be a promising solution for robots across a wide variety of applications. Stereo cameras and RGB-D sensors are widely used to realise fast 3D reconstruction and…

Recent vision-language pre-training models have exhibited remarkable generalization ability in zero-shot recognition tasks. Previous open-vocabulary 3D scene understanding methods mostly focus on training 3D models using either image or…

Recent advances in Multi-modal Large Language Models (MLLMs) target 3D spatial intelligence, yet the progress has been largely driven by post-training on curated benchmarks, leaving the inference-time approach relatively underexplored. In…

Machine learning interatomic potentials (MLIPs) have revolutionized the modeling of materials and molecules by directly fitting to ab initio data. However, while these models excel at capturing local and semi-local interactions, they often…

Effective scene representation is critical for the visual grounding ability of representations, yet existing methods for 3D Visual Grounding are often constrained. They either only focus on geometric and visual cues, or, like traditional 3D…

Visual place recognition is one of the essential and challenging problems in the fields of robotics. In this letter, we for the first time explore the use of multi-modal fusion of semantic and visual modalities in dynamics-invariant space…