Current methods for 2D and 3D object understanding struggle with severe occlusions in busy urban environments, partly due to the lack of large-scale labeled ground-truth annotations for learning occlusion. In this work, we introduce a novel framework for automatically generating a large, realistic dataset of dynamic objects under occlusions using freely available time-lapse imagery. By leveraging off-the-shelf 2D (bounding box, segmentation, keypoint) and 3D (pose, shape) predictions as pseudo-groundtruth, unoccluded 3D objects are identified automatically and composited into the background in a clip-art style, ensuring realistic appearances and physically accurate occlusion configurations. The resulting clip-art image with pseudo-groundtruth enables efficient training of object reconstruction methods that are robust to occlusions. Our method demonstrates significant improvements in both 2D and 3D reconstruction, particularly in scenarios with heavily occluded objects like vehicles and people in urban scenes.
Digitising the 3D world into a clean, CAD model-based representation has important applications for augmented reality and robotics. Current state-of-the-art methods are computationally intensive as they individually encode each detected object and optimise CAD alignments in a second stage. In this work, we propose FastCAD, a real-time method that simultaneously retrieves and aligns CAD models for all objects in a given scene. In contrast to previous works, we directly predict alignment parameters and shape embeddings. We achieve high-quality shape retrievals by learning CAD embeddings in a contrastive learning framework and distilling those into FastCAD. Our single-stage method accelerates the inference time by a factor of 50 compared to other methods operating on RGB-D scans while outperforming them on the challenging Scan2CAD alignment benchmark. Further, our approach collaborates seamlessly with online 3D reconstruction techniques. This enables the real-time generation of precise CAD model-based reconstructions from videos at 10 FPS. Doing so, we significantly improve the Scan2CAD alignment accuracy in the video setting from 43.0% to 48.2% and the reconstruction accuracy from 22.9% to 29.6%.
We apply Bayesian Additive Regression Tree (BART) principles to training an ensemble of small neural networks for regression tasks. Using Markov Chain Monte Carlo, we sample from the posterior distribution of neural networks that have a single hidden layer. To create an ensemble of these, we apply Gibbs sampling to update each network against the residual target value (i.e. subtracting the effect of the other networks). We demonstrate the effectiveness of this technique on several benchmark regression problems, comparing it to equivalent shallow neural networks, BART, and ordinary least squares. Our Bayesian Additive Regression Networks (BARN) provide more consistent and often more accurate results. On test data benchmarks, BARN averaged between 5 to 20 percent lower root mean square error. This error performance does come at the cost, however, of greater computation time. BARN sometimes takes on the order of a minute where competing methods take a second or less. But, BARN without cross-validated hyperparameter tuning takes about the same amount of computation time as tuned other methods. Yet BARN is still typically more accurate.
Demand forecasts are the crucial basis for numerous business decisions, ranging from inventory management to strategic facility planning. While machine learning (ML) approaches offer accuracy gains, their interpretability and acceptance are notoriously lacking. Addressing this dilemma, we introduce Hierarchical Neural Additive Models for time series (HNAM). HNAM expands upon Neural Additive Models (NAM) by introducing a time-series specific additive model with a level and interacting covariate components. Covariate interactions are only allowed according to a user-specified interaction hierarchy. For example, weekday effects may be estimated independently of other covariates, whereas a holiday effect may depend on the weekday and an additional promotion may depend on both former covariates that are lower in the interaction hierarchy. Thereby, HNAM yields an intuitive forecasting interface in which analysts can observe the contribution for each known covariate. We evaluate the proposed approach and benchmark its performance against other state-of-the-art machine learning and statistical models extensively on real-world retail data. The results reveal that HNAM offers competitive prediction performance whilst providing plausible explanations.
Growing polarisation in society caught the attention of the scientific community as well as news media, which devote special issues to this phenomenon. At the same time, digitalisation of social interactions requires to revise concepts from social science regarding establishment of trust, which is a key feature of all human interactions, and group polarisation, as well as new computational tools to process large quantities of available data. Existing methods seem insufficient to tackle the problem fully, thus, we propose to approach the problem by investigating rhetorical strategies employed by individuals in polarising discussions online. To this end, we develop multi-topic and multi-platform corpora with manual annotation of appeals to ethos and pathos, two modes of persuasion in Aristotelian rhetoric. It can be employed for training language models to advance the study of communication strategies online on a large scale. With the use of computational methods, our corpora allows an investigation of recurring patterns in polarising exchanges across topics of discussion and media platforms, and conduct both quantitative and qualitative analyses of language structures leading to and engaged in polarisation.
Computational prediction of stable crystal structures has a profound impact on the large-scale discovery of novel functional materials. However, predicting the crystal structure solely from a material's composition or formula is a promising yet challenging task, as traditional ab initio crystal structure prediction (CSP) methods rely on time-consuming global searches and first-principles free energy calculations. Inspired by the recent success of deep learning approaches in protein structure prediction, which utilize pairwise amino acid interactions to describe 3D structures, we present AlphaCrystal-II, a novel knowledge-based solution that exploits the abundant inter-atomic interaction patterns found in existing known crystal structures. AlphaCrystal-II predicts the atomic distance matrix of a target crystal material and employs this matrix to reconstruct its 3D crystal structure. By leveraging the wealth of inter-atomic relationships of known crystal structures, our approach demonstrates remarkable effectiveness and reliability in structure prediction through comprehensive experiments. This work highlights the potential of data-driven methods in accelerating the discovery and design of new materials with tailored properties.
The following paper presents an adaptive anchor pairs selection method for ultra-wideband (UWB) Time Difference of Arrival (TDOA) based positioning systems. The method divides the area covered by the system into several zones and assigns them anchor pair sets. The pair sets are determined during calibration based on localization root mean square error (RMSE). The calibration assumes driving a mobile platform equipped with a LiDAR sensor and a UWB tag through the specified zones. The robot is localized separately based on a large set of different TDOA pairs and using a LiDAR, which acts as the reference. For each zone, the TDOA pairs set for which the registered RMSE is lowest is selected and used for localization in the routine system work. The proposed method has been tested with simulations and experiments. The results for both simulated static and experimental dynamic scenarios have proven that the adaptive selection of the anchor nodes leads to an increase in localization accuracy. In the experiment, the median trajectory error for a moving person localization was at a level of 25 cm.
Via thousands of papers in Explainable AI (XAI), attention maps \cite{vaswani2017attention} and feature attribution maps \cite{bansal2020sam} have been established as a common means for explaining the input features that are important to AI's decisions. It is an interesting but unexplored question whether allowing users to edit the importance scores of input features at test time would improve the human-AI team's accuracy on downstream tasks. In this paper, we address this question by taking CHM-Corr, a state-of-the-art, ante-hoc explanation method \cite{taesiri2022visual} that first predicts patch-wise correspondences between the input and the training-set images, and then uses them to make classification decisions. We build an interactive interface on top of CHM-Corr, enabling users to directly edit the initial feature attribution map provided by CHM-Corr. Via our CHM-Corr++ interface, users gain insights into if, when, and how the model changes its outputs, enhancing understanding beyond static explanations. Our user study with 18 machine learning researchers who performed $\sim$1,400 decisions shows that our interactive approach does not improve user accuracy on CUB-200 bird image classification over static explanations. This challenges the belief that interactivity inherently boosts XAI effectiveness~\cite{sokol2020one,sun2022exploring,shen2024towards,singh2024rethinking,mindlin2024beyond,lakkaraju2022rethinking,cheng2019explaining,liu2021understanding} and raises needs for future research. Our work contributes to the field by open-sourcing an interactive tool for manipulating model attention, and it lays the groundwork for future research to enable effective human-AI interaction in computer vision. We release code and data on \href{https://anonymous.4open.science/r/CHMCorrPlusPlus/}{github}. Our interface are available \href{http://137.184.82.109:7080/}{here}.
Large Language Models (LLMs) have the potential of facilitating the development of Artificial Intelligence technology to assist medical experts for interactive decision support, which has been demonstrated by their competitive performances in Medical QA. However, while impressive, the required quality bar for medical applications remains far from being achieved. Currently, LLMs remain challenged by outdated knowledge and by their tendency to generate hallucinated content. Furthermore, most benchmarks to assess medical knowledge lack reference gold explanations which means that it is not possible to evaluate the reasoning of LLMs predictions. Finally, the situation is particularly grim if we consider benchmarking LLMs for languages other than English which remains, as far as we know, a totally neglected topic. In order to address these shortcomings, in this paper we present MedExpQA, the first multilingual benchmark based on medical exams to evaluate LLMs in Medical Question Answering. To the best of our knowledge, MedExpQA includes for the first time reference gold explanations written by medical doctors which can be leveraged to establish various gold-based upper-bounds for comparison with LLMs performance. Comprehensive multilingual experimentation using both the gold reference explanations and Retrieval Augmented Generation (RAG) approaches show that performance of LLMs still has large room for improvement, especially for languages other than English. Furthermore, and despite using state-of-the-art RAG methods, our results also demonstrate the difficulty of obtaining and integrating readily available medical knowledge that may positively impact results on downstream evaluations for Medical Question Answering. So far the benchmark is available in four languages, but we hope that this work may encourage further development to other languages.
We propose VecKM, a novel local point cloud geometry encoder that is descriptive, efficient and robust to noise. VecKM leverages a unique approach by vectorizing a kernel mixture to represent the local point clouds. Such representation is descriptive and robust to noise, which is supported by two theorems that confirm its ability to reconstruct and preserve the similarity of the local shape. Moreover, VecKM is the first successful attempt to reduce the computation and memory costs from $O(n^2+nKd)$ to $O(nd)$ by sacrificing a marginal constant factor, where $n$ is the size of the point cloud and $K$ is neighborhood size. The efficiency is primarily due to VecKM's unique factorizable property that eliminates the need of explicitly grouping points into neighborhoods. In the normal estimation task, VecKM demonstrates not only 100x faster inference speed but also strongest descriptiveness and robustness compared with existing popular encoders. In classification and segmentation tasks, integrating VecKM as a preprocessing module achieves consistently better performance than the PointNet, PointNet++, and point transformer baselines, and runs consistently faster by up to 10x.