arXiv subjects

Moacir Ponti

Publications and source records attributed to Moacir Ponti.

10 recordsLinked to original sources

arXiv2026

An overview of 3D Vision-Language Models

Vision-Language Models (VLMs) are reshaping computer vision by aligning visual and textual embeddings, allowing models to recognize visual concepts and reason about them using natural language. Traditional 3D deep-learning models, however, are typically trained for specific tasks, such as classification, segmentation, or detection, and do not naturally support cross-modal retrieval from their embedding spaces using text or images as queries. To address this issue, Contrastive Language-Image Pretraining (CLIP)-based methods align 3D embeddings with pretrained image and text representations, giving rise to 3D Vision-Language Models (3D VLMs) that support zero-shot classification, cross-modal retrieval, and open-vocabulary recognition of 3D shapes. This tutorial provides an overview of 3D VLMs, ranging from basic definitions of 3D representations and their encoding into embeddings to cross-modal contrastive alignment, modern multimodal frameworks, and 3D Vision-Large Language Models (3D VLLMs). We present the main definitions of contrastive learning for multimodal embedding alignment and highlight recent advances in language-guided 3D Gaussian splatting, 3D shape generation, and embodied AI for robotics.

cs.CV↗

arXiv2026

3D-MRL: Nested Multimodal 3D Representations via Matryoshka Representation Learning

Vision-Language Models align point clouds with image and text embeddings, enabling zero-shot recognition, retrieval, and open-vocabulary understanding of 3D shapes. Existing multimodal 3D pre-training methods produce fixed-dimensional embeddings, requiring separate models for different computational budgets. We propose 3D Matryoshka Representation Learning (3D-MRL), a multimodal 3D pre-training framework based on Matryoshka Representation Learning. 3D-MRL learns nested 3D representations by aligning point clouds with frozen CLIP image and text embeddings while applying contrastive supervision across multiple embedding dimensions. The Matryoshka objective is applied only to the 3D encoder, allowing a single model to produce representations at different dimensionalities without retraining. Experiments on the Objaverse-LVIS, ModelNet40, and ScanNet datasets show that 3D-MRL achieves competitive performance on zero-shot and few-shot 3D recognition tasks. In addition, the learned representations support retrieval across different embedding dimensions within a single model. On Objaverse-LVIS, 3D-MRL improves Top-1 accuracy from 46.8% to 50.9%. Retrieval experiments further show that different embedding dimensions yield varying levels of semantic and geometric specificity.

cs.CV↗

arXiv2026

Differentiable Lifting for Topological Neural Networks

Topological neural networks (TNNs) enable leveraging high-order structures on graphs (e.g., cycles and cliques) to boost the expressive power of message-passing neural networks. In turn, however, these structures are typically identified a priori through an unsupervised graph lifting operation. Notwithstanding, this choice is crucial and may have a drastic impact on a TNN's performance on downstream tasks. To circumvent this issue, we propose $\partial$lift (DiffLift), a general framework for learning graph liftings to hypergraphs and cellular- and simplicial complexes in an end-to-end fashion. In particular, our approach leverages learned vertex-level latent representations to identify and parameterize distributions over candidate higher-order cells for inclusion. This results in a scalable model which can be readily integrated into any TNN. Our experiments show that $\partial$lift outperforms existing lifting methods on multiple benchmarks for graph and node classification across different TNN architectures. Notably, our approach leads to gains of up to 45% over static liftings, including both connectivity- and feature-based ones.

cs.LG↗

arXiv2021

Scene Designer: a Unified Model for Scene Search and Synthesis from Sketch

Scene Designer is a novel method for searching and generating images using free-hand sketches of scene compositions; i.e. drawings that describe both the appearance and relative positions of objects. Our core contribution is a single unified model to learn both a cross-modal search embedding for matching sketched compositions to images, and an object embedding for layout synthesis. We show that a graph neural network (GNN) followed by Transformer under our novel contrastive learning setting is required to allow learning correlations between object type, appearance and arrangement, driving a mask generation module that synthesises coherent scene layouts, whilst also delivering state of the art sketch based visual search of scenes.

cs.CV↗

arXiv2020

A Visual Mining Approach to Improved Multiple-Instance Learning

Multiple-instance learning (MIL) is a paradigm of machine learning that aims to classify a set (bag) of objects (instances), assigning labels only to the bags. This problem is often addressed by selecting an instance to represent each bag, transforming a MIL problem into standard supervised learning. Visualization can be a useful tool to assess learning scenarios by incorporating the users' knowledge into the classification process. Considering that multiple-instance learning is a paradigm that cannot be handled by current visualization techniques, we propose a multiscale tree-based visualization called MILTree to support MIL problems. The first level of the tree represents the bags, and the second level represents the instances belonging to each bag, allowing users to understand the MIL datasets in an intuitive way. In addition, we propose two new instance selection methods for MIL, which help users improve the model even further. Our methods can handle both binary and multiclass scenarios. In our experiments, SVM was used to build the classifiers. With support of the MILTree layout, the initial classification model was updated by changing the training set, which is composed of the prototype instances. Experimental results validate the effectiveness of our approach, showing that visual mining by MILTree can support exploring and improving models in MIL scenarios and that our instance selection methods outperform the currently available alternatives in most cases.

cs.HC↗

arXiv2020

Sketchformer: Transformer-based Representation for Sketched Structure

Sketchformer is a novel transformer-based representation for encoding free-hand sketches input in a vector form, i.e. as a sequence of strokes. Sketchformer effectively addresses multiple tasks: sketch classification, sketch based image retrieval (SBIR), and the reconstruction and interpolation of sketches. We report several variants exploring continuous and tokenized input representations, and contrast their performance. Our learned embedding, driven by a dictionary learning tokenization scheme, yields state of the art performance in classification and image retrieval tasks, when compared against baseline representations driven by LSTM sequence to sequence architectures: SketchRNN and derivatives. We show that sketch reconstruction and interpolation are improved significantly by the Sketchformer embedding for complex sketches with longer stroke sequences.

cs.CV↗

arXiv2016

Generalisation and Sharing in Triplet Convnets for Sketch based Visual Search

We propose and evaluate several triplet CNN architectures for measuring the similarity between sketches and photographs, within the context of the sketch based image retrieval (SBIR) task. In contrast to recent fine-grained SBIR work, we study the ability of our networks to generalise across diverse object categories from limited training data, and explore in detail strategies for weight sharing, pre-processing, data augmentation and dimensionality reduction. We exceed the performance of pre-existing techniques on both the Flickr15k category level SBIR benchmark by $18\%$, and the TU-Berlin SBIR benchmark by $\sim10 \mathcal{T}_b$, when trained on the 250 category TU-Berlin classification dataset augmented with 25k corresponding photographs harvested from the Internet.

cs.CV↗

arXiv2016

Better than Counting Seconds: Identifying Fallers among Healthy Elderly using Fusion of Accelerometer Features and Dual-Task Timed Up and Go

Devices and sensors for identification of fallers can be used to implement actions to prevent falls and to allow the elderly to live an independent life while reducing the long-term care costs. In this study we aimed to investigate the accuracy of Timed Up and Go test, for fallers' identification, using fusion of features extracted from accelerometer data. Single and dual tasks TUG (manual and cognitive) were performed by a final sample (94% power) of 36 community dwelling healthy older persons (18 fallers paired with 18 non-fallers) while they wear a single triaxial accelerometer at waist with sampling rate of 200Hz. The segmentation of the TUG different trials and its comparative analysis allows to better discriminate fallers from non-fallers, while conventional functional tests fail to do so. In addition, we show that the fusion of features improve the discrimination power, achieving AUC of 0.84 (Sensitivity=Specificity=0.83, 95% CI 0.62-0.91), and demonstrating the clinical relevance of the study. We concluded that features extracted from segmented TUG trials acquired with dual tasks has potential to improve performance when identifying fallers via accelerometer sensors, which can improve TUG accuracy for clinical and epidemiological applications.

cs.CY↗

arXiv2016

An empirical study on the effects of different types of noise in image classification tasks

Image classification is one of the main research problems in computer vision and machine learning. Since in most real-world image classification applications there is no control over how the images are captured, it is necessary to consider the possibility that these images might be affected by noise (e.g. sensor noise in a low-quality surveillance camera). In this paper we analyse the impact of three different types of noise on descriptors extracted by two widely used feature extraction methods (LBP and HOG) and how denoising the images can help to mitigate this problem. We carry out experiments on two different datasets and consider several types of noise, noise levels, and denoising methods. Our results show that noise can hinder classification performance considerably and make classes harder to separate. Although denoising methods were not able to reach the same performance of the noise-free scenario, they improved classification results for noisy data.

cs.CV↗

arXiv2016

An incremental linear-time learning algorithm for the Optimum-Path Forest classifier

We present a classification method with incremental capabilities based on the Optimum-Path Forest classifier (OPF). The OPF considers instances as nodes of a fully-connected training graph, arc weights represent distances between two feature vectors. Our algorithm includes new instances in an OPF in linear-time, while keeping similar accuracies when compared with the original quadratic-time model.

cs.LG↗