Related papers: Performance of Gaussian Mixture Model Classifiers …

Generative Adversarial Networks (GANs) have been shown to produce realistically looking synthetic images with remarkable success, yet their performance seems less impressive when the training set is highly diverse. In order to provide a…

With the surge in available data from various modalities, there is a growing need to bridge the gap between different data types. In this work, we introduce a novel approach to learn cross-modal representations between image data and…

Although foundational vision-language models (VLMs) have proven to be very successful for various semantic discrimination tasks, they still struggle to perform faithfully for fine-grained categorization. Moreover, foundational models…

In recent years, parametric representations of point clouds have been widely applied in tasks such as memory-efficient mapping and multi-robot collaboration. Highly adaptive models, like spline surfaces or quadrics, are computationally…

Generative models have advantageous characteristics for classification tasks such as the availability of unsupervised data and calibrated confidence, whereas discriminative models have advantages in terms of the simplicity of their model…

Lifting multi-view 2D instance segmentation to a radiance field has proven to be effective to enhance 3D understanding. Existing methods rely on direct matching for end-to-end lifting, yielding inferior results; or employ a two-stage…

The goal of multi-modal learning is to use complimentary information on the relevant task provided by the multiple modalities to achieve reliable and robust performance. Recently, deep learning has led significant improvement in multi-modal…

Widely used deep latent variable models (DLVMs), in particular Variational Autoencoders (VAEs), employ overly simplistic priors on the latent space. To achieve strong clustering performance, existing methods that replace the standard normal…

Classifying videos according to content semantics is an important problem with a wide range of applications. In this paper, we propose a hybrid deep learning framework for video classification, which is able to model static spatial…

We address the problem of generalized category discovery (GCD) in this paper, i.e. clustering the unlabeled images leveraging the information from a set of seen classes, where the unlabeled images could contain both seen classes and unseen…

Previous studies on image classification have mainly focused on the performance of the networks, not on real-time operation or model compression. We propose a Gaussian Deep Recurrent visual Attention Model (GDRAM)- a reinforcement learning…

This paper proposes Neural-MMGS, a novel neural 3DGS framework for multimodal large-scale scene reconstruction that fuses multiple sensing modalities in a per-gaussian compact, learnable embedding. While recent works focusing on large-scale…

Fuzzy Cognitive Maps (FCMs) are considered a soft computing technique combining elements of fuzzy logic and recurrent neural networks. They found multiple application in such domains as modeling of system behavior, prediction of time…

In deep metric learning (DML), high-level input data are represented in a lower-level representation (embedding) space, such that samples from the same class are mapped close together, while samples from disparate classes are mapped further…

Multi-Label Image Classification (MLIC) aims to predict a set of labels that present in an image. The key to deal with such problem is to mine the associations between image contents and labels, and further obtain the correct assignments…

CLIP is a discriminative model trained to align images and text in a shared embedding space. Due to its multimodal structure, it serves as the backbone of many generative pipelines, where a decoder is trained to map from the shared space…

Particle identification in large high-energy physics experiments typically relies on classifiers obtained by combining many experimental observables. Predicting the probability density function (pdf) of such classifiers in the multivariate…

Constructing effective representations is a critical but challenging problem in multimedia understanding. The traditional handcraft features often rely on domain knowledge, limiting the performances of exiting methods. This paper discusses…

In order to improve classification accuracy different image representations are usually combined. This can be done by using two different fusing schemes. In feature level fusion schemes, image representations are combined before the…

Contrastive Language and Image Pairing (CLIP), a transformative method in multimedia retrieval, typically trains two neural networks concurrently to generate joint embeddings for text and image pairs. However, when applied directly, these…