相关论文: End-to-end One-shot Human Parsing

The Split and Rephrase (SPRP) task, which consists in splitting complex sentences into a sequence of shorter grammatical sentences, while preserving the original meaning, can facilitate the processing of complex texts for humans and…

Early classification algorithms help users react faster to their machine learning model's predictions. Early warning systems in hospitals, for example, let clinicians improve their patients' outcomes by accurately predicting infections.…

Large vision models based in deep learning architectures have been consistently advancing the state-of-the-art in biometric recognition. However, three weaknesses are commonly reported for such kind of approaches: 1) their extreme demands…

Detecting out-of-distribution (OOD) samples is essential when deploying machine learning models in open-world scenarios. Zero-shot OOD detection, requiring no training on in-distribution (ID) data, has been possible with the advent of…

Semi-supervised object detection (SSOD) is a research hot spot in computer vision, which can greatly reduce the requirement for expensive bounding-box annotations. Despite great success, existing progress mainly focuses on two-stage…

In this paper we introduce a novel method to estimate the head pose of people in single images starting from a small set of head keypoints. To this purpose, we propose a regression model that exploits keypoints computed automatically by 2D…

Few-shot object detection (FSOD) aims to detect objects with limited samples for novel classes, while relying on abundant data for base classes. Existing FSOD approaches, predominantly built on the Faster R-CNN detector, entangle objectness…

Capsule networks (CapsNets) were introduced to address convolutional neural networks limitations, learning object-centric representations that are more robust, pose-aware, and interpretable. They organize neurons into groups called…

In this paper, we propose a novel model for high-dimensional data, called the Hybrid Orthogonal Projection and Estimation (HOPE) model, which combines a linear orthogonal projection and a finite mixture model under a unified generative…

Few-shot models aim at making predictions using a minimal number of labeled examples from a given task. The main challenge in this area is the one-shot setting where only one element represents each class. We propose HyperShot - the fusion…

We introduce One-shot Open Affordance Learning (OOAL), where a model is trained with just one example per base object category, but is expected to identify novel objects and affordances. While vision-language models excel at recognizing…

Given the current visual observations, the traditional procedure planning task in instructional videos requires a model to generate goal-directed plans within a given action space. All previous methods for this task conduct training and…

Few-shot learning aims to learn a classifier using a few labelled instances for each class. Metric-learning approaches for few-shot learning embed instances into a high-dimensional space and conduct classification based on distances among…

Few-shot learning aims to learn classifiers for new classes with only a few training examples per class. Most existing few-shot learning approaches belong to either metric-based meta-learning or optimization-based meta-learning category,…

This paper studies the omnidirectional sensor-placement problem (OSPP), which involves placing static sensors in a continuous 2D environment to achieve a user-defined coverage requirement while minimizing sensor count. The problem is…

The successive subspace learning (SSL) principle was developed and used to design an interpretable learning model, known as the PixelHop method,for image classification in our prior work. Here, we propose an improved PixelHop method and…

In this paper, we revisit the problem of 3D human modeling from two orthogonal silhouettes of individuals (i.e., front and side views). Different from our prior work, a supervised learning approach based on convolutional neural network…

Machine Learning (ML) models are trained on in-distribution (ID) data but often encounter out-of-distribution (OOD) inputs during deployment -- posing serious risks in safety-critical domains. Recent works have focused on designing scoring…

One-shot imitation learning (OSIL) offers a promising way to teach robots new skills without large-scale data collection. However, current OSIL methods are primarily limited to short-horizon tasks, thus limiting their applicability to…

Few-Shot classification aims at solving problems that only a few samples are available in the training process. Due to the lack of samples, researchers generally employ a set of training tasks from other domains to assist the target task,…