Related papers: Identity Preserve Transform: Understand What Activ…

Imitation learning has shown success in many tasks by learning from expert demonstrations. However, most existing work relies on large-scale demonstrations from technical professionals and close monitoring of the training process. These are…

By thoroughly revisiting the classic human action recognition paradigm, this paper aims at proposing a new approach for the design of effective action classification systems. Taking as testbed publicly available three-dimensional (MoCap)…

Pretrained language models are typically trained on massive web-based datasets, which are often "contaminated" with downstream test sets. It is not clear to what extent models exploit the contaminated data for downstream tasks. We present a…

Continual post-training (CPT) is a popular and effective technique for adapting foundation models like multimodal large language models to specific and ever-evolving downstream tasks. While existing research has primarily concentrated on…

The daily activities performed by a disabled or elderly person can be monitored by a smart environment, and the acquired data can be used to learn a predictive model of user behavior. To speed up the learning, several researchers designed…

Model inversion, which aims to reconstruct the original training data from pre-trained discriminative models, is especially useful when the original training data is unavailable due to privacy, usage rights, or size constraints. However,…

Recent machine learning techniques have dramatically changed how we process digital images. However, the way in which we capture images is still largely driven by human intuition and experience. This restriction is in part due to the many…

Human Activity Recognition (HAR) on mobile devices has been demonstrated to be possible using neural models trained on data collected from the device's inertial measurement units. These models have used Convolutional Neural Networks (CNNs),…

Vision Transformer (ViT), a radically different architecture than convolutional neural networks offers multiple advantages including design simplicity, robustness and state-of-the-art performance on many vision tasks. However, in contrast…

Imitation learning enables autonomous agents to learn from human examples, without the need for a reward signal. Still, if the provided dataset does not encapsulate the task correctly, or when the task is too complex to be modeled, such…

How do we transfer the relevant knowledge from ever larger foundation models into small, task-specific downstream models that can run at much lower costs? Standard transfer learning using pre-trained weights as the initialization transfers…

In this work, we propose an attention-based deep reinforcement learning approach to address the adaptive informative path planning (IPP) problem in 3D space, where an aerial robot equipped with a downward-facing sensor must dynamically…

Transformer models have achieved remarkable empirical successes, largely due to their in-context learning capabilities. Inspired by this, we explore training an autoregressive transformer for in-context reinforcement learning (ICRL). In…

Activity recognition has become a popular research branch in the field of pervasive computing in recent years. A large number of experiments can be obtained that activity sensor-based data's characteristic in activity recognition is…

Transfer of pre-trained representations improves sample efficiency and simplifies hyperparameter tuning when training deep neural networks for vision. We revisit the paradigm of pre-training on large supervised datasets and fine-tuning the…

In recent years, domains such as natural language processing and image recognition have popularized the paradigm of using large datasets to pretrain representations that can be effectively transferred to downstream tasks. In this work we…

Knowledge tracing is a technique that predicts students' future performance by analyzing their learning process through historical interactions with intelligent educational platforms, enabling a precise evaluation of their knowledge…

This paper presents a study on improving human action recognition through the utilization of knowledge distillation, and the combination of CNN and ViT models. The research aims to enhance the performance and efficiency of smaller student…

The goal of imitation learning is to mimic expert behavior from demonstrations, without access to an explicit reward signal. A popular class of approach infers the (unknown) reward function via inverse reinforcement learning (IRL) followed…

Pre-trained Transformer-based models have achieved state-of-the-art performance for various Natural Language Processing (NLP) tasks. However, these models often have billions of parameters, and, thus, are too resource-hungry and…