Related papers: Learning in Focus: Detecting Behavioral and Collab…

Pedestrian Intention prediction is one of the key technologies in the transition from level 3 to level 4 autonomous driving. To understand pedestrian crossing behaviour, several elements and features should be taken into consideration to…

Vision Transformers (ViT)s have recently become popular due to their outstanding modeling capabilities, in particular for capturing long-range information, and scalability to dataset and model sizes which has led to state-of-the-art…

Recently, the Vision Transformer (ViT), which applied the transformer structure to the image classification task, has outperformed convolutional neural networks. However, the high performance of the ViT results from pre-training using a…

Human intention is an internal, mental characterization for acquiring desired information. From interactive interfaces containing either textual or graphical information, intention to perceive desired information is subjective and strongly…

Attention mechanism has been widely believed as the key to success of vision transformers (ViTs), since it provides a flexible and powerful way to model spatial relationships. However, is the attention mechanism truly an indispensable part…

Fine-tuning pre-trained convolutional neural networks on ImageNet for downstream tasks is well-established. Still, the impact of model size on the performance of vision transformers in similar scenarios, particularly under label noise,…

Diffusion models with their powerful expressivity and high sample quality have achieved State-Of-The-Art (SOTA) performance in the generative domain. The pioneering Vision Transformer (ViT) has also demonstrated strong modeling capabilities…

We introduce JetViT, a novel family of hybrid-architecture Vision Transformer (ViT) models that match the accuracy of state-of-the-art full-attention vision foundation models while achieving substantially higher inference efficiency on…

Engagement in virtual learning is crucial for a variety of factors including student satisfaction, performance, and compliance with learning programs, but measuring it is a challenging task. There is therefore considerable interest in…

Automatic assessment and evaluation of team performance during collaborative tasks is key to the learning analytics and computer-supported cooperative work research. There is a growing interest in the use of gaze-oriented cues for…

We address the task of identifying distracted driving by analyzing in-car videos using efficient transformers. Although transformer models have achieved outstanding performance in human action recognition tasks, their high computational…

Vision Transformers have achieved state-of-the-art performance in many visual tasks. Due to the quadratic computational and memory complexities of self-attention, recent works either apply attention only to low-resolution inputs or restrict…

Inspired by recent trends in vision and language learning, we explore applications of attention mechanisms for visio-lingual fusion within an application to story-based video understanding. Like other video-based QA tasks, video story…

Modeling engagement in collaborative learning remains challenging, especially in technology-enhanced environments where surface indicators such as participation frequency can be misleading. This study proposes a lightweight and…

Though vision transformers (ViTs) have achieved state-of-the-art performance in a variety of settings, they exhibit surprising failures when performing tasks involving visual relations. This begs the question: how do ViTs attempt to perform…

Understanding the relationship between different parts of an image is crucial in a variety of applications, including object recognition, scene understanding, and image classification. Despite the fact that Convolutional Neural Networks…

Loss of plasticity refers to the progressive inability of a model to adapt to new tasks and poses a fundamental challenge for continual learning. While this phenomenon has been extensively studied in homogeneous neural architectures, such…

In this paper, we investigate the application of Vehicle-to-Everything (V2X) communication to improve the perception performance of autonomous vehicles. We present a robust cooperative perception framework with V2X communication using a…

Group activity recognition is the task of understanding the activity conducted by a group of people as a whole in a multi-person video. Existing models for this task are often impractical in that they demand ground-truth bounding box labels…

Facial Action Units detection (FAUs) represents a fine-grained classification problem that involves identifying different units on the human face, as defined by the Facial Action Coding System. In this paper, we present a simple yet…