Related papers: PEg TRAnsfer Workflow recognition challenge report…

Inertial sensors are crucial for recognizing pedestrian activity. Recent advances in deep learning have greatly improved inertial sensing performance and robustness. Different domains and platforms use deep-learning techniques to enhance…

In recent years, many works in the video action recognition literature have shown that two stream models (combining spatial and temporal input streams) are necessary for achieving state of the art performance. In this paper we show the…

Recently neural scene representations have provided very impressive results for representing 3D scenes visually, however, their study and progress have mainly been limited to visualization of virtual models in computer graphics or scene…

We propose to improve transformers of a specific modality with irrelevant data from other modalities, e.g., improve an ImageNet model with audio or point cloud datasets. We would like to highlight that the data samples of the target…

People identification in video based on the way they walk (i.e. gait) is a relevant task in computer vision using a non-invasive approach. Standard and current approaches typically derive gait signatures from sequences of binary energy maps…

Fast domain adaptation remains a fundamental challenge for deploying multi-agent systems across diverse environments in Vehicle-to-Everything (V2X) collaborative perception. Despite the success of Parameter-Efficient Fine-Tuning (PEFT) in…

Given video demonstrations and paired narrations of an at-home procedural task such as changing a tire, we present an approach to extract the underlying task structure -- relevant actions and their temporal dependencies -- via…

Accurate segmentation of the pelvic CTs is crucial for the clinical diagnosis of pelvic bone diseases and for planning patient-specific hip surgeries. With the emergence and advancements of deep learning for digital healthcare, several…

Creating a dataset for training supervised machine learning algorithms can be a demanding task. This is especially true for medical image segmentation since one or more specialists are usually required for image annotation, and creating…

Vision-Language Models (VLMs) perform well on multimodal benchmarks but lag behind humans and specialized models on visual perception tasks like depth estimation or object counting. Finetuning on one task can unpredictably affect…

Traditional vision-based material perception methods often experience substantial performance degradation under visually impaired conditions, thereby motivating the shift toward non-visual multimodal material perception. Despite this,…

In learning action recognition, models are typically pre-trained on object recognition with images, such as ImageNet, and later fine-tuned on target action recognition with videos. This approach has achieved good empirical performance…

Representation learning is a key technique in modern machine learning that enables models to identify meaningful patterns in complex data. However, different methods tend to extract distinct aspects of the data, and relying on a single…

Although deep neural networks are capable of achieving performance superior to humans on various tasks, they are notorious for requiring large amounts of data and computing resources, restricting their success to domains where such…

Surgical tool segmentation and action recognition are fundamental building blocks in many computer-assisted intervention applications, ranging from surgical skills assessment to decision support systems. Nowadays, learning-based action…

Facial Action Units (AU) is a vital concept in the realm of affective computing, and AU detection has always been a hot research topic. Existing methods suffer from overfitting issues due to the utilization of a large number of learnable…

Phase recognition in surgical videos is crucial for enhancing computer-aided surgical systems as it enables automated understanding of sequential procedural stages. Existing methods often rely on fixed temporal windows for video analysis to…

The field of numerical simulation is of significant importance for the design and management of real-world systems, with partial differential equations (PDEs) being a commonly used mathematical modeling tool. However, solving PDEs remains…

Robust object detection for challenging scenarios increasingly relies on event cameras, yet existing Event-RGB datasets remain constrained by sparse coverage of extreme conditions and low spatial resolution (<= 640 x 480), which prevents…

Expression recognition in in-the-wild video data remains challenging due to substantial variations in facial appearance, background conditions, audio noise, and the inherently dynamic nature of human affect. Relying on a single modality,…