Related papers: HA-ViD: A Human Assembly Video Dataset for Compreh…
Advancements in deep neural networks have contributed to near perfect results for many computer vision problems such as object recognition, face recognition and pose estimation. However, human action recognition is still far from…
Despite tremendous recent progress in human video generation, generative video diffusion models still struggle to capture the dynamics and physics of human motions faithfully. In this paper, we propose a new framework for human video…
Wearable cameras allow to acquire images and videos from the user's perspective. These data can be processed to understand humans behavior. Despite human behavior analysis has been thoroughly investigated in third person vision, it is still…
User engagement is greatly enhanced by fully immersive multi-modal experiences that combine visual and auditory stimuli. Consequently, the next frontier in VR/AR technologies lies in immersive volumetric videos with complete scene capture,…
Audio event detection is a widely studied audio processing task, with applications ranging from self-driving cars to healthcare. In-the-wild datasets such as Audioset have propelled research in this field. However, many efforts typically…
Shape assembly is a ubiquitous task in daily life, integral for constructing complex 3D structures like IKEA furniture. While significant progress has been made in developing autonomous agents for shape assembly, existing datasets have not…
There are substantial instructional videos on the Internet, which enables us to acquire knowledge for completing various tasks. However, most existing datasets for instructional video analysis have the limitations in diversity and…
Understanding action correspondence between humans and robots is essential for evaluating alignment in decision-making, particularly in human-robot collaboration and imitation learning within unstructured environments. We propose a…
Anomaly detection and localization in visual data, including images and videos, are crucial in machine learning and real-world applications. Despite rapid advancements in visual anomaly detection (VAD), interpreting these often black-box…
This paper presents a new large multiview dataset called HUMBI for human body expressions with natural clothing. The goal of HUMBI is to facilitate modeling view-specific appearance and geometry of gaze, face, hand, body, and garment from…
QUB-PHEO introduces a visual-based, dyadic dataset with the potential of advancing human-robot interaction (HRI) research in assembly operations and intention inference. This dataset captures rich multimodal interactions between two…
Learning visuomotor policies from expert demonstrations is an important frontier in modern robotics research, however, most popular methods require copious efforts for collecting teleoperation data and struggle to generalize…
Cutting-edge robot learning techniques including foundation models and imitation learning from humans all pose huge demands on large-scale and high-quality datasets which constitute one of the bottleneck in the general intelligent robot…
Action recognition is so far mainly focusing on the problem of classification of hand selected preclipped actions and reaching impressive results in this field. But with the performance even ceiling on current datasets, it also appears that…
Recent progress in imitation learning from human demonstrations has shown promising results in teaching robots manipulation skills. To further scale up training datasets, recent works start to use portable data collection devices without…
Comparing two images in terms of Commonalities and Differences (CaD) is a fundamental human capability that forms the basis of advanced visual reasoning and interpretation. It is essential for the generation of detailed and contextually…
While deep convolutional neural networks frequently approach or exceed human-level performance at benchmark tasks involving static images, extending this success to moving images is not straightforward. Having models which can learn to…
From an image of a person in action, we can easily guess the 3D motion of the person in the immediate past and future. This is because we have a mental model of 3D human dynamics that we have acquired from observing visual sequences of…
This paper describes the AVA-Kinetics localized human actions video dataset. The dataset is collected by annotating videos from the Kinetics-700 dataset using the AVA annotation protocol, and extending the original AVA dataset with these…
Thanks to the substantial and explosively inscreased instructional videos on the Internet, novices are able to acquire knowledge for completing various tasks. Over the past decade, growing efforts have been devoted to investigating the…