Related papers: A Short Note about Kinetics-600
Most existing action quality assessment methods rely on the deep features of an entire video to predict the score, which is less reliable due to the non-transparent inference process and poor interpretability. We argue that understanding…
How much can a pitcher's body reveal about the upcoming pitch? We study this question at scale by classifying eight pitch types from monocular 3D pose sequences, without access to ball-flight data. Our pipeline chains a diffusion-based 3D…
Many application areas ranging from serious games for health to learning by demonstration in robotics, could benefit from large body movement datasets extracted from textual instructions accompanied by images. The interpretation of…
As audio-visual systems increasingly bring immersive and interactive capabilities into our work and leisure activities, so the need for naturalistic test material grows. New volumetric datasets have captured high-quality 3D video, but…
Choreographers determine what the dances look like, while cameramen determine the final presentation of dances. Recently, various methods and datasets have showcased the feasibility of dance synthesis. However, camera movement synthesis…
This paper introduces a new large consent-driven dataset aimed at assisting in the evaluation of algorithmic bias and robustness of computer vision and audio speech models in regards to 11 attributes that are self-provided or labeled by…
Detecting 3D objects keypoints is of great interest to the areas of both graphics and computer vision. There have been several 2D and 3D keypoint datasets aiming to address this problem in a data-driven way. These datasets, however, either…
World models aim to understand, remember, and predict dynamic visual environments, yet a unified benchmark for evaluating their fundamental abilities remains lacking. To address this gap, we introduce MIND, the first open-domain closed-loop…
This paper presents a new large-scale dataset for recognition and temporal localization of human actions collected from Web videos. We refer to it as HACS (Human Action Clips and Segments). We leverage both consensus and disagreement among…
Understanding behavior requires datasets that capture humans while carrying out complex tasks. The kitchen is an excellent environment for assessing human motor and cognitive function, as many complex actions are naturally exhibited in…
Recent advances in deep learning methods have increased the performance of face detection and recognition systems. The accuracy of these models relies on the range of variation provided in the training data. Creating a dataset that…
Dual-arm robotic grasping is crucial for handling large objects that require stable and coordinated manipulation. While single-arm grasping has been extensively studied, datasets tailored for dual-arm settings remain scarce. We introduce a…
While automatic monitoring and coaching of exercises are showing encouraging results in non-medical applications, they still have limitations such as errors and limited use contexts. To allow the development and assessment of physical…
Current fully-supervised video datasets consist of only a few hundred thousand videos and fewer than a thousand domain-specific labels. This hinders the progress towards advanced video architectures. This paper presents an in-depth study of…
The SkatingVerse Workshop & Challenge aims to encourage research in developing novel and accurate methods for human action understanding. The SkatingVerse dataset used for the SkatingVerse Challenge has been publicly released. There are two…
Recently, there has been a growing interest in wearable sensors which provides new research perspectives for 360 {\deg} video analysis. However, the lack of 360 {\deg} datasets in literature hinders the research in this field. To bridge…
Effectively measuring the similarity between two human motions is necessary for several computer vision tasks such as gait analysis, person identi- fication and action retrieval. Nevertheless, we believe that traditional approaches such as…
Human activity recognition (HAR) is often limited by the scarcity of labeled datasets due to the high cost and complexity of real-world data collection. To mitigate this, recent work has explored generating virtual inertial measurement unit…
This paper presents a comparison of various deep learning models such as Exception, Resnet-50, and Inception V3 for the classification and prediction of hand hygiene gestures, which were recorded in accordance with the World Health…
Videos are more informative than images because they capture the dynamics of the scene. By representing motion in videos, we can capture dynamic activities. In this work, we introduce GPT-4 generated motion descriptions that capture…