Related papers: Skeleton-to-Image Encoding: Enabling Skeleton Repr…
Current 3D self-supervised learning methods of 3D scenes face a data desert issue, resulting from the time-consuming and expensive collecting process of 3D scene data. Conversely, 3D shape datasets are easier to collect. Despite this,…
Emotion recognition through body movements has emerged as a compelling and privacy-preserving alternative to traditional methods that rely on facial expressions or physiological signals. Recent advancements in 3D skeleton acquisition…
Animation of 2D hand-drawn sketches provides an effective medium for visual communication. However, these sketches pose challenges, particularly in handling occlusions and accurately mapping motion. While 3D animation naturally addresses…
Deep learning based neural decoding from stereotactic electroencephalography (sEEG) would likely benefit from scaling up both dataset and model size. To achieve this, combining data across multiple subjects is crucial. However, in sEEG…
In this work, we study self-supervised representation learning for 3D skeleton-based action recognition. We extend Bootstrap Your Own Latent (BYOL) for representation learning on skeleton sequence data and propose a new data augmentation…
Human motion synthesis is a long-standing problem with various applications in digital twins and the Metaverse. However, modern deep learning based motion synthesis approaches barely consider the physical plausibility of synthesized motions…
Tissue phenotyping is a fundamental task in learning objective characterizations of histopathologic biomarkers within the tumor-immune microenvironment in cancer pathology. However, whole-slide imaging (WSI) is a complex computer vision in…
Decoding sensory experiences from neural activity to reconstruct human-perceived visual stimuli and semantic content remains a challenge in neuroscience and artificial intelligence. Despite notable progress in current brain decoding models,…
Large Language Models (LLMs) have demonstrated exceptional proficiency in text understanding and embedding tasks. However, their potential in multimodal representation, particularly for item-to-item (I2I) recommendations, remains…
Action recognition with 3D skeleton sequences is becoming popular due to its speed and robustness. The recently proposed Convolutional Neural Networks (CNN) based methods have shown good performance in learning spatio-temporal…
Image-to-image translation (I2I) aims at transferring the content representation from an input domain to an output one, bouncing along different target domains. Recent I2I generative models, which gain outstanding results in this task,…
Vision encoders are increasingly used in modern applications, from vision-only models to multimodal systems such as vision-language models. Despite their remarkable success, it remains unclear how these architectures represent features…
We present a new approach for representing and reconstructing multidimensional magnetic resonance imaging (MRI) data. Our method builds on a novel, learned feature-based image representation that disentangles different types of features,…
Self-supervised representation learning for human action recognition has developed rapidly in recent years. Most of the existing works are based on skeleton data while using a multi-modality setup. These works overlooked the differences in…
In this work, we interpret the representations of multi-object scenes in vision encoders through the lens of structured representations. Structured representations allow modeling of individual objects distinctly and their flexible use based…
Generating realistic and structurally plausible human images into existing scenes remains a significant challenge for current generative models, which often produce artifacts like distorted limbs and unnatural poses. We attribute this…
Most recent view-invariant action recognition and performance assessment approaches rely on a large amount of annotated 3D skeleton data to extract view-invariant features. However, acquiring 3D skeleton data can be cumbersome, if not…
Skeleton data is of low dimension. However, there is a trend of using very deep and complicated feedforward neural networks to model the skeleton sequence without considering the complexity in recent year. In this paper, a simple yet…
Self-supervised learning approaches leverage unlabeled samples to acquire generic knowledge about different concepts, hence allowing for annotation-efficient downstream task learning. In this paper, we propose a novel self-supervised method…
Skeleton data carries valuable motion information and is widely explored in human action recognition. However, not only the motion information but also the interaction with the environment provides discriminative cues to recognize the…