Related papers: HAP: Structure-Aware Masked Image Modeling for Hum…

Masked Image Modeling (MIM) is a self-supervised learning technique that involves masking portions of an image, such as pixels, patches, or latent representations, and training models to predict the missing information using the visible…

Pre-training is playing an increasingly important role in learning generic feature representation for Person Re-identification (ReID). We argue that a high-quality ReID representation should have three properties, namely, multi-level…

Almost all existing amodal segmentation methods make the inferences of occluded regions by using features corresponding to the whole image. This is against the human's amodal perception, where human uses the visible part and the shape prior…

We present Reusable Motion prior (ReMP), an effective motion prior that can accurately track the temporal evolution of motion in various downstream tasks. Inspired by the success of foundation models, we argue that a robust spatio-temporal…

Understanding how humans interact with the world necessitates accurate 3D hand pose estimation, a task complicated by the hand's high degree of articulation, frequent occlusions, self-occlusions, and rapid motions. While most existing…

Recent progress in human shape learning, shows that neural implicit models are effective in generating 3D human surfaces from limited number of views, and even from a single RGB image. However, existing monocular approaches still struggle…

Human de-occlusion, which aims to infer the appearance of invisible human parts from an occluded image, has great value in many human-related tasks, such as person re-id, and intention inference. To address this task, this paper proposes a…

An important goal of self-supervised learning is to enable model pre-training to benefit from almost unlimited data. However, one method that has recently become popular, namely masked image modeling (MIM), is suspected to be unable to…

Masked Image Modeling (MIM) is a new self-supervised vision pre-training paradigm using a Vision Transformer (ViT). Previous works can be pixel-based or token-based, using original pixels or discrete visual tokens from parametric tokenizer…

Statistical models of 3D human shape and pose learned from scan databases have developed into valuable tools to solve a variety of vision and graphics problems. Unfortunately, most publicly available models are of limited expressiveness as…

We develop a robust multi-scale structure-aware neural network for human pose estimation. This method improves the recent deep conv-deconv hourglass models with four key improvements: (1) multi-scale supervision to strengthen contextual…

Masked Image Modeling (MIM) has become an essential method for building foundational visual models in remote sensing (RS). However, the limitations in size and diversity of existing RS datasets restrict the ability of MIM methods to learn…

Human action recognition is a crucial task for intelligent robotics, particularly within the context of human-robot collaboration research. In self-supervised skeleton-based action recognition, the mask-based reconstruction paradigm learns…

Dense pixel-specific representation learning at scale has been bottlenecked due to the unavailability of large-scale multi-view datasets. Current methods for building effective pretraining datasets heavily rely on annotated 3D meshes, point…

It is always well believed that parsing an image into constituent visual patterns would be helpful for understanding and representing an image. Nevertheless, there has not been evidence in support of the idea on describing an image with a…

Humans combine prediction and perception to observe the world. When faced with rapidly moving birds or insects, we can only perceive them clearly by predicting their next position and focusing our gaze there. Inspired by this, this paper…

Despite remarkable progress in computer vision, modern recognition systems remain fundamentally limited by their dependence on rich, redundant visual inputs. In contrast, humans can effortlessly understand sparse, minimal representations…

Forecasting 3D human motion is an important embodiment of fine-grained understanding and cognition of human behavior by artificial agents. Current approaches excessively rely on implicit network modeling of spatiotemporal relationships and…

Recent techniques on implicit geometry representation learning and neural rendering have shown promising results for 3D clothed human reconstruction from sparse video inputs. However, it is still challenging to reconstruct detailed surface…

We present deep neural network methodology to reconstruct the 3d pose and shape of people, given an input RGB image. We rely on a recently introduced, expressivefull body statistical 3d human model, GHUM, trained end-to-end, and learn to…