Related papers: Weakly and Semi Supervised Human Body Part Parsing…

In semi-supervised segmentation, capturing meaningful semantic structures from unlabeled data is essential. This is particularly challenging in histopathology image analysis, where objects are densely distributed. To address this issue, we…

Estimating human pose, shape, and motion from images and videos are fundamental challenges with many applications. Recent advances in 2D human pose estimation use large amounts of manually-labeled training data for learning convolutional…

The success of large language models has inspired the computer vision community to explore image segmentation foundation model that is able to zero/few-shot generalize through prompt engineering. Segment-Anything(SAM), among others, is the…

Skeleton-based temporal action segmentation is a fundamental yet challenging task, playing a crucial role in enabling intelligent systems to perceive and respond to human activities. While fully-supervised methods achieve satisfactory…

Segmenting humans in 3D indoor scenes has become increasingly important with the rise of human-centered robotics and AR/VR applications. To this end, we propose the task of joint 3D human semantic segmentation, instance segmentation and…

The main challenges of 3D pose transfer are: 1) Lack of paired training data with different characters performing the same pose; 2) Disentangling pose and shape information from the target mesh; 3) Difficulty in applying to meshes with…

In the scenario of one/multi-shot learning, conventional end-to-end learning strategies without sufficient supervision are usually not powerful enough to learn correct patterns from noisy signals. Thus, given a CNN pre-trained for object…

We propose a method for hand pose estimation based on a deep regressor trained on two different kinds of input. Raw depth data is fused with an intermediate representation in the form of a segmentation of the hand into parts. This…

Annotation of medical images has been a major bottleneck for the development of accurate and robust machine learning models. Annotation is costly and time-consuming and typically requires expert knowledge, especially in the medical domain.…

Aligning multiple modalities in a latent space, such as images and texts, has shown to produce powerful semantic visual representations, fueling tasks like image captioning, text-to-image generation, or image grounding. In the context of…

Parsing human poses in images is fundamental in extracting critical visual information for artificial intelligent agents. Our goal is to learn self-contained body part representations from images, which we call visual symbols, and their…

Automatic human matting is highly desired for many real applications. We investigate recent human matting methods and show that common bad cases happen when semantic human segmentation fails. This indicates that semantic understanding is…

Superior human pose and shape reconstruction from monocular images depends on removing the ambiguities caused by occlusions and shape variance. Recent works succeed in regression-based methods which estimate parametric models directly…

Human skeletons and RGB sequences are both widely-adopted input modalities for human action recognition. However, skeletons lack appearance features and color data suffer large amount of irrelevant depiction. To address this, we introduce…

We present a new pose transfer method for synthesizing a human animation from a single image of a person controlled by a sequence of body poses. Existing pose transfer methods exhibit significant visual artifacts when applying to a novel…

Modern deep learning-based 3D pose estimation approaches require plenty of 3D pose annotations. However, existing 3D datasets lack diversity, which limits the performance of current methods and their generalization ability. Although…

Human pose estimation deeply relies on visual clues and anatomical constraints between parts to locate keypoints. Most existing CNN-based methods do well in visual representation, however, lacking in the ability to explicitly learn the…

The goal of self-supervised visual representation learning is to learn strong, transferable image representations, with the majority of research focusing on object or scene level. On the other hand, representation learning at part level has…

The misaligned human texture across different human parts is one of the main limitations of existing 3D human reconstruction methods. Each human part, such as a jacket or pants, should maintain a distinct texture without blending into…

Human Activity Recognition (HAR) using on-body devices identifies specific human actions in unconstrained environments. HAR is challenging due to the inter and intra-variance of human movements; moreover, annotated datasets from on-body…