Related papers: Human Part-wise 3D Motion Context Learning for Sig…

Different from traditional video retrieval, sign language retrieval is more biased towards understanding the semantic information of human actions contained in video clips. Previous works typically only encode RGB videos to obtain…

Vision-based sign language recognition aims at helping deaf people to communicate with others. However, most existing sign language datasets are limited to a small number of words. Due to the limited vocabulary size, models learned from…

Recent studies have shown remarkable advances in 3D human pose estimation from monocular images, with the help of large-scale in-door 3D datasets and sophisticated network architectures. However, the generalizability to different…

Estimation of 3D human pose from monocular image has gained considerable attention, as a key step to several human-centric applications. However, generalizability of human pose estimation models developed using supervision on large-scale…

Pose-estimation methods enable extracting human motion from common videos in the structured form of 3D skeleton sequences. Despite great application opportunities, effective content-based access to such spatio-temporal motion data is a…

Skeleton-based Temporal Action Segmentation involves the dense action classification of variable-length skeleton sequences. Current approaches primarily apply graph-based networks to extract framewise, whole-body-level motion…

Generating animations from natural language sentences finds its applications in a a number of domains such as movie script visualization, virtual human animation and, robot motion planning. These sentences can describe different kinds of…

This paper presents a novel method for learning a pose lexicon comprising semantic poses defined by textual instructions and their associated visual poses defined by visual features. The proposed method simultaneously takes two input…

Recovering temporally consistent 3D human body pose, shape and motion from a monocular video is a challenging task due to (self-)occlusions, poor lighting conditions, complex articulated body poses, depth ambiguity, and limited availability…

3D scene understanding is fundamental for embodied AI and robotics, supporting reliable perception for interaction and navigation. Recent approaches achieve zero-shot, open-vocabulary 3D semantic mapping by assigning embedding vectors to 2D…

Most state-of-the-art methods for action recognition rely only on 2D spatial features encoding appearance, motion or pose. However, 2D data lacks the depth information, which is crucial for recognizing fine-grained actions. In this paper,…

The connection between our 3D surroundings and the descriptive language that characterizes them would be well-suited for localizing and generating human motion in context but for one problem. The complexity introduced by multiple modalities…

In this work we present a novel approach to joint semantic localisation and scene understanding. Our work is motivated by the need for localisation algorithms which not only predict 6-DoF camera pose but also simultaneously recognise…

Recognition of human poses and actions is crucial for autonomous systems to interact smoothly with people. However, cameras generally capture human poses in 2D as images and videos, which can have significant appearance variations across…

Parsing human body into semantic regions is crucial to human-centric analysis. In this paper, we propose a segment-based parsing pipeline that explores human pose information, i.e. the joint location of a human model, which improves the…

Learning descriptive 3D features is crucial for understanding 3D scenes with diverse objects and complex structures. However, it is usually unknown whether important geometric attributes and scene context obtain enough emphasis in an…

This paper aims to model 3D human motion across domains, where a single model is expected to handle multiple modalities, tasks, and datasets. Existing cross-domain models often rely on domain-specific components and multi-stage training,…

We propose a novel 3D gaze estimation approach that learns spatial relationships between the subject and objects in the scene, and outputs 3D gaze direction. Our method targets unconstrained settings, including cases where close-up views of…

For human pose estimation in still images, this paper proposes three semi- and weakly-supervised learning schemes. While recent advances of convolutional neural networks improve human pose estimation using supervised training data, our…

We present a method to combine markerless motion capture and dense pose feature estimation into a single framework. We demonstrate that dense pose information can help for multiview/single-view motion capture, and multiview motion capture…