Current human motion synthesis frameworks rely on global action descriptions, creating a modality gap that limits both motion understanding and generation capabilities. A single coarse description, such as run, fails to capture details such as variations in speed, limb positioning, and kinematic dynamics, leading to ambiguities between text and motion modalities. To address this challenge, we introduce KinMo, a unified framework built on a hierarchical describable motion representation that extends beyond global actions by incorporating kinematic group movements and their interactions. We design an automated annotation pipeline to generate high-quality, fine-grained descriptions for this decomposition, resulting in the KinMo dataset and offering a scalable and cost-efficient solution for dataset enrichment. To leverage these structured descriptions, we propose Hierarchical Text-Motion Alignment that progressively integrates additional motion details, thereby improving semantic motion understanding. Furthermore, we introduce a coarse-to-fine motion generation procedure to leverage enhanced spatial understanding to improve motion synthesis. Experimental results show that KinMo significantly improves motion understanding, demonstrated by enhanced text-motion retrieval performance and enabling more fine-grained motion generation and editing capabilities. Project Page: https://andypinxinliu.github.io/KinMo

We introduce a novel approach to generate diverse high fidelity texture maps for 3D human meshes in a semi-supervised setup. Given a segmentation mask defining the layout of the semantic regions in the texture map, our network generates high-resolution textures with a variety of styles, that are then used for rendering purposes. To accomplish this task, we propose a Region-adaptive Adversarial Variational AutoEncoder (ReAVAE) that learns the probability distribution of the style of each region individually so that the style of the generated texture can be controlled by sampling from the region-specific distributions. In addition, we introduce a data generation technique to augment our training set with data lifted from single-view RGB inputs. Our training strategy allows the mixing of reference image styles with arbitrary styles for different regions, a property which can be valuable for virtual try-on AR/VR applications. Experimental results show that our method synthesizes better texture maps compared to prior work while enabling independent layout and style controllability.

A digital calculator is one of the most frequently used touch screen applications. However, keypad-based character input in existing calculator applications requires precise, targeted key presses that are time-consuming and error-prone for many screen readers users. We introduce GestureCalc, a digital calculator that uses target-free gestures for arithmetic tasks. It allows eyes-free target-less input of digits and operations through taps and directional swipes with one to three fingers, guided by minimal audio feedback. We conducted a mixed methods longitudinal study with eight screen reader users and found that they entered characters with GestureCalc 40.5% faster on average than with a typical touch screen calculator. Participants made more mistakes but also corrected more errors with GestureCalc, resulting in 52.2% fewer erroneous calculations than the baseline. Over the three sessions in the study, participants were able to learn the GestureCalc gestures and efficiently perform short calculations. From our interviews after the second session, participants recognized the effort in learning a new gesture set, yet reported confidence in their ability to become fluent in practice.

Keypad-based character input in existing digital calculator applications on touch screen devices requires precise, targeted key presses that are time-consuming and error-prone for many screen reader users. We demonstrate GestureCalc, a digital calculator that uses target-free gestures for arithmetic tasks. It allows eyes-free target-less input of digits and operations through taps and directional swipes with one to three fingers, guided by minimal audio feedback. A study of the effectiveness of GestureCalc for screen reader users appears in a full paper by the authors at this conference.

Facial motion retargeting is an important problem in both computer graphics and vision, which involves capturing the performance of a human face and transferring it to another 3D character. Learning 3D morphable model (3DMM) parameters from 2D face images using convolutional neural networks is common in 2D face alignment, 3D face reconstruction etc. However, existing methods either require an additional face detection step before retargeting or use a cascade of separate networks to perform detection followed by retargeting in a sequence. In this paper, we present a single end-to-end network to jointly predict the bounding box locations and 3DMM parameters for multiple faces. First, we design a novel multitask learning framework that learns a disentangled representation of 3DMM parameters for a single face. Then, we leverage the trained single face model to generate ground truth 3DMM parameters for multiple faces to train another network that performs joint face detection and motion retargeting for images with multiple faces. Experimental results show that our joint detection and retargeting network has high face detection accuracy and is robust to extreme expressions and poses while being faster than state-of-the-art methods.

We present ExprGen, a system to automatically generate 3D stylized character expressions from humans in a perceptually valid and geometrically consistent manner. Our multi-stage deep learning system utilizes the latent variables of human and character expression recognition convolutional neural networks to control a 3D animated character rig. This end-to-end system takes images of human faces and generates the character rig parameters that best match the human's facial expression. ExprGen generalizes to multiple characters, and allows expression transfer between characters in a semi-supervised manner. Qualitative and quantitative evaluation of our method based on Mechanical Turk tests show the high perceptual accuracy of our expression transfer results.

Conventional supervised content-based remote sensing (RS) image retrieval systems require a large number of already annotated images to train a classifier for obtaining high retrieval accuracy. Most systems assume that each training image is annotated by a single label associated to the most significant semantic content of the image. However, this assumption does not fit well with the complexity of RS images, where an image might have multiple land-cover classes (i.e., multilabels). Moreover, annotating images with multilabels is costly and time consuming. To address these issues, in this paper, we introduce a semisupervised graph-theoretic method in the framework of multilabel RS image retrieval problems. The proposed method is based on four main steps. The first step segments each image in the archive and extracts the features of each region. The second step constructs an image neighborhood graph and uses a correlated label propagation algorithm to automatically assign a set of labels to each image in the archive by exploiting only a small number of training images annotated with multilabels. The third step associates class labels with image regions by a novel region labeling strategy, whereas the final step retrieves the images similar to a given query image by a subgraph matching strategy. Experiments carried out on an archive of aerial images show the effectiveness of the proposed method when compared with the state-of-the-art RS content-based image retrieval methods.

This letter introduces a novel unsupervised graph-theoretic approach in the framework of region-based retrieval of remote sensing (RS) images. The proposed approach is characterized by two main steps: (1) modeling each image by a graph, which provides region-based image representation combining both local information and related spatial organization, and (2) retrieving the images in the archive that are most similar to the query image by evaluating graph-based similarities. In the first step, each image is initially segmented into distinct regions and then modeled by an attributed relational graph, where nodes and edges represent region characteristics and their spatial relationships, respectively. In the second step, a novel inexact graph matching strategy, which jointly exploits a subgraph isomorphism algorithm and a spectral graph embedding technique, is applied to match corresponding graphs and to retrieve images in the order of graph similarity. Experiments carried out on an archive of aerial images point out that the proposed approach significantly improves the retrieval performance compared to the state-of-the-art unsupervised RS image retrieval methods.(RS) images.