相关论文: An Identity-Preserved Framework for Human Motion T…

We study the problem of human action recognition using motion capture (MoCap) sequences. Unlike existing techniques that take multiple manual steps to derive standardized skeleton representations as model input, we propose a novel…

We introduce Human Motion Unlearning and motivate it through the concrete task of preventing violent 3D motion synthesis, an important safety requirement given that popular text-to-motion datasets (HumanML3D and Motion-X) contain from 7\%…

Text-driven human motion synthesis has showcased its potential for revolutionizing motion design in the movie and game industry. Existing methods often rely on 3D motion capture data, which requires special setups, resulting in high costs…

Identity-preserving text-to-video (IPT2V) generation aims to create high-fidelity videos with consistent human identity. It is an important task in video generation but remains an open problem for generative models. This paper pushes the…

We propose PressureTransferNet, a novel method for Human Activity Recognition (HAR) using ground pressure information. Our approach generates body-specific dynamic ground pressure profiles for specific activities by leveraging existing…

Human Motion Segmentation (HMS), which aims to partition a video into non-overlapping segments corresponding to different human motions, has recently attracted increasing research attention. Existing HMS approaches are predominantly based…

We present a data-driven framework for unsupervised human motion retargeting that animates a target subject with the motion of a source subject. Our method is correspondence-free, requiring neither spatial correspondences between the source…

Most existing video tasks related to "human" focus on the segmentation of salient humans, ignoring the unspecified others in the video. Few studies have focused on segmenting and tracking all humans in a complex video, including pedestrians…

Recognizing human actions in untrimmed videos is an important challenging task. An effective 3D motion representation and a powerful learning model are two key factors influencing recognition performance. In this paper we introduce a new…

Cross-embodiment video generation aims to transfer motions across different humanoid embodiments, such as human-to-robot and robot-to-robot, enabling scalable data generation for embodied intelligence. A major challenge in this setting is…

This paper introduces a novel deep learning framework for image animation. Given an input image with a target object and a driving video sequence depicting a moving object, our framework generates a video in which the target object is…

This paper proposes a new end-to-end neural rendering architecture to transfer appearance and reenact human actors. Our method leverages a carefully designed graph convolutional network (GCN) to model the human body manifold structure,…

Scaling real robot data is a key bottleneck in imitation learning, leading to the use of auxiliary data for policy training. While other aspects of robotic manipulation such as image or language understanding may be learned from…

Existing Graph Convolutional Networks to achieve human motion prediction largely adopt a one-step scheme, which output the prediction straight from history input, failing to exploit human motion patterns. We observe that human motions have…

Videos convey richer information than images or text, capturing both spatial and temporal dynamics. However, most existing video customization methods rely on reference images or task-specific temporal priors, failing to fully exploit the…

We describe a novel metric-based learning approach that introduces a multimodal framework and uses deep audio and geophone encoders in siamese configuration to design an adaptable and lightweight supervised model. This framework eliminates…

Vision-based human-to-robot handover is an important and challenging task in human-robot interaction. Recent work has attempted to train robot policies by interacting with dynamic virtual humans in simulated environments, where the policies…

This paper proposes MotionVerse, a unified framework that harnesses the capabilities of Large Language Models (LLMs) to comprehend, generate, and edit human motion in both single-person and multi-person scenarios. To efficiently represent…

Visible-infrared person re-identification (VI-ReID) technique could associate the pedestrian images across visible and infrared modalities in the practical scenarios of background illumination changes. However, a substantial gap inherently…

Generating diverse and natural human motion is one of the long-standing goals for creating intelligent characters in the animated world. In this paper, we propose a self-supervised method for generating long-range, diverse and plausible…