Search Results for author:
Found 10 papers, 6 papers with code
Multi-Track Timeline Control for Text-Driven 3D Human Motion Generation
To generate composite animations from a multi-track timeline, we propose a new test-time denoising method.
TMR: Text-to-Motion Retrieval Using Contrastive 3D Human Motion Synthesis
We show that maintaining the motion generation loss, along with the contrastive training, is crucial to obtain good performance.
SINC: Spatial Composition of 3D Human Motions for Simultaneous Action Generation
Motivated by the observation that the correspondence between actions and body parts is encoded in powerful language models, we extract this knowledge by prompting GPT-3 with text such as "what are the body parts involved in the action <action name>?
TEACH: Temporal Action Composition for 3D Humans
In particular, our goal is to enable the synthesis of a series of actions, which we refer to as temporal action composition.
TEMOS: Generating diverse human motions from textual descriptions
In contrast to most previous work which focuses on generating a single, deterministic, motion from a textual description, we design a variational approach that can produce multiple diverse human motions.
Ranked #7 on
Motion Synthesis
on InterHuman
Action-Conditioned 3D Human Motion Synthesis with Transformer VAE
By sampling from this latent space and querying a certain duration through a series of positional encodings, we synthesize variable-length motion sequences conditioned on a categorical action.
Feature-Robust Optimal Transport for High-Dimensional Data
To show the effectiveness of FROT, we propose using the FROT algorithm for the layer selection problem in deep neural networks for semantic correspondence.
Feature Robust Optimal Transport for High-dimensional Data
To show the effectiveness of FROT, we propose using the FROT algorithm for the layer selection problem in deep neural networks for semantic correspondence.
Fast local linear regression with anchor regularization
Regression is an important task in machine learning and data mining.
FsNet: Feature Selection Network on High-dimensional Biological Data
Because a large number of parameters in the selection and reconstruction layers can easily result in overfitting under a limited number of samples, we use two tiny networks to predict the large, virtual weight matrices of the selection and reconstruction layers.
