Search Results for author:
Found 12 papers, 6 papers with code
Can only LLMs do Reasoning?: Potential of Small Language Models in Task Planning
This leads us to pose a question: If small LMs can be trained to reason in chains within a single domain, would even small LMs be good task planners for the robots?
A Unified Masked Autoencoder with Patchified Skeletons for Motion Synthesis
Experimental results show that our model successfully forecasts human motion on the Human3. 6M dataset.
Human-Object Interaction Prediction in Videos through Gaze Following
Understanding the human-object interactions (HOIs) from a video is essential to fully comprehend a visual scene.
Ranked #2 on
Human-Object Interaction Anticipation
on VidHOI
Human-Object Interaction Anticipation
Human-Object Interaction Detection
+1
Can We Use Diffusion Probabilistic Models for 3D Motion Prediction?
After many researchers observed fruitfulness from the recent diffusion probabilistic model, its effectiveness in image generation is actively studied these days.
Robust Human Motion Forecasting using Transformer-based Model
In addition, our model is tested in conditions where the human motion is severely occluded, demonstrating its robustness in reconstructing and predicting 3D human motion in a highly noisy environment.
Intention-Conditioned Long-Term Human Egocentric Action Forecasting
Our framework first extracts two level of human information over the N observed videos human actions through a Hierarchical Multi-task MLP Mixer (H3M).
Ranked #1 on
Long Term Action Anticipation
on Ego4D
Self-Supervised Motion Retargeting with Safety Guarantee
In this paper, we present self-supervised shared latent embedding (S3LE), a data-driven motion retargeting method that enables the generation of natural motions in humanoid robots from motion capture data or RGB videos.
Refining Action Segmentation With Hierarchical Video Representations
In this paper, we propose Hierarchical Action Segmentation Refiner (HASR), which can refine temporal action segmentation results from various models by understanding the overall context of a given video in a hierarchical way.
Ranked #12 on
Action Segmentation
on 50 Salads
Visually Grounding Language Instruction for History-Dependent Manipulation
We also suggest a relevant dataset and model which can be a baseline, and show that our model trained with the proposed dataset can also be applied to the real world based on the CycleGAN.
Generative Autoregressive Networks for 3D Dancing Move Synthesis from Music
The trained dance pose generator, which is a generative autoregressive model, is able to synthesize a dance sequence longer than 5, 000 pose frames.
Interactive Text2Pickup Network for Natural Language based Human-Robot Collaboration
To handle the inherent ambiguity in human language commands, a suitable question which can resolve the ambiguity is generated.
Text2Action: Generative Adversarial Synthesis from Language to Action
We demonstrate that the network can generate human-like actions which can be transferred to a Baxter robot, such that the robot performs an action based on a provided sentence.
