Search Results for author:
Found 15 papers, 5 papers with code
InsActor: Instruction-driven Physics-based Characters
Generating animation of physics-based characters with intuitive control has long been a desirable task with numerous applications.
Vision-Language Foundation Models as Effective Robot Imitators
We believe RoboFlamingo has the potential to be a cost-effective and easy-to-use solution for robotics manipulation, empowering everyone with the ability to fine-tune their own robotics policy.
DiffMimic: Efficient Motion Mimicking with Differentiable Physics
Motion mimicking is a foundational task in physics-based character animation.
Balanced MSE for Imbalanced Visual Regression
Data imbalance exists ubiquitously in real-world visual regressions, e. g., age estimation and pose estimation, hurting the model's generalizability and fairness.
Bayesian Imbalanced Regression Debiasing
Compared to imbalanced and long-tailed classification, imbalanced regression has its unique challenges as the regression label space can be continuous, boundless, and high-dimensional.
REFINE: Prediction Fusion Network for Panoptic Segmentation
Panoptic segmentation aims at generating pixel-wise class and instance predictions for each pixel in the input image, which is a challenging task and far more complicated than naively fusing the semantic and instance segmentation results.
Ranked #11 on
Panoptic Segmentation
on COCO test-dev
Balanced Activation for Long-tailed Visual Recognition
Deep classifiers have achieved great success in visual recognition.
Leveraging Localization for Multi-camera Association
We present McAssoc, a deep learning approach to the as-sociation of detection bounding boxes in different views ofa multi-camera system.
MessyTable: Instance Association in Multiple Camera Views
We present an interesting and challenging dataset that features a large number of scenes with messy tables captured from multiple camera views.
Balanced Meta-Softmax for Long-Tailed Visual Recognition
In our experiments, we demonstrate that Balanced Meta-Softmax outperforms state-of-the-art long-tailed classification solutions on both visual recognition and instance segmentation tasks.
Ranked #7 on
Long-tail Learning
on CIFAR-10-LT (ρ=10)
Leveraging Temporal Information for 3D Detection and Domain Adaptation
Ever since the prevalent use of the LiDARs in autonomous driving, tremendous improvements have been made to the learning on the point clouds.
Spatio-Temporal Graph Transformer Networks for Pedestrian Trajectory Prediction
In this paper, we present STAR, a Spatio-Temporal grAph tRansformer framework, which tackles trajectory prediction by only attention mechanisms.
Learning an Efficient Network for Large-Scale Hierarchical Object Detection with Data Imbalance: 3rd Place Solution to Open Images Challenge 2019
This report details our solution to the Google AI Open Images Challenge 2019 Object Detection Track.
3D Convolution on RGB-D Point Clouds for Accurate Model-free Object Pose Estimation
The conventional pose estimation of a 3D object usually requires the knowledge of the 3D model of the object.
