31 citations · 51 across the 6 of their papers we have counts for
6 papers · 1 filter
GEM: Generating LiDAR World Model via Deformable Mamba
Yang Wu, Zhaojiang Liu, Qiang Meng +5
World models, which simulate environmental dynamics and generate sensor observations, are gaining increasing attention in autonomous driving. However, progress in LiDAR-based world…
Joint Spatial-Temporal and Appearance Modeling with Transformer for Multiple Object Tracking
Peng Dai, Yiqiang Feng, Renliang Weng +1
The recent trend in multiple object tracking (MOT) is heading towards leveraging deep learning to boost the tracking performance. In this paper, we propose a novel solution named T…
3SD: Self-Supervised Saliency Detection With No Labels
Rajeev Yasarla, Renliang Weng, Wongun Choi +2
We present a conceptually simple self-supervised method for saliency detection. Our method generates and uses pseudo-ground truth labels for training. The generated pseudo-GT label…
Ray3D: ray-based 3D human pose estimation for monocular absolute 3D localization
Yu Zhan, Fenghai Li, Renliang Weng +1
In this paper, we propose a novel monocular ray-based 3D (Ray3D) absolute human pose estimation with calibrated camera. Accurate and generalizable absolute 3D human pose estimation…
IIP-Transformer: Intra-Inter-Part Transformer for Skeleton-Based Action Recognition
Qingtian Wang, Jianlin Peng, Shuze Shi +3
Recently, Transformer-based networks have shown great promise on skeleton-based action recognition tasks. The ability to capture global and local dependencies is the key to success…
Learning a Proposal Classifier for Multiple Object Tracking
Peng Dai, Renliang Weng, Wongun Choi +3
The recent trend in multiple object tracking (MOT) is heading towards leveraging deep learning to boost the tracking performance. However, it is not trivial to solve the data-assoc…