Search Results for author:
Found 5 papers, 4 papers with code
Joint Spatial-Temporal and Appearance Modeling with Transformer for Multiple Object Tracking
The recent trend in multiple object tracking (MOT) is heading towards leveraging deep learning to boost the tracking performance.
Ray3D: ray-based 3D human pose estimation for monocular absolute 3D localization
Accurate and generalizable absolute 3D human pose estimation from monocular 2D pose input is an ill-posed problem.
Ranked #1 on
Monocular 3D Human Pose Estimation
on Human3.6M
(Use Video Sequence metric)
3SD: Self-Supervised Saliency Detection With No Labels
Our method generates and uses pseudo-ground truth labels for training.
IIP-Transformer: Intra-Inter-Part Transformer for Skeleton-Based Action Recognition
From the data aspect, we introduce a part-level skeleton data encoding that significantly reduces the computational complexity and is more robust to joint-level skeleton noise.
Learning a Proposal Classifier for Multiple Object Tracking
In this paper, we propose a novel proposal-based learnable framework, which models MOT as a proposal generation, proposal scoring and trajectory inference paradigm on an affinity graph.
