For faster sampling and higher sample quality, we propose DiNof
(Diffusi...
A new method is proposed for human motion prediction by learning tempora...
We investigate the impact of pre-defined keypoints for pose estimation, ...
We propose a novel solution for predicting future trajectories of
pedest...
A continual learning solution is proposed to address the out-of-distribu...
The Long-Tailed Recognition (LTR) problem emerges in the context of lear...
We propose a method that augments a simulated dataset using diffusion mo...
We propose a novel keypoint voting 6DoF object pose estimation method, w...
We present ObjectBox, a novel single-stage anchor-free and highly
genera...
We propose a multitask approach for crowd counting and person localizati...
This work presents a novel approach to improve the results of pose estim...
A novel object detection method is presented that handles freely rotated...
A new method is proposed for human motion predition by learning temporal...
We propose a novel keypoint voting scheme based on intersecting spheres,...
We present the Teacher-Student Generative Adversarial Network (TS-GAN) t...
A novel user friendly method is proposed for calibrating a procam system...
Face representation learning solutions have recently achieved great succ...
We explore end-to-end trained differentiable models that integrate natur...
Commonsense reasoning simulates the human ability to make presumptions a...
We propose the new problem of learning to recover reasoning chains from
...
A novel attention aware method is proposed to fuse two image modalities,...
A novel multi-scale operator for unorganized 3D point clouds is introduc...