research
∙
12/02/2022
Transformer-Based Learned Optimization
In this paper, we propose a new approach to learned optimization. As com...
share
research
∙
05/24/2022
Trajectory Optimization for Physics-Based Reconstruction of 3d Human Pose from Monocular Video
We focus on the task of estimating a physically plausible articulated hu...
research
∙
05/24/2022
Differentiable Dynamics for Articulated 3d Human Motion Reconstruction
We introduce DiffPhy, a differentiable physics-based model for articulat...
research
∙
07/16/2020
Efficient Full Image Interactive Segmentation by Leveraging Within-image Appearance Similarity
We propose a new approach to interactive full-image semantic segmentatio...
research
∙
06/17/2019
Panoptic Image Annotation with a Collaborative Assistant
This paper aims to reduce the time to annotate images for the panoptic s...
research
∙
06/20/2018
Fluid Annotation: a human-machine collaboration interface for full image annotation
We introduce Fluid Annotation, an intuitive human-machine collaboration ...
research
∙
10/27/2017
PoseTrack: A Benchmark for Human Pose Estimation and Tracking
Human poses and motions are important cues for analysis of videos with p...
research
∙
12/05/2016
ArtTrack: Articulated Multi-person Tracking in the Wild
In this paper we propose an approach for articulated tracking of multipl...
research
∙
08/17/2016
Multi-Person Tracking by Multicut and Deep Matching
In [1], we proposed a graph-based formulation that links and clusters pe...
research
∙
07/21/2015
Every Moment Counts: Dense Detailed Labeling of Actions in Complex Videos
Every moment counts in action recognition. A comprehensive understanding...
research
∙
06/16/2015
End-to-end people detection in crowded scenes
Current people detectors operate either by scanning an image in a slidin...
research
∙
04/07/2015
An Empirical Evaluation of Deep Learning on Highway Driving
Numerous groups have applied a variety of deep learning techniques to co...
research
∙
02/23/2015
Recognizing Fine-Grained and Composite Activities using Hand-Centric Features and Script Data
Activity recognition has shown impressive progress in recent years. Howe...
research
∙
06/07/2014
Fine-grained Activity Recognition with Holistic and Pose based Features
Holistic methods based on dense trajectories are currently the de facto ...
research
∙
12/27/2013