361 citations · 1.3k across the 81 of their papers we have counts for
14 papers · 1 filter
Material Classification in the Wild: Do Synthesized Training Data Generalise Better than Real-World Training Data?
Grigorios Kalliatakis, Anca Sticlaru, George Stamatiadis +4
We question the dominant role of real-world training images in the field of material classification by investigating whether synthesized data can generalise more effectively than r…
PoseTrack: A Benchmark for Human Pose Estimation and Tracking
Mykhaylo Andriluka, Umar Iqbal, Eldar Insafutdinov +4
Human poses and motions are important cues for analysis of videos with people and there is strong evidence that representations based on body pose are highly effective for a variet…
SurfaceNet: An End-to-end 3D Neural Network for Multiview Stereopsis
Mengqi Ji, Juergen Gall, Haitian Zheng +2
This paper proposes an end-to-end learning framework for multiview stereopsis. We term the network SurfaceNet. It takes a set of images and their corresponding camera parameters as…
Adaptive Binarization for Weakly Supervised Affordance Segmentation
Johann Sawatzky, Juergen Gall
The concept of affordance is important to understand the relevance of object parts for a certain functional interaction. Affordance types generalize across object categories and ar…
Recurrent Residual Learning for Action Recognition
Ahsan Iqbal, Alexander Richard, Hilde Kuehne +1
Action recognition is a fundamental problem in computer vision with a lot of potential applications such as video surveillance, human computer interaction, and robot learning. Give…
Action Sets: Weakly Supervised Action Segmentation without Ordering Constraints
Alexander Richard, Hilde Kuehne, Juergen Gall
Action detection and temporal segmentation of actions in videos are topics of increasing interest. While fully supervised systems have gained much attention lately, full annotation…
A Dual-Source Approach for 3D Human Pose Estimation from a Single Image
Umar Iqbal, Andreas Doering, Hashim Yasin +3
In this work we address the challenging problem of 3D human pose estimation from single images. Recent approaches learn deep neural networks to regress 3D pose directly from images…
3D Object Reconstruction from Hand-Object Interactions
Dimitrios Tzionas, Juergen Gall
Recent advances have enabled 3d object reconstruction approaches using a single off-the-shelf RGB-D camera. Although these approaches are successful for a wide range of object clas…
Capturing Hand Motion with an RGB-D Sensor, Fusing a Generative Model with Salient Points
Dimitrios Tzionas, Abhilash Srikantha, Pablo Aponte +1
Hand motion capture has been an active research topic in recent years, following the success of full-body pose tracking. Despite similarities, hand tracking proves to be more chall…
A Comparison of Directional Distances for Hand Pose Estimation
Dimitrios Tzionas, Juergen Gall
Benchmarking methods for 3d hand tracking is still an open problem due to the difficulty of acquiring ground truth data. We introduce a new dataset and benchmarking protocol that i…
A Bag-of-Words Equivalent Recurrent Neural Network for Action Recognition
Alexander Richard, Juergen Gall
The traditional bag-of-words approach has found a wide range of applications in computer vision. The standard pipeline consists of a generation of a visual vocabulary, a quantizati…
Detection of Human Rights Violations in Images: Can Convolutional Neural Networks help?
Grigorios Kalliatakis, Shoaib Ehsan, Maria Fasli +3
After setting the performance benchmarks for image, video, speech and audio processing, deep convolutional networks have been core to the greatest advances in image recognition tas…
Evaluating Deep Convolutional Neural Networks for Material Classification
Grigorios Kalliatakis, Georgios Stamatiadis, Shoaib Ehsan +4
Determining the material category of a surface from an image is a demanding task in perception that is drawing increasing attention. Following the recent remarkable results achieve…
Weakly Supervised Action Learning with RNN based Fine-to-coarse Modeling
Alexander Richard, Hilde Kuehne, Juergen Gall
We present an approach for weakly supervised learning of human actions. Given a set of videos and an ordered list of the occurring actions, the goal is to infer start and end frame…