361 citations · 1.3k across the 81 of their papers we have counts for
18 papers · 1 filter
Bonn Activity Maps: Dataset Description
Julian Tanke, Oh-Hun Kwon, Patrick Stotko +9
The key prerequisite for accessing the huge potential of current machine learning techniques is the availability of large databases that capture the complex relations of interest.…
Joint Viewpoint and Keypoint Estimation with Real and Synthetic Data
Pau Panareda Busto, Juergen Gall
The estimation of viewpoints and keypoints effectively enhance object detection methods by extracting valuable traits of the object instances. While the output of both processes di…
Human Motion Anticipation with Symbolic Label
Julian Tanke, Andreas Weber, Juergen Gall
Anticipating human motion depends on two factors: the past motion and the person's intention. While the first factor has been extensively utilized to forecast short sequences of hu…
Discovering Latent Classes for Semi-Supervised Semantic Segmentation
Olga Zatsarynna, Johann Sawatzky, Juergen Gall
High annotation costs are a major bottleneck for the training of semantic segmentation systems. Therefore, methods working with less annotation effort are of special interest. This…
Cross-modal knowledge distillation for action recognition
Fida Mohammad Thoker, Juergen Gall
In this work, we address the problem how a network for action recognition that has been trained on a modality like RGB videos can be adapted to recognize actions for another modali…
Uncertainty-Aware Anticipation of Activities
Yazan Abu Farha, Juergen Gall
Anticipating future activities in video is a task with many practical applications. While earlier approaches are limited to just a few seconds in the future, the prediction time ho…
Open Set Domain Adaptation for Image and Action Recognition
Pau Panareda Busto, Ahsan Iqbal, Juergen Gall
Since annotating and curating large datasets is very expensive, there is a need to transfer the knowledge from existing annotated datasets to unlabelled data. Data that is relevant…
A Hybrid RNN-HMM Approach for Weakly Supervised Temporal Action Segmentation
Hilde Kuehne, Alexander Richard, Juergen Gall
Action recognition has become a rapidly developing research field within the last decade. But with the increasing demand for large scale data, the need of hand annotated data for t…
Mining YouTube - A dataset for learning fine-grained action concepts from webly supervised video data
Hilde Kuehne, Ahsan Iqbal, Alexander Richard +1
Action recognition is so far mainly focusing on the problem of classification of hand selected preclipped actions and reaching impressive results in this field. But with the perfor…
Harvesting Information from Captions for Weakly Supervised Semantic Segmentation
Johann Sawatzky, Debayan Banerjee, Juergen Gall
Since acquiring pixel-wise annotations for training convolutional neural networks for semantic image segmentation is time-consuming, weakly supervised approaches that only require…
3D Semantic Scene Completion from a Single Depth Image using Adversarial Training
Yueh-Tung Chen, Martin Garbade, Juergen Gall
We address the task of 3D semantic scene completion, i.e. , given a single depth image, we predict the semantic labels and occupancy of voxels in a 3D grid representing the scene.…
Unifying Part Detection and Association for Recurrent Multi-Person Pose Estimation
Rania Briq, Andreas Doering, Juergen Gall
We propose a joint model of human joint detection and association for 2D multi-person pose estimation (MPPE). The approach unifies training of joint detection and association witho…
Unsupervised learning of action classes with continuous temporal embedding
Anna Kukleva, Hilde Kuehne, Fadime Sener +1
The task of temporally detecting and segmenting actions in untrimmed videos has seen an increased attention recently. One problem in this context arises from the need to define and…
What Object Should I Use? - Task Driven Object Detection
Johann Sawatzky, Yaser Souri, Christian Grund +1
When humans have to solve everyday tasks, they simply pick the objects that are most suitable. While the question which object should one use for a specific task sounds trivial for…
MS-TCN: Multi-Stage Temporal Convolutional Network for Action Segmentation
Yazan Abu Farha, Juergen Gall
Temporally locating and classifying action segments in long untrimmed videos is of particular interest to many applications like surveillance and robotics. While traditional approa…
Large Scale Holistic Video Understanding
Ali Diba, Mohsen Fayyaz, Vivek Sharma +4
Video recognition has been advanced in recent years by benchmarks with rich annotations. However, research is still mainly limited to human action or sports recognition - focusing…
Fast Weakly Supervised Action Segmentation Using Mutual Consistency
Yaser Souri, Mohsen Fayyaz, Luca Minciullo +2
Action segmentation is the task of predicting the actions for each frame of a video. As obtaining the full annotation of videos for action segmentation is expensive, weakly supervi…
SemanticKITTI: A Dataset for Semantic Scene Understanding of LiDAR Sequences
Jens Behley, Martin Garbade, Andres Milioto +4
Semantic scene understanding is important for various applications. In particular, self-driving cars need a fine-grained understanding of the surfaces and objects in their vicinity…