paper-conference

Comparing humans and machines: the case of object detection
The success of deep learning models raises the question of how they achieve these impressive results and to what degree performance is …
Minsuk Sung, Björn Browatzki, Christian Wallraven
Cite
Comparing humans and machines: the case of object detection
TARDIS-Pose: Targeted Distillation of Self-Supervised ViT features for Animal Pose Estimation
Animal pose estimation is an important ingredient of many real-world applications in behavior monitoring, agriculture, and wildlife …
Björn Browatzki, Christian Wallraven
PDF Cite
TARDIS-Pose: Targeted Distillation of Self-Supervised ViT features for Animal Pose Estimation
Encoder-Decoder Networks for Retinal Vessel Segmentation Using Large Multi-scale Patches
We propose an encoder-decoder framework for the segmentation of blood vessels in retinal images that relies on the extraction of …
Björn Browatzki, Jörn Philipp Lies, Christian Wallraven
PDF Cite Video DOI
Encoder-Decoder Networks for Retinal Vessel Segmentation Using Large Multi-scale Patches
3FabRec: Fast Few-Shot Face Alignment by Reconstruction
Current supervised methods for facial landmark detection require a large amount of training data and may suffer from overfitting to specific datasets due to the massive number of parameters. […]
Björn Browatzki, Christian Wallraven
PDF Cite Code DOI arXiv Video (1min) Video (5min)
3FabRec: Fast Few-Shot Face Alignment by Reconstruction
Robust discrimination and generation of faces using compact, disentangled embeddings
Current solutions to discriminative and generative tasks in computer vision exist separately and often lack interpretability and …
Björn Browatzki, Christian Wallraven
PDF Cite DOI supplementary
Robust discrimination and generation of faces using compact, disentangled embeddings
Active object recognition on a humanoid robot
Interaction with its environment is a key requisite for a humanoid robot. Especially the ability to recognize and manipulate unknown …
Björn Browatzki, Vadim Tikhanoff, Giorgio Metta, Heinrich H. Bulthoff, Christian Wallraven
PDF Cite DOI Video
Active object recognition on a humanoid robot
Going into depth: Evaluating 2D and 3D cues for object classification on a new large-scale object dataset
Categorization of objects solely based on shape and appearance is still a largely unresolved issue. With the advent of new sensor …
Björn Browatzki, Jan Fischer, Birgit Graf, Heinrich H. Bulthoff, Christian Wallraven
Cite DOI Dataset
Going into depth: Evaluating 2D and 3D cues for object classification on a new large-scale object dataset
Image retrieval with semantic sketches
With increasingly large image databases, searching in them becomes an ever more difficult endeavor. Consequently, there is a need for …
David Engel, Christian Herdtweck, Björn Browatzki, Cristóbal Curio
Cite DOI