Search Results for author:
Found 24 papers, 5 papers with code
From colouring-in to pointillism: revisiting semantic segmentation supervision
The prevailing paradigm for producing semantic segmentation training data relies on densely labelling each pixel of each image in the training set, akin to colouring-in books.
Large-scale interactive object segmentation with human annotators
Manually annotating object segmentation masks is very time consuming.
Person Recognition in Personal Photo Collections
Person recognition in social media photos sets new challenges for computer vision, including non-cooperative subjects (e. g. backward viewpoints, unusual poses) and great changes in appearance.
Learning non-maximum suppression
Object detectors have hugely profited from moving towards an end-to-end learning paradigm: proposals, features, and the classifier becoming one neural network improved results two-fold on general object detection.
Lucid Data Dreaming for Video Object Segmentation
Our approach is suitable for both single and multiple object segmentation.
CityPersons: A Diverse Dataset for Pedestrian Detection
Convnets have enabled significant progress in pedestrian detection recently, but there are still open questions regarding suitable architectures and training data.
Ranked #14 on
Pedestrian Detection
on Caltech
Exploiting saliency for object segmentation from image level labels
We show how to combine both information sources in order to recover 80% of the fully supervised performance - which is the new state of the art in weakly supervised training for pixel-wise semantic labelling.
Ranked #26 on
Semantic Segmentation
on PASCAL VOC 2012 val
Learning Video Object Segmentation from Static Images
Inspired by recent advances of deep learning in instance segmentation and object tracking, we introduce video object segmentation problem as a concept of guided instance segmentation.
Ranked #6 on
Semi-Supervised Video Object Segmentation
on YouTube
Faceless Person Recognition; Privacy Implications in Social Media
As we shift more of our lives into the virtual domain, the volume of data shared on the web keeps increasing and presents a threat to our privacy.
Improved Image Boundaries for Better Video Segmentation
Graph-based video segmentation methods rely on superpixels as starting point.
The Cityscapes Dataset for Semantic Urban Scene Understanding
Visual understanding of complex urban street scenes is an enabling factor for a wide range of applications.
Simple Does It: Weakly Supervised Instance and Semantic Segmentation
Semantic labelling and instance segmentation are two tasks that require particularly costly annotations.
Ranked #1 on
Semantic Segmentation
on PASCAL VOC 2012 val
(Mean IoU metric)
How Far are We from Solving Pedestrian Detection?
We enable our analysis by creating a human baseline for pedestrian detection (over the Caltech dataset), and by manually clustering the recurrent errors of a top detector.
Weakly Supervised Object Boundaries
State-of-the-art learning based boundary detection methods require extensive training data.
Ranked #2 on
Edge Detection
on SBD
A convnet for non-maximum suppression
Non-maximum suppression (NMS) is used in virtually all state-of-the-art object detection pipelines.
Person Recognition in Personal Photo Collections
Recognising persons in everyday photos presents major challenges (occluded faces, different clothing, locations, etc.)
Filtered Feature Channels for Pedestrian Detection
This paper starts from the observation that multiple top performing pedestrian detectors can be modelled by using an intermediate layer filtering low-level features in combination with a boosted decision forest.
What makes for effective detection proposals?
Current top performing object detectors employ detection proposals to guide the search for objects, thereby avoiding exhaustive sliding window search across images.
Taking a Deeper Look at Pedestrians
In this paper we study the use of convolutional neural networks (convnets) for the task of pedestrian detection.
Ranked #31 on
Pedestrian Detection
on Caltech
Filtered Channel Features for Pedestrian Detection
This paper starts from the observation that multiple top performing pedestrian detectors can be modelled by using an intermediate layer filtering low-level features in combination with a boosted decision forest.
Ranked #29 on
Pedestrian Detection
on Caltech
Ten Years of Pedestrian Detection, What Have We Learned?
Paper-by-paper results make it easy to miss the forest for the trees. We analyse the remarkable progress of the last decade by discussing the main ideas explored in the 40+ detectors currently present in the Caltech pedestrian detection benchmark.
How good are detection proposals, really?
Current top performing Pascal VOC object detectors employ detection proposals to guide the search for objects thereby avoiding exhaustive sliding window search across images.
Seeking the Strongest Rigid Detector
The current state of the art solutions for object detection describe each class by a set of models trained on discovered sub-classes (so called "components"), with each model itself composed of collections of interrelated parts (deformable models).
