1.8k citations · 4.1k across the 34 of their papers we have counts for
18 papers · 1 filter
Learning Video Instance Segmentation with Recurrent Graph Neural Networks
Joakim Johnander, Emil Brissman, Martin Danelljan +1
Most existing approaches to video instance segmentation comprise multiple modules that are heuristically combined to produce the final output. Formulating a purely learning-based m…
Scaling Semantic Segmentation Beyond 1K Classes on a Single GPU
Shipra Jain, Danda Paudel Pani, Martin Danelljan +1
The state-of-the-art object detection and image classification methods can perform impressively on more than 9k and 10k classes, respectively. In contrast, the number of classes in…
Accurate 3D Object Detection using Energy-Based Models
Fredrik K. Gustafsson, Martin Danelljan, Thomas B. Schön
Accurate 3D object detection (3DOD) is crucial for safe navigation of complex environments by autonomous robots. Regressing accurate 3D bounding boxes in cluttered environments bas…
Fast Few-Shot Classification by Few-Iteration Meta-Learning
Ardhendu Shekhar Tripathi, Martin Danelljan, Luc Van Gool +1
Autonomous agents interacting with the real world need to learn new concepts efficiently and reliably. This requires learning in a low-data regime, which is a highly challenging pr…
AIM 2020 Challenge on Efficient Super-Resolution: Methods and Results
Kai Zhang, Martin Danelljan, Yawei Li +75
This paper reviews the AIM 2020 challenge on efficient single image super-resolution with focus on the proposed solutions and results. The challenge task was to super-resolve an in…
GOCor: Bringing Globally Optimized Correspondence Volumes into Your Neural Network
Prune Truong, Martin Danelljan, Luc Van Gool +1
The feature correlation layer serves as a key neural network module in numerous computer vision problems that involve dense correspondences between image pairs. It predicts a corre…
SRFlow: Learning the Super-Resolution Space with Normalizing Flow
Andreas Lugmayr, Martin Danelljan, Luc Van Gool +1
Super-resolution is an ill-posed problem, since it allows for multiple predictions for a given low-resolution image. This fundamental fact is largely ignored by state-of-the-art de…
DeepSVG: A Hierarchical Generative Network for Vector Graphics Animation
Alexandre Carlier, Martin Danelljan, Alexandre Alahi +1
Scalable Vector Graphics (SVG) are ubiquitous in modern 2D interfaces due to their ability to scale to different resolutions. However, despite the success of deep learning-based mo…
Video Object Segmentation with Episodic Graph Memory Networks
Xiankai Lu, Wenguan Wang, Martin Danelljan +3
How to make a segmentation model efficiently adapt to a specific video and to online target appearance variations are fundamentally crucial issues in the field of video object segm…
NTIRE 2020 Challenge on Video Quality Mapping: Methods and Results
Dario Fuoli, Zhiwu Huang, Martin Danelljan +18
This paper reviews the NTIRE 2020 challenge on video quality mapping (VQM), which addresses the issues of quality mapping from source video domain to target video domain. The chall…
The Heterogeneity Hypothesis: Finding Layer-Wise Differentiated Network Architectures
Yawei Li, Wen Li, Martin Danelljan +4
In this paper, we tackle the problem of convolutional neural network design. Instead of focusing on the design of the overall architecture, we investigate a design space that is us…
NTIRE 2020 Challenge on Real-World Image Super-Resolution: Methods and Results
Andreas Lugmayr, Martin Danelljan, Radu Timofte +43
This paper reviews the NTIRE 2020 challenge on real world super-resolution. It focuses on the participating methods and final results. The challenge addresses the real world settin…
How to Train Your Energy-Based Model for Regression
Fredrik K. Gustafsson, Martin Danelljan, Radu Timofte +1
Energy-based models (EBMs) have become increasingly popular within computer vision in recent years. While they are commonly employed for generative image modeling, recent work has…
Learning What to Learn for Video Object Segmentation
Goutam Bhat, Felix Järemo Lawin, Martin Danelljan +4
Video object segmentation (VOS) is a highly challenging problem, since the target object is only defined during inference with a given first-frame reference mask. The problem of ho…
Know Your Surroundings: Exploiting Scene Information for Object Tracking
Goutam Bhat, Martin Danelljan, Luc Van Gool +1
Current state-of-the-art trackers only rely on a target appearance model in order to localize the object in each frame. Such approaches are however prone to fail in case of e.g. fa…
Learning Human-Object Interaction Detection using Interaction Points
Tiancai Wang, Tong Yang, Martin Danelljan +3
Understanding interactions between humans and objects is one of the fundamental problems in visual classification and an essential step towards detailed scene understanding. Human-…
Learning Fast and Robust Target Models for Video Object Segmentation
Andreas Robinson, Felix Järemo Lawin, Martin Danelljan +2
Video object segmentation (VOS) is a highly challenging problem since the initial mask, defining the target object, is only given at test-time. The main difficulty is to effectivel…
Probabilistic Regression for Visual Tracking
Martin Danelljan, Luc Van Gool, Radu Timofte
Visual tracking is fundamentally the problem of regressing the state of the target in each video frame. While significant progress has been achieved, trackers are still prone to fa…