Weakly Supervised Training of Universal Visual Concepts for Multi-domain Semantic Segmentation

Outlier detection by ensembling uncertainty with negative objectness

Quantile-Based Maximum Likelihood Training for Outlier Detection

Hybrid Open-set Segmentation with Synthetic Negative Data

MC-PanDA: Mask Confidence for Panoptic Domain Adaptation

Hybrid Open-Set Segmentation With Synthetic Negative Data

Identifying Label Errors in Object Detection Datasets by Loss Inspection

Backdoor Defense through Self-Supervised and Generative Learning

Dense Out-of-Distribution Detection by Robust Learning on Synthetic Negative Data

Dynamic Loss Balancing and Sequential Enhancement for Road-Safety Assessment and Traffic Scene Classification

Revisiting Consistency for Semi-Supervised Semantic Segmentation

On Advantages of Mask-level Recognition for Outlier-aware Segmentation

Normalizing Flow based Feature Synthesis for Outlier-Aware Object Detection

Panoptic SwiftNet: Pyramidal Fusion for Real-Time Panoptic Segmentation

DenseHybrid: Hybrid Anomaly Detection for Dense Open-Set Recognition

Dense Semantic Forecasting with Multi-Level Feature Warping

The chirality of the mitotic spindle provides a mechanical response to forces and depends on microtubule motors and augmin

Dense open-set recognition based on training with noisy negative images

Multi-domain semantic segmentation with overlapping labels

Joint Forecasting of Features and Feature Motion for Semantic Future Prediction in Video

Automatic universal taxonomies for multi-domain semantic segmentation

Applications of generative approaches for artificial intelligence

Elements of Learning Algorithms for Natural Scene Understanding

Densely connected normalizing flows

A baseline for semi-supervised learning of efficient semantic segmentation models

Dense open-set recognition with synthetic outliers generated by Real NVP

Dense Semantic Forecasting in Video by Joint Regression of Features and Feature Motion

Convolutional architecture for efficient semantic segmentation of large images

Efficient semantic segmentation with pyramidal fusion

Efficient semantic image segmentation using pyramidal fusion

Center of Excellence for Computer Vision

Multi-domain semantic segmentation with pyramidal fusion

Multimodal semantic forecasting based on conditional generation of future features

Warp to the Future: Joint Forecasting of Features and Feature Motion

Dense out-of-distribution detection by using generative models

Efficient Ladder-Style DenseNets for Semantic Segmentation of Large Images

Traffic Scene Classification on a Representation Budget

Multi-Task Learning for iRAP Attribute Classification and Road Safety Assessment

Perceptual Autoencoder for Compressive Sensing Image Reconstruction

In Defense of Pre-Trained ImageNet Architectures for Real-Time Semantic Segmentation of Road-Driving Images

Improving fleet management systems by computer vision

Single Level Feature-to-Feature Forecasting with Deformable Convolutions

Convolutional models for image understanding

Pedestrian Tracking by Probabilistic Data Association and Correspondence Embeddings

Lightweight convolutional models for real-time dense prediction and forecasting

Simultaneous Semantic Segmentation and Outlier Detection in Presence of Domain Shift

Convolutional Models for Segmentation and Localization

Sparse weakly supervised models for object localization in road environment

Natural image understanding: principles, challenges and research outlook

Bottom-up object localization with Fisher vectors

Ladder-style DenseNets for Semantic Segmentation of Large Natural Images

Convolutional Scale Invariance for Semantic Segmentation

Python for the curious

Weakly-Supervised Semantic Segmentation by Redistributing Region Scores Back to the Pixels

Patch-level Spatial Layout for Classification and Weakly Supervised Localization

Robust Traffic Scene Recognition with a Limited Descriptor Length

Improving the Egomotion Estimation by Correcting the Calibration Bias

Weakly Supervised Object Localization with Large Fisher Vectors

Weakly Supervised Object Localization, Fisher Vectors, Sparse Classification Models.

Fast Approximate GMM Soft-Assign for Fine-Grained Image Classification with Large Fisher Vectors

Recognizing 3D Objects from a Limited Number of Views using Temporal Ensembles of Shape Functions

Experimental Evaluation of Vehicle Detection Based on Background Modelling in Daytime and Night-Time Video

Multi-Label Classification of Traffic Scenes

Convolutional Neural Networks for Croatian Traffic Signs Recognition

Image Representations on a Budget: Traffic Scene Classification in a Restricted Bandwidth Scenario

Detecting the vehicle presence by an embedded computer

Exploiting temporal and spatial constraints in traffic sign detection from a moving vehicle

Temporal Ensemble of Shape Functions

Estimation of scene structure and camera movement with calibrated stereo camera system

A Novel Georeferenced Dataset for Stereo Visual Odometry

Multiclass Road Sign Detection using Multiplicative Kernel

Classifying Traffic Scenes Using The GIST Image Descriptor

Combining Spatio-Temporal Appearance Descriptors and Optical Flow for Human Action Recognition in Video Data

Sliding Window Object Detection without Spatial Clustering of Raw Detection Responses

Towards Space-Time Semantics in Two Frames

Estimating OD matrices at intersections in airborne video - a pilot study

Optical character recognition on traffic signs

Addressing false alarms and localization inaccuracy in traffic sign detection and recognition

Histogram-Based Description of Local Space-Time Appearance

Experimental Evaluation of Autonomous Driving Based on Visual Memory and Image Based Visual Servoing

Detecting and recognizing centerlines as parabolic sections of the steerable filter response

Preliminary experiments in multi-view video stitching

Using GPS positioning to recover a comprehensive road appearance mosaic

Recent advances in traffic sign detection

Streamlining collection of training samples for object detection and classification in video

Recovering a comprehensive road appearance mosaic from video

Generative modeling of spatio-temporal traffic sign trajectories

A computer vision assisted geoinformation inventory for traffic infrastructure

Traffic sign detection as a component of an automated traffic infrastructure inventory system

Towards automatic assessment and mapping of traffic infrastructure by adding vision capabilities to a geoinformation inventory

A mapping and localization framework for scalable appearance-based navigation

Online/Realtime Structure and Motion for General Camera Models

Large scale vision based navigation without an accurate global reconstruction

A Framework for Scalable Vision-Only Navigation

Outdoor Visual Path Following Experiments

Performance evaluation of the five-point relative pose with emphasis on planar scenes

Experimental evaluation of an urban visual path following framework

Influence of the numerical conditioning to the accuracy of relative orientation

Enhancing the Point Feature Tracker by Adaptive Modelling of the Feature Support

A Multimodal Image Registration Technique for Structured Polygonal Scenes

Real-time Active Visual Tracking System

Multi-agent Object Tracking by Active Vision

A Software Architecture for Distributed Visual Tracking in a Global Vision Localization System

Detecting Salient Curvature Features Using the Local Control of the Feature Support

Determining the absolute orientation in a corridor using projective geometry and active vision

Extracting the Canonical Set of Closed Contours Using the Best-First Search Algorithm

Locally adaptive thresholding of the sequence of image frames

Using Projective Geometry and Active Vision for Scene Interpretation

A Software Architecture for Image Acquisition and Camera Control in an Active Vision System

Real Time Segmentation by Using Locally Adaptive Dynamic thresholding

Self-localisation procedure for autonomous navigation through corridors

Using vanishing points for purposive adjustment of viewing direction

Robust Extraction of Line Segments from Colour Images by an Iterative Weighted Polarised Hough Transform