Dengxin Dai

is this you? claim profile

∙ 0 followers
ETH Zurich ∙ Wuhan University

Lecturer at ETH Zurich, Department of Information Technology and Electrical Engineering

ACDC: The Adverse Conditions Dataset with Correspondences for Semantic Driving Scene Understanding

Level 5 autonomy for self-driving cars requires a robust visual percepti...
04/27/2021 ∙ by Christos Sakaridis, et al. ∙ 0 ∙ share

read it
Learnable Online Graph Representations for 3D Multi-Object Tracking

Tracking of objects in 3D is a fundamental task in computer vision that ...
04/23/2021 ∙ by Jan-Nico Zaech, et al. ∙ 0 ∙ share

read it
Spectral Tensor Train Parameterization of Deep Learning Layers

We study low-rank parameterizations of weight matrices with embedded spe...
03/07/2021 ∙ by Anton Obukhov, et al. ∙ 15 ∙ share

read it
Hyperspectral Image Super-Resolution with Spectral Mixup and Heterogeneous Datasets

This work studies Hyperspectral image (HSI) super-resolution (SR). HSI S...
01/19/2021 ∙ by Ke Li, et al. ∙ 17 ∙ share

read it
Three Ways to Improve Semantic Segmentation with Self-Supervised Depth Estimation

Training deep networks for semantic segmentation requires large amounts ...
12/19/2020 ∙ by Lukas Hoyer, et al. ∙ 9 ∙ share

read it
mDALU: Multi-Source Domain Adaptation and Label Unification with Partial Datasets

Object recognition advances very rapidly these days. One challenge is to...
12/15/2020 ∙ by Rui Gong, et al. ∙ 0 ∙ share

read it
Cluster, Split, Fuse, and Update: Meta-Learning for Open Compound Domain Adaptive Semantic Segmentation

Open compound domain adaptation (OCDA) is a domain adaptation setting, w...
12/15/2020 ∙ by Rui Gong, et al. ∙ 0 ∙ share

read it
Depth Estimation from Monocular Images and Sparse Radar Data

In this paper, we explore the possibility of achieving a more accurate d...
09/30/2020 ∙ by Juan-Ting Lin, et al. ∙ 2 ∙ share

read it
Improving Point Cloud Semantic Segmentation by Learning 3D Object Proposal Generation

Point cloud semantic segmentation plays an essential role in autonomous ...
09/22/2020 ∙ by Ozan Unal, et al. ∙ 2 ∙ share

read it
Weakly Supervised 3D Object Detection from Lidar Point Cloud

It is laborious to manually label point cloud data for training high-qua...
07/23/2020 ∙ by Qinghao Meng, et al. ∙ 10 ∙ share

read it
Off-Policy Reinforcement Learning for Efficient and Effective GAN Architecture Search

In this paper, we introduce a new reinforcement learning (RL) based neur...
07/17/2020 ∙ by Yuan Tian, et al. ∙ 29 ∙ share

read it
T-Basis: a Compact Representation for Neural Networks

We introduce T-Basis, a novel concept for a compact representation of a ...
07/13/2020 ∙ by Anton Obukhov, et al. ∙ 20 ∙ share

read it
Learning Accurate and Human-Like Driving using Semantic Maps and Attention

This paper investigates how end-to-end driving models can be improved to...
07/10/2020 ∙ by Simon Hecker, et al. ∙ 0 ∙ share

read it
Analogical Image Translation for Fog Generation

Image-to-image translation is to map images from a given style to anothe...
06/28/2020 ∙ by Rui Gong, et al. ∙ 0 ∙ share

read it
Map-Guided Curriculum Domain Adaptation and Uncertainty-Aware Evaluation for Semantic Nighttime Image Segmentation

We address the problem of semantic nighttime image segmentation and impr...
05/28/2020 ∙ by Christos Sakaridis, et al. ∙ 3 ∙ share

read it
Action Sequence Predictions of Vehicles in Urban Environments using Map and Social Context

This work studies the problem of predicting the sequence of future actio...
04/29/2020 ∙ by Jan-Nico Zaech, et al. ∙ 5 ∙ share

read it
Revisiting Multi-Task Learning in the Deep Learning Era

Despite the recent progress in deep learning, most approaches still go f...
04/28/2020 ∙ by Simon Vandenhende, et al. ∙ 1 ∙ share

read it
Quantifying Data Augmentation for LiDAR based 3D Object Detection

In this work, we shed light on different data augmentation techniques co...
04/03/2020 ∙ by Martin Hahner, et al. ∙ 12 ∙ share

read it
Semantic Object Prediction and Spatial Sound Super-Resolution with Binaural Sounds

Humans can robustly recognize and localize objects by integrating visual...
03/09/2020 ∙ by Arun Balajee Vasudevan, et al. ∙ 8 ∙ share

read it
Matching Neuromorphic Events and Color Images via Adversarial Learning

The event camera has appealing properties: high dynamic range, low laten...
03/02/2020 ∙ by Fang Xu, et al. ∙ 6 ∙ share

read it
Don't Forget The Past: Recurrent Depth Estimation from Monocular Video

Autonomous cars need continuously updated depth information. Thus far, t...
01/08/2020 ∙ by Vaishakh Patil, et al. ∙ 29 ∙ share

read it
Self-supervised Object Motion and Depth Estimation from Video

We present a self-supervised learning framework to estimate the individu...
12/09/2019 ∙ by Qi Dai, et al. ∙ 14 ∙ share

read it
Semantic Understanding of Foggy Scenes with Purely Synthetic Data

This work addresses the problem of semantic scene understanding under fo...
10/09/2019 ∙ by Martin Hahner, et al. ∙ 7 ∙ share

read it
Talk2Nav: Long-Range Vision-and-Language Navigation in Cities

Autonomous driving models often consider the goal as fixed at the start ...
10/04/2019 ∙ by Arun Balajee Vasudevan, et al. ∙ 21 ∙ share

read it
Texture Underfitting for Domain Adaptation

Comprehensive semantic segmentation is one of the key components for rob...
08/29/2019 ∙ by Jan-Nico Zaech, et al. ∙ 8 ∙ share

read it
Learning a Curve Guardian for Motorcycles

Up to 17 through a curve and the main cause of curve accidents can be at...
07/12/2019 ∙ by Simon Hecker, et al. ∙ 3 ∙ share

read it
Gated CRF Loss for Weakly Supervised Semantic Image Segmentation

State-of-the-art approaches for semantic segmentation rely on deep convo...
06/11/2019 ∙ by Anton Obukhov, et al. ∙ 1 ∙ share

read it
Learning Accurate, Comfortable and Human-like Driving

Autonomous vehicles are more likely to be accepted if they drive accurat...
03/26/2019 ∙ by Simon Hecker, et al. ∙ 6 ∙ share

read it
Real-time 3D Traffic Cone Detection for Autonomous Driving

Considerable progress has been made in semantic scene understanding of r...
02/06/2019 ∙ by Ankit Dhall, et al. ∙ 10 ∙ share

read it
Semantic Nighttime Image Segmentation with Synthetic Stylized Data, Gradual Adaptation and Uncertainty-Aware Evaluation

This work addresses the problem of semantic segmentation of nighttime im...
01/17/2019 ∙ by Christos Sakaridis, et al. ∙ 6 ∙ share

read it
Curriculum Model Adaptation with Synthetic and Real Data for Semantic Foggy Scene Understanding

This work addresses the problem of semantic scene understanding under fo...
01/05/2019 ∙ by Dengxin Dai, et al. ∙ 2 ∙ share

read it
Dark Model Adaptation: Semantic Image Segmentation from Daytime to Nighttime

This work addresses the problem of semantic image segmentation of nightt...
10/05/2018 ∙ by Dengxin Dai, et al. ∙ 6 ∙ share

read it
Model Adaptation with Synthetic and Real Data for Semantic Dense Foggy Scene Understanding

This work addresses the problem of semantic scene understanding under de...
08/03/2018 ∙ by Christos Sakaridis, et al. ∙ 2 ∙ share

read it
Unified Hypersphere Embedding for Speaker Recognition

Incremental improvements in accuracy of Convolutional Neural Networks ar...
07/22/2018 ∙ by Mahdi Hajibabaei, et al. ∙ 0 ∙ share

read it
Failure Prediction for Autonomous Driving

The primary focus of autonomous driving research is to improve driving a...
05/04/2018 ∙ by Simon Hecker, et al. ∙ 0 ∙ share

read it
Ensemble Manifold Segmentation for Model Distillation and Semi-supervised Learning

Manifold theory has been the central concept of many learning methods. H...
04/06/2018 ∙ by Dengxin Dai, et al. ∙ 0 ∙ share

read it
Learning Driving Models with a Surround-View Camera System and a Route Planner

For people, having a rear-view mirror and side-view mirrors is vital for...
03/27/2018 ∙ by Simon Hecker, et al. ∙ 0 ∙ share

read it
Domain Adaptive Faster R-CNN for Object Detection in the Wild

Object detection typically assumes that training and test data are drawn...
03/08/2018 ∙ by Yuhua Chen, et al. ∙ 0 ∙ share

read it
Learning the Synthesizability of Dynamic Texture Samples

A dynamic texture (DT) refers to a sequence of images that exhibit tempo...
02/03/2018 ∙ by Feng Yang, et al. ∙ 0 ∙ share

read it
Object Referring in Videos with Language and Human Gaze

We investigate the problem of object referring (OR) i.e. to localize a t...
01/04/2018 ∙ by Arun Balajee Vasudevan, et al. ∙ 0 ∙ share

read it
Object Referring in Visual Scene with Spoken Language

Object referring has important applications, especially for human-machin...
11/10/2017 ∙ by Arun Balajee Vasudevan, et al. ∙ 0 ∙ share

read it
Semantic Foggy Scene Understanding with Synthetic Data

This work addresses the problem of semantic foggy scene understanding (S...
08/25/2017 ∙ by Christos Sakaridis, et al. ∙ 0 ∙ share

read it
Deep Domain Adaptation by Geodesic Distance Minimization

In this paper, we propose a new approach called Deep LogCORAL for unsupe...
07/13/2017 ∙ by Yifei Wang, et al. ∙ 0 ∙ share

read it
Speech-Based Visual Question Answering

This paper introduces speech-based visual question answering (VQA), the ...
05/01/2017 ∙ by Ted Zhang, et al. ∙ 0 ∙ share

read it
PathTrack: Fast Trajectory Annotation with Path Supervision

Progress in Multiple Object Tracking (MOT) has been historically limited...
03/07/2017 ∙ by Santiago Manen, et al. ∙ 0 ∙ share

read it
Fast Optical Flow using Dense Inverse Search

Most recent works in optical flow extraction focus on the accuracy and n...
03/11/2016 ∙ by Till Kroeger, et al. ∙ 0 ∙ share

read it
Unsupervised High-level Feature Learning by Ensemble Projection for Semi-supervised Image Classification and Image Clustering

This paper investigates the problem of image classification with limited...
02/02/2016 ∙ by Dengxin Dai, et al. ∙ 0 ∙ share

read it

Dengxin Dai

Featured Co-authors