1.4k citations · 3.1k across the 72 of their papers we have counts for
5 papers · 1 filter
Object Referring in Visual Scene with Spoken Language
Arun Balajee Vasudevan, Dengxin Dai, Luc Van Gool
Object referring has important applications, especially for human-machine interaction. While having received great attention, the task is mainly attacked with written language (tex…
Semantic Foggy Scene Understanding with Synthetic Data
Christos Sakaridis, Dengxin Dai, Luc Van Gool
This work addresses the problem of semantic foggy scene understanding (SFSU). Although extensive research has been performed on image dehazing and on semantic scene understanding w…
Deep Domain Adaptation by Geodesic Distance Minimization
Yifei Wang, Wen Li, Dengxin Dai +1
In this paper, we propose a new approach called Deep LogCORAL for unsupervised visual domain adaptation. Our work builds on the recently proposed Deep CORAL method, which proposed…
Speech-Based Visual Question Answering
Ted Zhang, Dengxin Dai, Tinne Tuytelaars +2
This paper introduces speech-based visual question answering (VQA), the task of generating an answer given an image and a spoken question. Two methods are studied: an end-to-end, d…
PathTrack: Fast Trajectory Annotation with Path Supervision
Santiago Manen, Michael Gygli, Dengxin Dai +1
Progress in Multiple Object Tracking (MOT) has been historically limited by the size of the available datasets. We present an efficient framework to annotate trajectories and use i…