Search Results for author: An Tran

Found 4 papers, 2 papers with code

WaveTransformer: A Novel Architecture for Audio Captioning Based on Learning Temporal and Time-Frequency Information

1 code implementation21 Oct 2020 An Tran, Konstantinos Drossos, Tuomas Virtanen

Automated audio captioning (AAC) is a novel task, where a method takes as an input an audio sample and outputs a textual description (i. e. a caption) of its contents.

Audio captioning Image Captioning +2

PP-LinkNet: Improving Semantic Segmentation of High Resolution Satellite Imagery with Multi-stage Training

no code implementations14 Oct 2020 An Tran, Ali Zonoozi, Jagannadan Varadarajan, Hannes Kruppa

In this paper, we propose a two-stage transfer learning technique to improve robustness of semantic segmentation for satellite images that leverages noisy pseudo ground truth masks obtained automatically (without human labor) from crowd-sourced OpenStreetMap (OSM) data.

Disaster Response Image Segmentation +2

Two-stream Flow-guided Convolutional Attention Networks for Action Recognition

1 code implementation30 Aug 2017 An Tran, Loong-Fah Cheong

This paper proposes a two-stream flow-guided convolutional attention networks for action recognition in videos.

Action Recognition Action Recognition In Videos +1

Actionness-Assisted Recognition of Actions

no code implementations ICCV 2015 Ye Luo, Loong-Fah Cheong, An Tran

We elicit from a fundamental definition of action low-level attributes that can reveal agency and intentionality.

Action Detection Action Recognition

Cannot find the paper you are looking for? You can Submit a new open access paper.