D-ro Marc A. Kastner

Pri mi

Novaĵoj

2024

2024-10-24

My paper "Investigating conceptual blending of a diffusion model for improving nonword-to-image generation" got nominated as a Best Paper Candidate at ACM Multimedia 2024.

2024-04-01

I moved to the Sound Design & Vision Interface Group at Hiroshima City University as an Assistant Professor.

2024-01-22

2023

2023-12-31

Our workshop "3rd International Workshop on Multimodal Human Understanding for the Web and Social Media (MUWS)" got accepted for co-location at the 14th ACM International Conference on Multimedia Retrieval (ICMR) 2024.

2023-11-08
2023-08-09

My paper "Nonword-to-Image Generation Considering Perceptual Association of Phonetically Similar Words" got accepted for presentation at the ACM Multimedia 2023 Workshop on Multimedia Content Generation and Evaluation (McGE).

2023-07-28

We received a MIRU 2023 Interactive Session Award (Poster Award) for "類音語の連想性を考慮した未知語の発音に対する画像生成" (Japanese-only).

2023-07-17

Our workshop "2nd International Workshop on Multimodal Human Understanding for the Web and Social Media (MUWS)" got accepted for co-location at the 32nd ACM International Conference on Information and Knowledge Management (CIKM) 2023.

2023-04-24

My paper "Computational Measurement of Perceived Pointiness from Pronunciation" got accepted for publication in the Springer journal Multimedia Tools and Applications (MTAP).

2023-04-03

[Call for papers] Our ACM MM 2023 workshop on "User-Centric Narrative Summarization of Long Videos (NarSUM)" is looking forward to your submissions!

2023-03-06

An arXiv preprint for my in-progress work on "IPA-CLIP: Integrating Phonetic Priors into Vision and Language Pretraining" has been made available.

2022

2022-11-29

[Call for papers] Our ICME 2023 Special Session on "Quality Enhancement and Assessment for Low-quality Multimedia Data Understanding" got accepted. We are looking forward to your submissions!

2022-10-25

My paper "Towards captioning an image collection from a combined scene graph representation approach" got accepted for the 29th Intl. Conf. on MultiMedia Modeling (MMM2023).

2022-10-15

My paper "Detection of birds in a 3D environment referring to audio-visual information" got accepted for the 18th IEEE Intl. Conf. on Advanced Video and Signal-based Surveillance (AVSS2022).

2022-05-11

My paper "Action Semantic Alignment for Image Captioning" got accepted for IEEE Int. Conf. on Multimedia Information Processing and Retrieval (MIPR) 2022.

2022-04-01

I joined the Computer Vision Laboratory at Kyoto University as an Assistant Professor.

2021

2021-12-02

Our workshop "1st International Workshop on Multimodal Understanding for the Web and Social Media (MUWS)" got accepted for co-location at The WebConf (ACM WWW) 2022.

2021-11-23

My paper "Imageability- and length-controllable image captioning" got accepted at the journal IEEE Access.

2021-10-09

My short paper "Pose-aware Outfit Transfer between Unpaired in-the-wild Fashion Images" got accepted for ACM MMAsia 2021.

2021-09-21

I have added comment boxes below each publication and research project. You are invited to put comments, ideas, and question about my research.

2021-03-21

My paper "A multi-modal dataset for analyzing the imageability of concepts across modalities" got accepted for IEEE Int. Conf. on Multimedia Information Processing and Retrieval (MIPR) 2021.

2021-03-02

My extended abstract "Pointedness of an image: Measuring how pointy an image is perceived" got accepted for HCI International (HCII) 2021.

2020

2020-10-15

My paper "Tell as You Imagine: Sentence Imageability-aware Image Captioning" got accepted for MultiMedia Modelling (MMM) 2021.

2020-10-12

My paper "FashionGraph: Understanding Fashion Data Using Scene Graph Generation" got accepted for 25th International Conference on Pattern Recognition (ICPR) 2020.

2020-04-01

I joined Shin'ichi Satoh Laboratory at NII, Japan as a postdoctoral researcher.

2020-03-25

I successfully finished my Ph.D. at Nagoya University, Japan.

2020-03-09

My paper "Imageability estimation using visual and language features" got accepted for a short paper and poster presentation at ACM International Conference on Multimedia Retrieval (ICMR) 2020.

2020-02-29
© 2013-2023 Marc A. Kastner. Powered by KirbyCMS. Some rights reserved. Privacy policy.