Abstract Automatic Visual Captioning (AVC) generates syntactically and semantically correct sentences by describing important objects, attributes, and their relationships with each other …
Combining complementary information from multiple modalities is intuitively appealing for improving the performance of learning-based approaches. However, it is challenging to fully …
A Guzhov, F Raue, J Hees… - 2020 25th international …, 2021 - ieeexplore.ieee.org
Environmental Sound Classification (ESC) is an active research area in the audio domain and has seen a lot of progress in the past years. However, many of the existing approaches …
Describing videos with natural language is one of the ultimate goals of video understanding. Video records multi-modal information including image, motion, aural, speech and so on …
Crowd estimation is a very challenging problem. The most recent study tries to exploit auditory information to aid the visual models, however, the performance is limited due to the …
The topic diversity of open-domain videos leads to various vocabularies and linguistic expressions in describing video contents, and therefore, makes the video captioning task …
This paper focuses on an important problem of detecting offensive analogy meme on online social media where the visual content and the texts/captions of the meme together make an …
D Hu, C Wang, F Nie, X Li - ICASSP 2019-2019 IEEE …, 2019 - ieeexplore.ieee.org
Multiple modalities can provide more valuable information than single one by describing the same contents in various ways. Previous methods mainly focus on fusing the shallow …
S Chen, Q Jin, J Chen… - IEEE Transactions on …, 2019 - ieeexplore.ieee.org
Automatic video description generation (aka video captioning) is one of the ultimate goals for video understanding. Despite the wide range of applications such as video indexing and …