Comment-aided Video-Language Alignment via Contrastive Pre-training for Short-form Video Humor Detection
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914752664436736 |
|---|---|
| author | Liu, Yang Shen, Tongfei Zhang, Dong Sun, Qingying Li, Shoushan Zhou, Guodong |
| author_facet | Liu, Yang Shen, Tongfei Zhang, Dong Sun, Qingying Li, Shoushan Zhou, Guodong |
| contents | The growing importance of multi-modal humor detection within affective computing correlates with the expanding influence of short-form video sharing on social media platforms. In this paper, we propose a novel two-branch hierarchical model for short-form video humor detection (SVHD), named Comment-aided Video-Language Alignment (CVLA) via data-augmented multi-modal contrastive pre-training. Notably, our CVLA not only operates on raw signals across various modal channels but also yields an appropriate multi-modal representation by aligning the video and language components within a consistent semantic space. The experimental results on two humor detection datasets, including DY11k and UR-FUNNY, demonstrate that CVLA dramatically outperforms state-of-the-art and several competitive baseline approaches. Our dataset, code and model release at https://github.com/yliu-cs/CVLA. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_09055 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Comment-aided Video-Language Alignment via Contrastive Pre-training for Short-form Video Humor Detection Liu, Yang Shen, Tongfei Zhang, Dong Sun, Qingying Li, Shoushan Zhou, Guodong Computer Vision and Pattern Recognition Artificial Intelligence The growing importance of multi-modal humor detection within affective computing correlates with the expanding influence of short-form video sharing on social media platforms. In this paper, we propose a novel two-branch hierarchical model for short-form video humor detection (SVHD), named Comment-aided Video-Language Alignment (CVLA) via data-augmented multi-modal contrastive pre-training. Notably, our CVLA not only operates on raw signals across various modal channels but also yields an appropriate multi-modal representation by aligning the video and language components within a consistent semantic space. The experimental results on two humor detection datasets, including DY11k and UR-FUNNY, demonstrate that CVLA dramatically outperforms state-of-the-art and several competitive baseline approaches. Our dataset, code and model release at https://github.com/yliu-cs/CVLA. |
| title | Comment-aided Video-Language Alignment via Contrastive Pre-training for Short-form Video Humor Detection |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2402.09055 |