Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2603.17455 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917351391232000 |
|---|---|
| author | Chen, Weidong Ye, Cheng Mao, Zhendong Song, Peipei Liu, Xinyan Zhang, Lei Chang, Xiaojun Zhang, Yongdong |
| author_facet | Chen, Weidong Ye, Cheng Mao, Zhendong Song, Peipei Liu, Xinyan Zhang, Lei Chang, Xiaojun Zhang, Yongdong |
| contents | Emotional Video Captioning (EVC) is an emerging task, which aims to describe factual content with the intrinsic emotions expressed in videos. Existing works perceive global emotional cues and then combine with video content to generate descriptions. However, insufficient factual and emotional cues mining and coordination during generation make their methods difficult to deal with the factual-emotional bias, which refers to the factual and emotional requirements being different in different samples on generation. To this end, we propose a retrieval-enhanced framework with FActual Calibration and Emotion augmentation (FACE-net), which through a unified architecture collaboratively mines factual-emotional semantics and provides adaptive and accurate guidance for generation, breaking through the compromising tendency of factual-emotional descriptions in all sample learning. Technically, we firstly introduces an external repository and retrieves the most relevant sentences with the video content to augment the semantic information. Subsequently, our factual calibration via uncertainty estimation module splits the retrieved information into subject-predicate-object triplets, and self-refines and cross-refines different components through video content to effectively mine the factual semantics; while our progressive visual emotion augmentation module leverages the calibrated factual semantics as experts, interacts with the video content and emotion dictionary to generate visual queries and candidate emotions, and then aggregates them to adaptively augment emotions to each factual semantics. Moreover, to alleviate the factual-emotional bias, we design a dynamic bias adjustment routing module to predict and adjust the degree of bias of a sample. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_17455 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | FACE-net: Factual Calibration and Emotion Augmentation for Retrieval-enhanced Emotional Video Captioning Chen, Weidong Ye, Cheng Mao, Zhendong Song, Peipei Liu, Xinyan Zhang, Lei Chang, Xiaojun Zhang, Yongdong Computer Vision and Pattern Recognition Emotional Video Captioning (EVC) is an emerging task, which aims to describe factual content with the intrinsic emotions expressed in videos. Existing works perceive global emotional cues and then combine with video content to generate descriptions. However, insufficient factual and emotional cues mining and coordination during generation make their methods difficult to deal with the factual-emotional bias, which refers to the factual and emotional requirements being different in different samples on generation. To this end, we propose a retrieval-enhanced framework with FActual Calibration and Emotion augmentation (FACE-net), which through a unified architecture collaboratively mines factual-emotional semantics and provides adaptive and accurate guidance for generation, breaking through the compromising tendency of factual-emotional descriptions in all sample learning. Technically, we firstly introduces an external repository and retrieves the most relevant sentences with the video content to augment the semantic information. Subsequently, our factual calibration via uncertainty estimation module splits the retrieved information into subject-predicate-object triplets, and self-refines and cross-refines different components through video content to effectively mine the factual semantics; while our progressive visual emotion augmentation module leverages the calibrated factual semantics as experts, interacts with the video content and emotion dictionary to generate visual queries and candidate emotions, and then aggregates them to adaptively augment emotions to each factual semantics. Moreover, to alleviate the factual-emotional bias, we design a dynamic bias adjustment routing module to predict and adjust the degree of bias of a sample. |
| title | FACE-net: Factual Calibration and Emotion Augmentation for Retrieval-enhanced Emotional Video Captioning |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.17455 |