Face-Guided Sentiment Boundary Enhancement for Weakly-Supervised Temporal Sentiment Localization
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866918389983739904 |
|---|---|
| author | Han, Cailing Li, Zhangbin Zhou, Jinxing Qian, Wei Hu, Jingjing Zhou, Yanghao Duan, Zhangling Guo, Dan |
| author_facet | Han, Cailing Li, Zhangbin Zhou, Jinxing Qian, Wei Hu, Jingjing Zhou, Yanghao Duan, Zhangling Guo, Dan |
| contents | Point-level weakly-supervised temporal sentiment localization (P-WTSL) aims to detect sentiment-relevant segments in untrimmed multimodal videos using timestamp sentiment annotations, which greatly reduces the costly frame-level labeling. To further tackle the challenges of imprecise sentiment boundaries in P-WTSL, we propose the Face-guided Sentiment Boundary Enhancement Network (\textbf{FSENet}), a unified framework that leverages fine-grained facial features to guide sentiment localization. Specifically, our approach \textit{first} introduces the Face-guided Sentiment Discovery (FSD) module, which integrates facial features into multimodal interaction via dual-branch modeling for effective sentiment stimuli clues; We \textit{then} propose the Point-aware Sentiment Semantics Contrast (PSSC) strategy to discriminate sentiment semantics of candidate points (frame-level) near annotation points via contrastive learning, thereby enhancing the model's ability to recognize sentiment boundaries. At \textit{last}, we design the Boundary-aware Sentiment Pseudo-label Generation (BSPG) approach to convert sparse point annotations into temporally smooth supervisory pseudo-labels. Extensive experiments and visualizations on the benchmark demonstrate the effectiveness of our framework, achieving state-of-the-art performance under full supervision, video-level, and point-level weak supervision, thereby showcasing the strong generalization ability of our FSENet across different annotation settings. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_14750 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Face-Guided Sentiment Boundary Enhancement for Weakly-Supervised Temporal Sentiment Localization Han, Cailing Li, Zhangbin Zhou, Jinxing Qian, Wei Hu, Jingjing Zhou, Yanghao Duan, Zhangling Guo, Dan Computer Vision and Pattern Recognition Point-level weakly-supervised temporal sentiment localization (P-WTSL) aims to detect sentiment-relevant segments in untrimmed multimodal videos using timestamp sentiment annotations, which greatly reduces the costly frame-level labeling. To further tackle the challenges of imprecise sentiment boundaries in P-WTSL, we propose the Face-guided Sentiment Boundary Enhancement Network (\textbf{FSENet}), a unified framework that leverages fine-grained facial features to guide sentiment localization. Specifically, our approach \textit{first} introduces the Face-guided Sentiment Discovery (FSD) module, which integrates facial features into multimodal interaction via dual-branch modeling for effective sentiment stimuli clues; We \textit{then} propose the Point-aware Sentiment Semantics Contrast (PSSC) strategy to discriminate sentiment semantics of candidate points (frame-level) near annotation points via contrastive learning, thereby enhancing the model's ability to recognize sentiment boundaries. At \textit{last}, we design the Boundary-aware Sentiment Pseudo-label Generation (BSPG) approach to convert sparse point annotations into temporally smooth supervisory pseudo-labels. Extensive experiments and visualizations on the benchmark demonstrate the effectiveness of our framework, achieving state-of-the-art performance under full supervision, video-level, and point-level weak supervision, thereby showcasing the strong generalization ability of our FSENet across different annotation settings. |
| title | Face-Guided Sentiment Boundary Enhancement for Weakly-Supervised Temporal Sentiment Localization |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.14750 |