Research map / Vision-language and multimodal / Cross-modal learning
SPP-SCL: Semi-Push-Pull Supervised Contrastive Learning for Image-Text Sentiment Analysis and Beyond
Jiesheng Wu, Shengrong Li
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add inter-modal second step (two-step instead of one-step) (ablation) | SPP-SCL · MVSA-S | ACC: 0.7956 -> 0.8133 | Improved |
| add inter-modal second step (two-step instead of one-step) (ablation) | SPP-SCL · MVSA-M | ACC: 0.7276 -> 0.7871 | Improved |
| add inter-modal second step (two-step instead of one-step) (ablation) | SPP-SCL · HFM | ACC: 0.8800 -> 0.9469 | Improved |
| add inter-modal loss L_clm (ablation) | SPP-SCL · HFM | F1: 0.7753 -> 0.9450 | Improved |
| add inter-modal loss L_clm (ablation) | SPP-SCL · MVSA-S | ACC: 0.7289 -> 0.8133 | Improved |
| add inter-modal loss L_clm (ablation) | SPP-SCL · MVSA-M | ACC: 0.7688 -> 0.7871 | Improved |
| add intra-modal losses L_cli and L_clt (ablation) | SPP-SCL · MVSA-S | ACC: 0.7244 -> 0.8133 | Improved |
| add intra-modal losses L_cli and L_clt (ablation) | SPP-SCL · MVSA-M | ACC: 0.7459 -> 0.7871 | Improved |
| add intra-modal losses L_cli and L_clt (ablation) | SPP-SCL · HFM | F1: 0.9409 -> 0.9450 | No clear effect |
| add CMF cross-modal fusion module (ablation) | SPP-SCL · MVSA-S | ACC: 0.7289 -> 0.8133 | Improved |
| add CMF cross-modal fusion module (ablation) | SPP-SCL · MVSA-M | ACC: 0.7453 -> 0.7871 | Improved |
| add CMF cross-modal fusion module (ablation) | SPP-SCL · HFM | ACC: 0.8117 -> 0.9469 | Improved |
Closest papers by meaning
- Seek Common Ground While Reserving Differences: Semi-Supervised Image-Text Sentiment Recognition (CVPR 2025 · similarity 0.86)
- Semi-IIN: Semi-Supervised Intra-Inter Modal Interaction Learning Network for Multimodal Sentiment Analysis (AAAI 2025 · similarity 0.83)
- Debiasing Multimodal Sarcasm Detection with Contrastive Learning (AAAI 2024 · similarity 0.81)
- Semi-Supervised Multimodal Classification Through Learning from Modal and Strategic Complementarities (AAAI 2025 · similarity 0.81)
- On the Comparison between Multi-modal and Single-modal Contrastive Learning (NeurIPS 2024 · similarity 0.81)
- G^2SAM: Graph-Based Global Semantic Awareness Method for Multimodal Sarcasm Detection (AAAI 2024 · similarity 0.80)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
