Research map / Video / Video-language understanding
Video Captioning with Listwise Supervision
Yuan Liu, Xue Li, Zhongchao Shi
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 listwise supervision from sentence ranking lists, vs pairwise regularizer (LSTM-E) | LSTM-LS (VGG+C3D) · MSVD | BLEU@4: 45.3 -> 51.1 | Improved |
| concatenate VGG and C3D features instead of C3D alone (ablation) | LSTM-LS · MSVD | METEOR: 31.4 -> 32.6 | Improved |
| use C3D instead of VGG features (ablation) | LSTM-LS · MSVD | METEOR: 31.2 -> 31.4 | Improved |
| increase number of nearest sentences K from 2 to 4 (ablation) | LSTM-LS · MSVD | BLEU@4: 49.7 -> 51.1 | Improved |
| increase number of nearest sentences K from 4 to 5 (ablation) | LSTM-LS · MSVD | BLEU@4: 51.1 -> 49.8 | Hurt |
| increase LSTM hidden size from 128 to 1024 (ablation) | LSTM-LS · MSVD | BLEU@4: 45.4 -> 51.1 | Improved |
| use LSTM-LS instead of S2VT/LSTM-E on movie descriptions | LSTM-LS (VGG+C3D) · M-VAD | METEOR: 6.7 -> 6.9 | Improved |
Closest papers by meaning
- Fully Convolutional Video Captioning with Coarse-to-Fine and Inherited Attention (AAAI 2019 · similarity 0.88)
- Video Captioning With Transferred Semantic Attributes (CVPR 2017 · similarity 0.87)
- Distilling Vision-Language Models on Millions of Videos (CVPR 2024 · similarity 0.86)
- Panda-70M: Captioning 70M Videos with Multiple Cross-Modality Teachers (CVPR 2024 · similarity 0.85)
- Set Prediction Guided by Semantic Concepts for Diverse Video Captioning (AAAI 2024 · similarity 0.85)
- HiCM²: Hierarchical Compact Memory Modeling for Dense Video Captioning (AAAI 2025 · similarity 0.85)
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.
