Research map / Video / Video generation
Attentive Semantic Video Generation Using Captions
Tanya Marwah, Gaurav Mittal, Vineeth N. Balasubramanian
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 long-term context captioning (ablation) | caption-conditioned video generator · Moving MNIST/KTH (loss column 1) | training loss: 65.76 -> 63.55 | Improved |
| add long-term context captioning (ablation) | caption-conditioned video generator · Moving MNIST/KTH (loss column 2) | training loss: 17.97 -> 11.84 | Improved |
| add long-term context captioning (ablation) | caption-conditioned video generator · Moving MNIST/KTH (loss column 3) | training loss: 83.73 -> 75.39 | Improved |
| add long-term context s_l (ablation) | caption-conditioned video generator · Moving MNIST | qualitative coherence | Improved |
| add short-term context s_s (ablation) | caption-conditioned video generator · Moving MNIST | qualitative object quality | Improved |
| use attention-based caption latent instead of one-hot vectors (ablation) | caption-conditioned video generator · Moving MNIST unseen captions | qualitative caption response | Improved |
| use attention-based caption latent instead of pre-trained skipthought vectors (ablation) | caption-conditioned video generator · Moving MNIST unseen captions | qualitative motion match | Improved |
| train and test on both real and generated KTH videos | SVM on 3D conv features · KTH action classification | accuracy (%): 70.95 | Improved |
Closest papers by meaning
- Progress-Aware Video Frame Captioning (CVPR 2025 · similarity 0.87)
- OmniViD: A Generative Framework for Universal Video Understanding (CVPR 2024 · similarity 0.87)
- Video ReCap: Recursive Captioning of Hour-Long Videos (CVPR 2024 · similarity 0.87)
- InstanceCap: Improving Text-to-Video Generation via Instance-aware Structured Caption (CVPR 2025 · similarity 0.87)
- Fine-Grained Captioning of Long Videos through Scene Graph Consolidation (ICML 2025 · similarity 0.87)
- Set Prediction Guided by Semantic Concepts for Diverse Video Captioning (AAAI 2024 · similarity 0.87)
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.
