Research map / Video / Action recognition
A Unified Framework for Shot Type Classification Based on Subject Centric Lens
Anyi Rao, Jiaze Wang, Linning Xu, Xuekun Jiang, Qingqiu Huang, Bolei Zhou, Dahua Lin
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 subject map guidance to TSN (img) (ablation) | TSN-ResNet50 (img) · MovieShots scale type | accuracy: 84.08 -> 87.21 | Improved |
| add subject map guidance to TSN (img) (ablation) | TSN-ResNet50 (img) · MovieShots movement type | accuracy: 70.46 -> 71.30 | Improved |
| add variance map to SGNet (img) (ablation) | SGNet (img) · MovieShots movement type | accuracy: 71.30 -> 80.57 | Improved |
| add optical flow to SGNet (img) (ablation) | SGNet (img) · MovieShots movement type | accuracy: 71.30 -> 80.65 | Improved |
| add variance map and flow to SGNet (img) (ablation) | SGNet (img) · MovieShots scale type | accuracy: 87.21 -> 87.57 | No clear effect |
| add Kinetics pre-training to SGNet w/ Var (ablation) | SGNet w/ Var (img + flow) · MovieShots movement type | accuracy: 81.86 -> 83.72 | Improved |
| use whole image plus subject branch instead of subject only (ablation) | TSN w/ Var img+flow · MovieShots scale type | accuracy: 79.97 -> 87.57 | Improved |
| add background guidance instead of subject guidance for movement (ablation) | SGNet w/ Var · MovieShots movement type | accuracy: 80.86 -> 81.86 | Improved |
| add both subject and background guidance (four branches) (ablation) | SGNet w/ Var · MovieShots scale type | accuracy: 87.57 -> 87.31 | Hurt |
| replace SBS self-attention with fine-tuned R3Net-ResNet50 subject map (ablation) | TSN w/ Var img+flow · MovieShots scale type | accuracy: 83.82 -> 88.10 | Improved |
| add adversarial loss to student generator (ablation) | student generator · MovieShots scale type | accuracy: 85.34 -> 87.08 | Improved |
| add adversarial loss to student generator (ablation) | student generator · MovieShots movement type | accuracy: 79.11 -> 81.13 | Improved |
Closest papers by meaning
- Generalized Few-Shot Video Classification With Video Retrieval and Feature Generation (TPAMI 2021 · similarity 0.86)
- Shot Contrastive Self-Supervised Learning for Scene Boundary Detection (CVPR 2021 · similarity 0.85)
- Rethinking Generalization in Few-Shot Classification (NeurIPS 2022 · similarity 0.85)
- ShotBench: Expert-Level Cinematic Understanding in Vision-Language Models (NeurIPS 2025 · similarity 0.84)
- Pushing the Limit of Fine-Tuning for Few-Shot Learning: Where Feature Reusing Meets Cross-Scale Attention (AAAI 2024 · similarity 0.84)
- Neighbor Relations Matter in Video Scene Detection (CVPR 2024 · similarity 0.83)
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.
