Research map / Video / Action recognition
Exploiting Feature and Class Relationships in Video Categorization with Regularized Deep Neural Networks
Yu–Gang Jiang, Zuxuan Wu, Jun Wang, Xiangyang Xue, Shih‐Fu Chang
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 fusion-layer feature-relationship regularization (ablation) | DNN · FCVID | mAP: 72.1% -> 75.4% | Improved |
| add fusion-layer feature-relationship regularization (ablation) | DNN · Hollywood2 | mAP: 64.2% -> 65.9% | Improved |
| add class-relationship regularization on output layer (ablation) | DNN · FCVID | mAP: 72.1% -> 74.4% | Improved |
| add class-relationship regularization on output layer (ablation) | DNN · Hollywood2 | mAP: 64.2% -> 65.1% | Improved |
| add both regularizations (full rDNN) over rDNN-F (ablation) | rDNN-F · FCVID | mAP: 75.4% -> 76.0% | Improved |
| add both regularizations (full rDNN) over rDNN-C (ablation) | rDNN-C · Hollywood2 | mAP: 65.1% -> 66.9% | Improved |
| learn class relationship matrix V instead of fixing V to identity (ablation) | rDNN-C · Hollywood2, CCV, FCVID | mAP: drops 1.6, 0.8 and 3.0 percent | Improved |
| initialize V with prior class knowledge (ablation) | rDNN-C · FCVID | mAP: 74.4% -> 75.0% | No clear effect |
| deepen plain DNN to six layers (ablation) | DNN · FCVID | mAP: 72.1% -> 67.3% | Hurt |
| deepen plain DNN to eight layers (ablation) | DNN · Hollywood2 | mAP: 64.2% -> 56.2% | Hurt |
| use rDNN-C instead of DMF post-hoc class refinement (ablation) | DNN · Hollywood2 | mAP: 61.8% -> 65.1% | Improved |
| use rDNN-F instead of SVM early fusion (ablation) | SVM-EF · Hollywood2 | mAP: 64.1% -> 65.9% | Improved |
Closest papers by meaning
- Harnessing Object and Scene Semantics for Large-Scale Video Understanding (CVPR 2016 · similarity 0.87)
- VideoDG: Generalizing Temporal Relations in Videos to Novel Domains (TPAMI 2021 · similarity 0.87)
- ECO: Efficient Convolutional Network for Online Video Understanding (ECCV 2018 · similarity 0.85)
- Sympathy for the Details: Dense Trajectories and Hybrid Classification Architectures for Action Recognition (ECCV 2016 · similarity 0.85)
- Semantic Adversarial Network with Multi-Scale Pyramid Attention for Video Classification (AAAI 2019 · similarity 0.84)
- Discriminative Video Representation Learning Using Support Vector Classifiers (TPAMI 2019 · similarity 0.84)
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.
