Video Understanding by Design: How Datasets Shape Architectures and Insights
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914031928868864 |
|---|---|
| author | Wang, Lei Koniusz, Piotr Gao, Yongsheng |
| author_facet | Wang, Lei Koniusz, Piotr Gao, Yongsheng |
| contents | Video understanding has advanced rapidly, fueled by increasingly complex datasets and powerful architectures. Yet existing surveys largely classify models by task or family, overlooking the structural pressures through which datasets guide architectural evolution. This survey is the first to adopt a dataset-driven perspective, showing how motion complexity, temporal span, hierarchical composition, and multimodal richness impose inductive biases that models should encode. We reinterpret milestones, from two-stream and 3D CNNs to sequential, transformer, and multimodal foundation models, as concrete responses to these dataset-driven pressures. Building on this synthesis, we offer practical guidance for aligning model design with dataset invariances while balancing scalability and task demands. By unifying datasets, inductive biases, and architectures into a coherent framework, this survey provides both a comprehensive retrospective and a prescriptive roadmap for advancing general-purpose video understanding. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_09151 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Video Understanding by Design: How Datasets Shape Architectures and Insights Wang, Lei Koniusz, Piotr Gao, Yongsheng Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Video understanding has advanced rapidly, fueled by increasingly complex datasets and powerful architectures. Yet existing surveys largely classify models by task or family, overlooking the structural pressures through which datasets guide architectural evolution. This survey is the first to adopt a dataset-driven perspective, showing how motion complexity, temporal span, hierarchical composition, and multimodal richness impose inductive biases that models should encode. We reinterpret milestones, from two-stream and 3D CNNs to sequential, transformer, and multimodal foundation models, as concrete responses to these dataset-driven pressures. Building on this synthesis, we offer practical guidance for aligning model design with dataset invariances while balancing scalability and task demands. By unifying datasets, inductive biases, and architectures into a coherent framework, this survey provides both a comprehensive retrospective and a prescriptive roadmap for advancing general-purpose video understanding. |
| title | Video Understanding by Design: How Datasets Shape Architectures and Insights |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2509.09151 |