Context-Aware Feature Aggregation for Robust Object Detection in Dynamic Scenes
Fuente:
Zenodo
Salvato in:
| Autore principale: | |
|---|---|
| Natura: | Recurso digital |
| Pubblicazione: |
Zenodo
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866901732422844416 |
|---|---|
| author | Jamie Chen |
| author_facet | Jamie Chen |
| contents | Object detection remains a challenging task in dynamic environments due to factors such as occlusion, illumination changes, and rapid object motion. This paper proposes a novel context-aware feature aggregation network designed to enhance the robustness of object detection models in such scenarios. Our approach leverages spatial and temporal context information to refine feature representations, thereby improving the model's ability to accurately localize and classify objects even under adverse conditions. We present experimental results on benchmark datasets demonstrating the effectiveness of our method in comparison to state-of-the-art object detection frameworks. |
| format | Recurso digital |
| id | zenodo_https___doi_org_10_5281_zenodo_18945584 |
| institution | Zenodo |
| language | |
| publishDate | 2026 |
| publisher | Zenodo |
| record_format | zenodo |
| spellingShingle | Context-Aware Feature Aggregation for Robust Object Detection in Dynamic Scenes Jamie Chen machine learning deep learning artificial intelligence Object detection remains a challenging task in dynamic environments due to factors such as occlusion, illumination changes, and rapid object motion. This paper proposes a novel context-aware feature aggregation network designed to enhance the robustness of object detection models in such scenarios. Our approach leverages spatial and temporal context information to refine feature representations, thereby improving the model's ability to accurately localize and classify objects even under adverse conditions. We present experimental results on benchmark datasets demonstrating the effectiveness of our method in comparison to state-of-the-art object detection frameworks. |
| title | Context-Aware Feature Aggregation for Robust Object Detection in Dynamic Scenes |
| topic | machine learning deep learning artificial intelligence |
| url | https://doi.org/10.5281/zenodo.18945584 |