Sports videos pose complex challenges, including cluttered backgrounds, camera angle changes, small action-representing objects, and imbalanced action class distribution. Existing methods for detecting actions in sports videos heavily rely on global features, utilizing a backbone network as a black box that encompasses the entire spatial frame. However, these approaches tend to overlook the nuances of the scene and struggle with detecting actions that occupy a small portion of the frame. In particular, they face difficulties when dealing with action classes involving small objects, such as balls or yellow/red cards in soccer, which only occupy a fraction of the screen space. To address these challenges, we introduce a novel approach that analyzes and models scene entities using an adaptive attention mechanism. Particularly, our model disentangles the scene content into the global environment feature and local relevant scene entities feature. To efficiently extract environmental features while considering temporal information with less computational cost, we propose the use of a 2D backbone network with a time-shift mechanism. To accurately capture relevant scene entities, we employ a Vision-Language model in conjunction with the adaptive attention mechanism. Our model has demonstrated outstanding performance, securing the 1st place in the SoccerNet-v2 Action Spotting, FineDiving, and FineGym challenge with a substantial performance improvement of 1.6, 2.0, and 1.3 points in avg-mAP compared to the runner-up methods. Furthermore, our approach offers interpretability capabilities in contrast to other deep learning models, which are often designed as black boxes. Our code and models are released at: https://github.com/Fsoft-AIC/unifying-global-local-feature.
Despite the significant progress made in recent years, Multi-Object Tracking (MOT) approaches still suffer from several limitations, including their reliance on prior knowledge of tracking targets, which necessitates the costly annotation of large labeled datasets. As a result, existing MOT methods are limited to a small set of predefined categories, and they struggle with unseen objects in the real world. To address these issues, Generic Multiple Object Tracking (GMOT) has been proposed, which requires less prior information about the targets. However, all existing GMOT approaches follow a one-shot paradigm, relying mainly on the initial bounding box and thus struggling to handle variants e.g., viewpoint, lighting, occlusion, scale, and etc. In this paper, we introduce a novel approach to address the limitations of existing MOT and GMOT methods. Specifically, we propose a zero-shot GMOT (Z-GMOT) algorithm that can track never-seen object categories with zero training examples, without the need for predefined categories or an initial bounding box. To achieve this, we propose iGLIP, an improved version of Grounded language-image pretraining (GLIP), which can detect unseen objects while minimizing false positives. We evaluate our Z-GMOT thoroughly on the GMOT-40 dataset, AnimalTrack testset, DanceTrack testset. The results of these evaluations demonstrate a significant improvement over existing methods. For instance, on the GMOT-40 dataset, the Z-GMOT outperforms one-shot GMOT with OC-SORT by 27.79 points HOTA and 44.37 points MOTA. On the AnimalTrack dataset, it surpasses fully-supervised methods with DeepSORT by 12.55 points HOTA and 8.97 points MOTA. To facilitate further research, we will make our code and models publicly available upon acceptance of this paper.