Translating video demonstrations into executable robot commands remains challenging because existing methods often fail to identify which objects are functionally involved in the demonstrated action. As a result, they may generate commands that are linguistically plausible but operationally ambiguous. We propose an object-centric video understanding framework that decouples action recognition from object identification to generate precise, grammar-free manipulation commands. Our approach integrates Temporal Shift Modules (TSM) for efficient spatio-temporal action classification with a novel \textbf{Object Selection} algorithm that identifies task-relevant objects through trajectory-based role classification, blur detection, and overlap minimization. The selected objects are then processed by Vision-Language Models (VLMs) for robust category recognition and zero-shot generalization. Evaluated on a modified Something-Something V2 dataset, our method achieves 86.79\% action classification accuracy and BLEU-4 scores of 0.337 on standard objects and 0.261 on novel objects. These results improve over the strongest task-specific baseline by 80.2\% and 143.9\%, respectively. Larger gains are observed in METEOR and CIDEr, reaching 157.9\% and 171.7\% on novel objects. Across all semantic metrics, our approach consistently outperforms task-specific methods and remains competitive with, or surpasses, large general-purpose VLMs while retaining a modular, object-centric design.

翻译：将视频演示转化为可执行机器人指令仍具挑战性，现有方法常无法识别演示动作中实际参与的功能性对象，进而生成语言上合理但操作模糊的指令。我们提出以对象为中心的视频理解框架，通过解耦动作识别与对象识别，生成精确且无语法依赖的操作指令。该方法集成时序移位模块实现高效时空动作分类，并创新提出**对象选择**算法，基于轨迹角色分类、模糊检测与重叠最小化识别任务相关对象。选定对象随后由视觉语言模型处理，实现鲁棒类别识别与零样本泛化。在改进版Something-Something V2数据集上评估，本方法动作分类准确率达86.79%，标准对象与新型对象的BLEU-4得分分别为0.337与0.261，较最强任务专用基线分别提升80.2%与143.9%。METEOR与CIDEr指标提升更为显著，在新型对象上分别达157.9%与171.7%。所有语义指标均持续优于任务专用方法，与大型通用视觉语言模型持平甚至超越，同时保持模块化以对象为中心的设计特性。