Recognizing Complex Events in Videos by Learning Key Static-Dynamic Evidences

Abstract. Complex events consist of various human interactions with different objects in diverse environments. The evidences needed to rec-ognize events may occur in short time periods with variable lengths and can happen anywhere in a video. This fact prevents conventional machine learning algorithms from effectively recognizing the events. In this pa-per, we propose a novel method that can automatically identify the key evidences in videos for detecting complex events. Both static instances (objects) and dynamic instances (actions) are considered by sampling frames and temporal segments respectively. To compare the character-istic power of heterogeneous instances, we embed static and dynamic instances into a multiple instance learning framework via instance simi-larity measures, and cast the problem as an Evidence Selective Ranking (ESR) process. We impose 1 norm to select key evidences while us-ing the Infinite Push Loss Function to enforce positive videos to have higher detection scores than negative videos. The Alternating Direction Method of Multipliers (ADMM) algorithm is used to solve the optimiza-tion problem. Experiments on large-scale video datasets show that our method can improve the detection accuracy while providing the unique capability in discovering key evidences of each complex event