General body movements: cartwheel, clap hands, climb, climb stairs, dive, fall on the floor, backhand flip, handstand, jump, pull up, push up, run, sit down, sit up, somersault, stand up, turn, walk, wave.Facial actions with object manipulation: smoke, eat, drink.General facial actions smile, laugh, chew, talk.The actions categories can be grouped in five types: The dataset contains 6849 clips divided into 51 action categories, each containing a minimum of 101 clips. Here we introduce HMDB collected from various sources, mostly from movies, and a small proportion from public databases such as the Prelinger archive, YouTube and Google videos.
While much effort has been devoted to the collection and annotation of large scalable static image datasets containing thousands of image categories, human action datasets lack far behind. With nearly one billion online videos viewed everyday, an emerging new frontier in computer vision research is recognition and search in video.
0 kommentar(er)
