Papers with Code · CC BY-SA 4.0

데이터셋 탐색

데이터셋의 설명·홈페이지를 찾고, 관련 태스크의 평가 기록을 살펴보세요.

관련 논문 15편

Countix

Countix 설명 보기

Countix is a real world dataset of repetition videos collected in the wild (i.e.YouTube) covering a wide range of semantic settings with significant challenges such as camera and object motion, diverse set of periods and counts, and changes in the speed of repeated actions. Countix include repeated videos of workout activities (squats, pull ups, battle rope training, exercising arm), dance moves (pirouetting, pumping fist), playing instruments (playing ukulele), using tools repeatedly (hammer hitting objects, chainsaw cutting wood, slicing onion), artistic performances (hula hooping, juggling soccer ball), sports (playing ping pong and tennis) and many others. Figure 6 illustrates some examples from the dataset as well as the distribution of repetition counts and period lengths. Source: Counting Out Time: Class Agnostic Video Repetition Counting in the Wild

관련 논문 3편

Countix-AV

Countix-AV 설명 보기

Countix-AV is a dataset for repetitive action counting by sight and sound created by repurposing the Countix dataset. It is created by selecting 19 categories from Countix for which the repetitive action has a clear sound, such as clapping, playing tennis, etc. The dataset contains 1,863 videos, with 987, 311 and 565 for training, validation and testing. The authors maintained the original count annotations from Countix and kept the same split (i.e. training, validation, or testing) for each video.

관련 논문 1편

Extreme Countix-AV

Extreme Countix-AV 설명 보기
  • 214 videos under various extreme sight conditions for audiovisual repetition counting * 7 vision challenges: camera viewpoint changes, cluttered background, low illumination, fast motion, disappearing activity, scale variation, low resolution