US 11,935,296 B2
Apparatus and method for online action detection
Jin Young Moon, Daejeon (KR); Hyung Il Kim, Daejeon (KR); Jong Youl Park, Daejeon (KR); Kang Min Bae, Daejeon (KR); and Ki Min Yun, Daejeon (KR)
Assigned to ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE, Daejeon (KR)
Filed by Electronics and Telecommunications Research Institute, Daejeon (KR)
Filed on Aug. 25, 2021, as Appl. No. 17/411,728.
Claims priority of application No. 10-2020-0106794 (KR), filed on Aug. 25, 2020.
Prior Publication US 2022/0067382 A1, Mar. 3, 2022
Int. Cl. G06V 20/40 (2022.01)
CPC G06V 20/41 (2022.01) [G06V 20/46 (2022.01); G06V 20/49 (2022.01)] 12 Claims
OG exemplary drawing
 
1. An apparatus for online action detection, the apparatus comprising:
a feature extraction unit configured to extract a chunk-level feature of a video chunk sequence of a streaming video;
a filtering unit configured to perform filtering on the chunk-level features; and
an action classification unit configured to classify an action class using the filtered chunk-level features, wherein
the filtering unit configured to receive a chunk-level feature sequence and infer a relation of an action instance represented by a current chunk and other chunks to generate a filtered chunk-level feature sequence to be used for action classification, and
the filtering unit configured to predict an action relevance of each chunk with the current point in time so as to generate filtered features in which a feature of a chunk related to the current point in time is emphasized and a feature of a chunk unrelated to the current point in time is filtered out.