Matches in SemOpenAlex for { <https://semopenalex.org/work/W2890773082> ?p ?o ?g. }
- W2890773082 abstract "Action recognition has been extensively researched in computer vision due to its potential applications in a broad range of areas. The key to action recognition lies in modeling actions and measuring their similarity, which however poses great challenges. In this paper, we propose learning match kernels between actions on Grassmann manifold for action recognition. Specifically, we propose modeling actions as a linear subspace on the Grassmann manifold; the subspace is a set of convolutional neural network (CNN) feature vectors pooled temporally over frames in semantic video clips, which simultaneously captures local discriminant patterns and temporal dynamics of motion. To measure the similarity between actions, we propose Grassmann match kernels (GMK) based on canonical correlations of linear subspaces to directly match videos for action recognition; GMK is learned in a supervised way via kernel target alignment, which is endowed with a great discriminative ability to distinguish actions from different classes. The proposed approach leverages the strengths of CNNs for feature extraction and kernels for measuring similarity, which accomplishes a general learning framework of match kernels for action recognition. We have conducted extensive experiments on five challenging realistic data sets including Youtube, UCF50, UCF101, Penn action, and HMDB51. The proposed approach achieves high performance and substantially surpasses the state-of-the-art algorithms by large margins, which demonstrates the great effectiveness of proposed approach for action recognition." @default.
- W2890773082 created "2018-09-27" @default.
- W2890773082 creator A5026486701 @default.
- W2890773082 creator A5036987388 @default.
- W2890773082 creator A5051924224 @default.
- W2890773082 creator A5082634513 @default.
- W2890773082 date "2019-01-01" @default.
- W2890773082 modified "2023-10-12" @default.
- W2890773082 title "Learning Match Kernels on Grassmann Manifolds for Action Recognition" @default.
- W2890773082 cites W1522734439 @default.
- W2890773082 cites W1576762698 @default.
- W2890773082 cites W1686810756 @default.
- W2890773082 cites W1804110266 @default.
- W2890773082 cites W1884141828 @default.
- W2890773082 cites W1920196880 @default.
- W2890773082 cites W1922045146 @default.
- W2890773082 cites W1923404803 @default.
- W2890773082 cites W1926645898 @default.
- W2890773082 cites W1944448017 @default.
- W2890773082 cites W1944615693 @default.
- W2890773082 cites W1947481528 @default.
- W2890773082 cites W1974794302 @default.
- W2890773082 cites W1981781955 @default.
- W2890773082 cites W1983364832 @default.
- W2890773082 cites W1987775308 @default.
- W2890773082 cites W1991598519 @default.
- W2890773082 cites W1993229407 @default.
- W2890773082 cites W1994855553 @default.
- W2890773082 cites W1996904744 @default.
- W2890773082 cites W1999192586 @default.
- W2890773082 cites W2000590230 @default.
- W2890773082 cites W2016053056 @default.
- W2890773082 cites W2017719567 @default.
- W2890773082 cites W2035344929 @default.
- W2890773082 cites W2037513725 @default.
- W2890773082 cites W2039049096 @default.
- W2890773082 cites W2057815930 @default.
- W2890773082 cites W2063153269 @default.
- W2890773082 cites W2068611653 @default.
- W2890773082 cites W2084944189 @default.
- W2890773082 cites W2092367756 @default.
- W2890773082 cites W2100916003 @default.
- W2890773082 cites W2103096501 @default.
- W2890773082 cites W2105101328 @default.
- W2890773082 cites W2107081403 @default.
- W2890773082 cites W2110599581 @default.
- W2890773082 cites W2116435618 @default.
- W2890773082 cites W2117138194 @default.
- W2890773082 cites W2120453412 @default.
- W2890773082 cites W2122691893 @default.
- W2890773082 cites W2126017757 @default.
- W2890773082 cites W2126579184 @default.
- W2890773082 cites W2131042978 @default.
- W2890773082 cites W2137591992 @default.
- W2890773082 cites W2139893168 @default.
- W2890773082 cites W2139921999 @default.
- W2890773082 cites W2141830256 @default.
- W2890773082 cites W2149338181 @default.
- W2890773082 cites W2150600350 @default.
- W2890773082 cites W2153635508 @default.
- W2890773082 cites W2156303437 @default.
- W2890773082 cites W2161259116 @default.
- W2890773082 cites W2162931300 @default.
- W2890773082 cites W2165715280 @default.
- W2890773082 cites W2167581801 @default.
- W2890773082 cites W2176316098 @default.
- W2890773082 cites W2228536296 @default.
- W2890773082 cites W2342662179 @default.
- W2890773082 cites W2394538075 @default.
- W2890773082 cites W24089286 @default.
- W2890773082 cites W2462496837 @default.
- W2890773082 cites W2462996230 @default.
- W2890773082 cites W2465313502 @default.
- W2890773082 cites W2472293097 @default.
- W2890773082 cites W2533739470 @default.
- W2890773082 cites W2591961134 @default.
- W2890773082 cites W2597701578 @default.
- W2890773082 cites W2606294640 @default.
- W2890773082 cites W2618530766 @default.
- W2890773082 cites W2736334449 @default.
- W2890773082 cites W2795832645 @default.
- W2890773082 cites W2964191259 @default.
- W2890773082 cites W64418311 @default.
- W2890773082 doi "https://doi.org/10.1109/tip.2018.2866688" @default.
- W2890773082 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/30136940" @default.
- W2890773082 hasPublicationYear "2019" @default.
- W2890773082 type Work @default.
- W2890773082 sameAs 2890773082 @default.
- W2890773082 citedByCount "5" @default.
- W2890773082 countsByYear W28907730822020 @default.
- W2890773082 countsByYear W28907730822021 @default.
- W2890773082 crossrefType "journal-article" @default.
- W2890773082 hasAuthorship W2890773082A5026486701 @default.
- W2890773082 hasAuthorship W2890773082A5036987388 @default.
- W2890773082 hasAuthorship W2890773082A5051924224 @default.
- W2890773082 hasAuthorship W2890773082A5082634513 @default.
- W2890773082 hasConcept C103278499 @default.
- W2890773082 hasConcept C114614502 @default.
- W2890773082 hasConcept C115961682 @default.
- W2890773082 hasConcept C12362212 @default.