Matches in SemOpenAlex for { <https://semopenalex.org/work/W2897426518> ?p ?o ?g. }
Showing items 1 to 90 of
90
with 100 items per page.
- W2897426518 endingPage "676" @default.
- W2897426518 startingPage "660" @default.
- W2897426518 abstract "This paper introduces a large-scale, multi-label and multi-task video dataset named Scenes-Objects-Actions (SOA). Most prior video datasets are based on a predefined taxonomy, which is used to define the keyword queries issued to search engines. The videos retrieved by the search engines are then verified for correctness by human annotators. Datasets collected in this manner tend to generate high classification accuracy as search engines typically rank “easy” videos first. The SOA dataset adopts a different approach. We rely on uniform sampling to get a better representation of videos on the Web. Trained annotators are asked to provide free-form text labels describing each video in three different aspects: scene, object and action. These raw labels are then merged, split and renamed to generate a taxonomy for SOA. All the annotations are verified again based on the taxonomy. The final dataset includes 562K videos with 3.64M annotations spanning 49 categories for scenes, 356 for objects, 148 for actions, and naturally captures the long tail distribution of visual concepts in the real world. We show that datasets collected in this way are quite challenging by evaluating existing popular video models on SOA. We provide in-depth analysis about the performance of different models on SOA, and highlight potential new directions in video classification. We compare SOA with existing datasets and discuss various factors that impact the performance of transfer learning. A key-feature of SOA is that it enables the empirical study of correlation among scene, object and action recognition in video. We present results of this study and further analyze the potential of using the information learned from one task to improve the others. We also demonstrate different ways of scaling up SOA to learn better features. We believe that the challenges presented by SOA offer the opportunity for further advancement in video analysis as we progress from single-label classification towards a more comprehensive understanding of video data." @default.
- W2897426518 created "2018-10-26" @default.
- W2897426518 creator A5016319243 @default.
- W2897426518 creator A5035182164 @default.
- W2897426518 creator A5035190506 @default.
- W2897426518 creator A5054437548 @default.
- W2897426518 creator A5055620900 @default.
- W2897426518 creator A5082736347 @default.
- W2897426518 creator A5085331622 @default.
- W2897426518 date "2018-01-01" @default.
- W2897426518 modified "2023-10-01" @default.
- W2897426518 title "Scenes-Objects-Actions: A Multi-task, Multi-label Video Dataset" @default.
- W2897426518 cites W1489737693 @default.
- W2897426518 cites W1522734439 @default.
- W2897426518 cites W1755205674 @default.
- W2897426518 cites W1923404803 @default.
- W2897426518 cites W1947481528 @default.
- W2897426518 cites W1983364832 @default.
- W2897426518 cites W2016053056 @default.
- W2897426518 cites W2020163092 @default.
- W2897426518 cites W2031342017 @default.
- W2897426518 cites W2081580037 @default.
- W2897426518 cites W2097117768 @default.
- W2897426518 cites W2101443479 @default.
- W2897426518 cites W2108598243 @default.
- W2897426518 cites W2126574503 @default.
- W2897426518 cites W2126579184 @default.
- W2897426518 cites W2194775991 @default.
- W2897426518 cites W2337252826 @default.
- W2897426518 cites W2592463526 @default.
- W2897426518 cites W2608988379 @default.
- W2897426518 cites W2625366777 @default.
- W2897426518 cites W2770804203 @default.
- W2897426518 cites W2789221157 @default.
- W2897426518 cites W2962934715 @default.
- W2897426518 cites W2963155035 @default.
- W2897426518 cites W2963524571 @default.
- W2897426518 cites W2964260135 @default.
- W2897426518 cites W4249279051 @default.
- W2897426518 doi "https://doi.org/10.1007/978-3-030-01264-9_39" @default.
- W2897426518 hasPublicationYear "2018" @default.
- W2897426518 type Work @default.
- W2897426518 sameAs 2897426518 @default.
- W2897426518 citedByCount "19" @default.
- W2897426518 countsByYear W28974265182019 @default.
- W2897426518 countsByYear W28974265182020 @default.
- W2897426518 countsByYear W28974265182021 @default.
- W2897426518 countsByYear W28974265182022 @default.
- W2897426518 countsByYear W28974265182023 @default.
- W2897426518 crossrefType "book-chapter" @default.
- W2897426518 hasAuthorship W2897426518A5016319243 @default.
- W2897426518 hasAuthorship W2897426518A5035182164 @default.
- W2897426518 hasAuthorship W2897426518A5035190506 @default.
- W2897426518 hasAuthorship W2897426518A5054437548 @default.
- W2897426518 hasAuthorship W2897426518A5055620900 @default.
- W2897426518 hasAuthorship W2897426518A5082736347 @default.
- W2897426518 hasAuthorship W2897426518A5085331622 @default.
- W2897426518 hasConcept C121684516 @default.
- W2897426518 hasConcept C154945302 @default.
- W2897426518 hasConcept C162324750 @default.
- W2897426518 hasConcept C187736073 @default.
- W2897426518 hasConcept C2780451532 @default.
- W2897426518 hasConcept C31972630 @default.
- W2897426518 hasConcept C41008148 @default.
- W2897426518 hasConceptScore W2897426518C121684516 @default.
- W2897426518 hasConceptScore W2897426518C154945302 @default.
- W2897426518 hasConceptScore W2897426518C162324750 @default.
- W2897426518 hasConceptScore W2897426518C187736073 @default.
- W2897426518 hasConceptScore W2897426518C2780451532 @default.
- W2897426518 hasConceptScore W2897426518C31972630 @default.
- W2897426518 hasConceptScore W2897426518C41008148 @default.
- W2897426518 hasLocation W28974265181 @default.
- W2897426518 hasOpenAccess W2897426518 @default.
- W2897426518 hasPrimaryLocation W28974265181 @default.
- W2897426518 hasRelatedWork W1891287906 @default.
- W2897426518 hasRelatedWork W1969923398 @default.
- W2897426518 hasRelatedWork W2036807459 @default.
- W2897426518 hasRelatedWork W2058170566 @default.
- W2897426518 hasRelatedWork W2166044122 @default.
- W2897426518 hasRelatedWork W2229312674 @default.
- W2897426518 hasRelatedWork W258625772 @default.
- W2897426518 hasRelatedWork W2755342338 @default.
- W2897426518 hasRelatedWork W2772917594 @default.
- W2897426518 hasRelatedWork W3116076068 @default.
- W2897426518 isParatext "false" @default.
- W2897426518 isRetracted "false" @default.
- W2897426518 magId "2897426518" @default.
- W2897426518 workType "book-chapter" @default.