Matches in SemOpenAlex for { <https://semopenalex.org/work/W3203209821> ?p ?o ?g. }
- W3203209821 abstract "The objective of this work is person-clustering in videos – grouping characters according to their identity. Previous methods focus on the narrower task of face-clustering, and for the most part ignore other cues such as the person’s voice, their overall appearance (hair, clothes, posture), and the editing structure of the videos. Similarly, most current datasets evaluate only the task of face-clustering, rather than person-clustering. This limits their applicability to downstream applications such as story understanding which require person-level, rather than only face-level, reasoning.In this paper we make contributions to address both these deficiencies: first, we introduce a Multi-Modal High-Precision Clustering algorithm for person-clustering in videos using cues from several modalities (face, body, and voice). Second, we introduce a Video Person-Clustering dataset, for evaluating multi-modal person-clustering. It contains body-tracks for each annotated character, face-tracks when visible, and voice-tracks when speaking, with their associated features. The dataset is by far the largest of its kind, and covers films and TV-shows representing a wide range of demographics. Finally, we show the effectiveness of using multiple modalities for person-clustering, explore the use of this new broad task for story understanding through character co-occurrences, and achieve a new state of the art on all available datasets for face and person-clustering." @default.
- W3203209821 created "2021-10-11" @default.
- W3203209821 creator A5039721396 @default.
- W3203209821 creator A5048400549 @default.
- W3203209821 creator A5057678172 @default.
- W3203209821 date "2021-10-01" @default.
- W3203209821 modified "2023-10-01" @default.
- W3203209821 title "Face, Body, Voice: Video Person-Clustering with Multiple Modalities" @default.
- W3203209821 cites W121219881 @default.
- W3203209821 cites W1673564859 @default.
- W3203209821 cites W1892323599 @default.
- W3203209821 cites W1969014310 @default.
- W3203209821 cites W1982582425 @default.
- W3203209821 cites W1982925187 @default.
- W3203209821 cites W1986730198 @default.
- W3203209821 cites W2055622086 @default.
- W3203209821 cites W2063249218 @default.
- W3203209821 cites W2067175278 @default.
- W3203209821 cites W2073783916 @default.
- W3203209821 cites W2080027017 @default.
- W3203209821 cites W2089923519 @default.
- W3203209821 cites W2093153344 @default.
- W3203209821 cites W2107558380 @default.
- W3203209821 cites W2111899702 @default.
- W3203209821 cites W2115546586 @default.
- W3203209821 cites W2119031011 @default.
- W3203209821 cites W2121027212 @default.
- W3203209821 cites W2125742596 @default.
- W3203209821 cites W2138761194 @default.
- W3203209821 cites W2150469677 @default.
- W3203209821 cites W2151103935 @default.
- W3203209821 cites W2153603270 @default.
- W3203209821 cites W2165307239 @default.
- W3203209821 cites W2168996682 @default.
- W3203209821 cites W2170665590 @default.
- W3203209821 cites W2194775991 @default.
- W3203209821 cites W2204750386 @default.
- W3203209821 cites W2400416707 @default.
- W3203209821 cites W2519769969 @default.
- W3203209821 cites W2585635281 @default.
- W3203209821 cites W2620463417 @default.
- W3203209821 cites W2752782242 @default.
- W3203209821 cites W2799118171 @default.
- W3203209821 cites W2808631503 @default.
- W3203209821 cites W2884913105 @default.
- W3203209821 cites W2916104401 @default.
- W3203209821 cites W2962698660 @default.
- W3203209821 cites W2962749043 @default.
- W3203209821 cites W2962803520 @default.
- W3203209821 cites W2962845320 @default.
- W3203209821 cites W2962902099 @default.
- W3203209821 cites W2963047834 @default.
- W3203209821 cites W2963542293 @default.
- W3203209821 cites W2963614929 @default.
- W3203209821 cites W2963801643 @default.
- W3203209821 cites W2963839617 @default.
- W3203209821 cites W2963887950 @default.
- W3203209821 cites W2964241181 @default.
- W3203209821 cites W2981981567 @default.
- W3203209821 cites W2982673782 @default.
- W3203209821 cites W2987802279 @default.
- W3203209821 cites W3013020904 @default.
- W3203209821 cites W3034364644 @default.
- W3203209821 cites W3035124602 @default.
- W3203209821 cites W3096861448 @default.
- W3203209821 cites W3127635015 @default.
- W3203209821 cites W3206789311 @default.
- W3203209821 cites W38568571 @default.
- W3203209821 cites W4213009331 @default.
- W3203209821 doi "https://doi.org/10.1109/iccvw54120.2021.00357" @default.
- W3203209821 hasPublicationYear "2021" @default.
- W3203209821 type Work @default.
- W3203209821 sameAs 3203209821 @default.
- W3203209821 citedByCount "9" @default.
- W3203209821 countsByYear W32032098212021 @default.
- W3203209821 countsByYear W32032098212022 @default.
- W3203209821 countsByYear W32032098212023 @default.
- W3203209821 crossrefType "proceedings-article" @default.
- W3203209821 hasAuthorship W3203209821A5039721396 @default.
- W3203209821 hasAuthorship W3203209821A5048400549 @default.
- W3203209821 hasAuthorship W3203209821A5057678172 @default.
- W3203209821 hasBestOaLocation W32032098212 @default.
- W3203209821 hasConcept C120665830 @default.
- W3203209821 hasConcept C121332964 @default.
- W3203209821 hasConcept C144024400 @default.
- W3203209821 hasConcept C153180895 @default.
- W3203209821 hasConcept C154945302 @default.
- W3203209821 hasConcept C162324750 @default.
- W3203209821 hasConcept C185592680 @default.
- W3203209821 hasConcept C187736073 @default.
- W3203209821 hasConcept C188027245 @default.
- W3203209821 hasConcept C192209626 @default.
- W3203209821 hasConcept C2779304628 @default.
- W3203209821 hasConcept C2779903281 @default.
- W3203209821 hasConcept C2780451532 @default.
- W3203209821 hasConcept C36289849 @default.
- W3203209821 hasConcept C41008148 @default.
- W3203209821 hasConcept C71139939 @default.
- W3203209821 hasConcept C73555534 @default.
- W3203209821 hasConceptScore W3203209821C120665830 @default.