Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313038449> ?p ?o ?g. }
- W4313038449 endingPage "557" @default.
- W4313038449 startingPage "540" @default.
- W4313038449 abstract "YouTube users looking for instructions for a specific task may spend a long time browsing content trying to find the right video that matches their needs. Creating a visual summary (abridged version of a video) provides viewers with a quick overview and massively reduces search time. In this work, we focus on summarizing instructional videos, an under-explored area of video summarization. In comparison to generic videos, instructional videos can be parsed into semantically meaningful segments that correspond to important steps of the demonstrated task. Existing video summarization datasets rely on manual frame-level annotations, making them subjective and limited in size. To overcome this, we first automatically generate pseudo summaries for a corpus of instructional videos by exploiting two key assumptions: (i) relevant steps are likely to appear in multiple videos of the same task (Task Relevance), and (ii) they are more likely to be described by the demonstrator verbally (Cross-Modal Saliency). We propose an instructional video summarization network that combines a context-aware temporal video encoder and a segment scoring transformer. Using pseudo summaries as weak supervision, our network constructs a visual summary for an instructional video given only video and transcribed speech. To evaluate our model, we collect a high-quality test set, WikiHow Summaries, by scraping WikiHow articles that contain video demonstrations and visual depictions of steps allowing us to obtain the ground-truth summaries. We outperform several baselines and a state-of-the-art video summarization model on this new benchmark." @default.
- W4313038449 created "2023-01-06" @default.
- W4313038449 creator A5007681620 @default.
- W4313038449 creator A5029105520 @default.
- W4313038449 creator A5036002448 @default.
- W4313038449 creator A5037747070 @default.
- W4313038449 creator A5045217258 @default.
- W4313038449 creator A5059142581 @default.
- W4313038449 creator A5060145891 @default.
- W4313038449 date "2022-01-01" @default.
- W4313038449 modified "2023-09-26" @default.
- W4313038449 title "TL;DW? Summarizing Instructional Videos with Task Relevance and Cross-Modal Saliency" @default.
- W4313038449 cites W1987366351 @default.
- W4313038449 cites W1991750682 @default.
- W4313038449 cites W2108710284 @default.
- W4313038449 cites W2194775991 @default.
- W4313038449 cites W2477205648 @default.
- W4313038449 cites W2517959782 @default.
- W4313038449 cites W2529272619 @default.
- W4313038449 cites W2530494944 @default.
- W4313038449 cites W2600081845 @default.
- W4313038449 cites W2737677090 @default.
- W4313038449 cites W2788303226 @default.
- W4313038449 cites W2795187948 @default.
- W4313038449 cites W2798345491 @default.
- W4313038449 cites W2798970487 @default.
- W4313038449 cites W2883429621 @default.
- W4313038449 cites W2895758197 @default.
- W4313038449 cites W2903758693 @default.
- W4313038449 cites W2957775769 @default.
- W4313038449 cites W2962795934 @default.
- W4313038449 cites W2963220254 @default.
- W4313038449 cites W2963432616 @default.
- W4313038449 cites W2963508075 @default.
- W4313038449 cites W2963524571 @default.
- W4313038449 cites W2963642716 @default.
- W4313038449 cites W2963919999 @default.
- W4313038449 cites W2964094654 @default.
- W4313038449 cites W2964158702 @default.
- W4313038449 cites W2967219836 @default.
- W4313038449 cites W2982335217 @default.
- W4313038449 cites W2982672255 @default.
- W4313038449 cites W2984008963 @default.
- W4313038449 cites W3034815696 @default.
- W4313038449 cites W3035218028 @default.
- W4313038449 cites W3035635319 @default.
- W4313038449 cites W3107252718 @default.
- W4313038449 cites W4255898812 @default.
- W4313038449 cites W805710393 @default.
- W4313038449 doi "https://doi.org/10.1007/978-3-031-19830-4_31" @default.
- W4313038449 hasPublicationYear "2022" @default.
- W4313038449 type Work @default.
- W4313038449 citedByCount "1" @default.
- W4313038449 countsByYear W43130384492023 @default.
- W4313038449 crossrefType "book-chapter" @default.
- W4313038449 hasAuthorship W4313038449A5007681620 @default.
- W4313038449 hasAuthorship W4313038449A5029105520 @default.
- W4313038449 hasAuthorship W4313038449A5036002448 @default.
- W4313038449 hasAuthorship W4313038449A5037747070 @default.
- W4313038449 hasAuthorship W4313038449A5045217258 @default.
- W4313038449 hasAuthorship W4313038449A5059142581 @default.
- W4313038449 hasAuthorship W4313038449A5060145891 @default.
- W4313038449 hasConcept C103910844 @default.
- W4313038449 hasConcept C111919701 @default.
- W4313038449 hasConcept C118505674 @default.
- W4313038449 hasConcept C146849305 @default.
- W4313038449 hasConcept C151730666 @default.
- W4313038449 hasConcept C154945302 @default.
- W4313038449 hasConcept C158154518 @default.
- W4313038449 hasConcept C162324750 @default.
- W4313038449 hasConcept C170858558 @default.
- W4313038449 hasConcept C176217482 @default.
- W4313038449 hasConcept C17744445 @default.
- W4313038449 hasConcept C187736073 @default.
- W4313038449 hasConcept C199539241 @default.
- W4313038449 hasConcept C204321447 @default.
- W4313038449 hasConcept C21547014 @default.
- W4313038449 hasConcept C23123220 @default.
- W4313038449 hasConcept C2779343474 @default.
- W4313038449 hasConcept C2780451532 @default.
- W4313038449 hasConcept C41008148 @default.
- W4313038449 hasConcept C49774154 @default.
- W4313038449 hasConcept C86803240 @default.
- W4313038449 hasConceptScore W4313038449C103910844 @default.
- W4313038449 hasConceptScore W4313038449C111919701 @default.
- W4313038449 hasConceptScore W4313038449C118505674 @default.
- W4313038449 hasConceptScore W4313038449C146849305 @default.
- W4313038449 hasConceptScore W4313038449C151730666 @default.
- W4313038449 hasConceptScore W4313038449C154945302 @default.
- W4313038449 hasConceptScore W4313038449C158154518 @default.
- W4313038449 hasConceptScore W4313038449C162324750 @default.
- W4313038449 hasConceptScore W4313038449C170858558 @default.
- W4313038449 hasConceptScore W4313038449C176217482 @default.
- W4313038449 hasConceptScore W4313038449C17744445 @default.
- W4313038449 hasConceptScore W4313038449C187736073 @default.
- W4313038449 hasConceptScore W4313038449C199539241 @default.
- W4313038449 hasConceptScore W4313038449C204321447 @default.
- W4313038449 hasConceptScore W4313038449C21547014 @default.