Matches in SemOpenAlex for { <https://semopenalex.org/work/W4226241749> ?p ?o ?g. }
Showing items 1 to 66 of
66
with 100 items per page.
- W4226241749 abstract "Video-based computer vision tasks can benefit from the estimation of the salient regions and interactions between those regions. Traditionally, this has been done by identifying the object regions in the images by utilizing pre-trained models to perform object detection, object segmentation, and/or object pose estimation. Though using pre-trained models seems to be a viable approach, it is infeasible in practice due to the need for exhaustive annotation of object categories, domain gap between datasets, and bias present in pre-trained models. To overcome these downsides, we propose to utilize the common rationale that a sequence of video frames capture a set of common objects and interactions between them, thus a notion of co-segmentation between the video frame features may equip the model with the ability to automatically focus on salient regions and improve underlying task's performance in an end-to-end manner. In this regard, we propose a generic module called Co-Segmentation Activation Module (COSAM) that can be plugged into any CNN to promote the notion of co-segmentation based attention among a sequence of video frame features. We show the application of COSAM in three video-based tasks namely: 1) Video-based person re-ID, 2) Video captioning, & 3) Video action classification, and demonstrate that COSAM is able to capture salient regions in the video frames, thus leading to notable performance improvements along with interpretable attention maps." @default.
- W4226241749 created "2022-05-05" @default.
- W4226241749 creator A5005071910 @default.
- W4226241749 creator A5049298671 @default.
- W4226241749 creator A5078970246 @default.
- W4226241749 creator A5080919155 @default.
- W4226241749 creator A5085648720 @default.
- W4226241749 date "2021-11-14" @default.
- W4226241749 modified "2023-09-27" @default.
- W4226241749 title "Co-segmentation Inspired Attention Module for Video-based Computer Vision Tasks" @default.
- W4226241749 hasPublicationYear "2021" @default.
- W4226241749 type Work @default.
- W4226241749 citedByCount "0" @default.
- W4226241749 crossrefType "posted-content" @default.
- W4226241749 hasAuthorship W4226241749A5005071910 @default.
- W4226241749 hasAuthorship W4226241749A5049298671 @default.
- W4226241749 hasAuthorship W4226241749A5078970246 @default.
- W4226241749 hasAuthorship W4226241749A5080919155 @default.
- W4226241749 hasAuthorship W4226241749A5085648720 @default.
- W4226241749 hasBestOaLocation W42262417491 @default.
- W4226241749 hasConcept C115961682 @default.
- W4226241749 hasConcept C126042441 @default.
- W4226241749 hasConcept C153180895 @default.
- W4226241749 hasConcept C154945302 @default.
- W4226241749 hasConcept C157657479 @default.
- W4226241749 hasConcept C162324750 @default.
- W4226241749 hasConcept C187736073 @default.
- W4226241749 hasConcept C202474056 @default.
- W4226241749 hasConcept C2780451532 @default.
- W4226241749 hasConcept C2780719617 @default.
- W4226241749 hasConcept C2781238097 @default.
- W4226241749 hasConcept C31972630 @default.
- W4226241749 hasConcept C41008148 @default.
- W4226241749 hasConcept C76155785 @default.
- W4226241749 hasConcept C89600930 @default.
- W4226241749 hasConceptScore W4226241749C115961682 @default.
- W4226241749 hasConceptScore W4226241749C126042441 @default.
- W4226241749 hasConceptScore W4226241749C153180895 @default.
- W4226241749 hasConceptScore W4226241749C154945302 @default.
- W4226241749 hasConceptScore W4226241749C157657479 @default.
- W4226241749 hasConceptScore W4226241749C162324750 @default.
- W4226241749 hasConceptScore W4226241749C187736073 @default.
- W4226241749 hasConceptScore W4226241749C202474056 @default.
- W4226241749 hasConceptScore W4226241749C2780451532 @default.
- W4226241749 hasConceptScore W4226241749C2780719617 @default.
- W4226241749 hasConceptScore W4226241749C2781238097 @default.
- W4226241749 hasConceptScore W4226241749C31972630 @default.
- W4226241749 hasConceptScore W4226241749C41008148 @default.
- W4226241749 hasConceptScore W4226241749C76155785 @default.
- W4226241749 hasConceptScore W4226241749C89600930 @default.
- W4226241749 hasLocation W42262417491 @default.
- W4226241749 hasOpenAccess W4226241749 @default.
- W4226241749 hasPrimaryLocation W42262417491 @default.
- W4226241749 hasRelatedWork W10777306 @default.
- W4226241749 hasRelatedWork W10828093 @default.
- W4226241749 hasRelatedWork W11270157 @default.
- W4226241749 hasRelatedWork W11555516 @default.
- W4226241749 hasRelatedWork W1230437 @default.
- W4226241749 hasRelatedWork W5619462 @default.
- W4226241749 hasRelatedWork W5999557 @default.
- W4226241749 hasRelatedWork W6473745 @default.
- W4226241749 hasRelatedWork W8031603 @default.
- W4226241749 hasRelatedWork W9142954 @default.
- W4226241749 isParatext "false" @default.
- W4226241749 isRetracted "false" @default.
- W4226241749 workType "article" @default.