Matches in SemOpenAlex for { <https://semopenalex.org/work/W2954275231> ?p ?o ?g. }
- W2954275231 abstract "In this paper, we address a new task called instance co-segmentation. Given a set of images jointly covering object instances of a specific category, instance co-segmentation aims to identify all of these instances and segment each of them, i.e. generating one mask for each instance. This task is important since instance-level segmentation is preferable for humans and many vision applications. It is also challenging because no pixel-wise annotated training data are available and the number of instances in each image is unknown. We solve this task by dividing it into two sub-tasks, co-peak search and instance mask segmentation. In the former sub-task, we develop a CNN-based network to detect the co-peaks as well as co-saliency maps for a pair of images. A co-peak has two endpoints, one in each image, that are local maxima in the response maps and similar to each other. Thereby, the two endpoints are potentially covered by a pair of instances of the same category. In the latter subtask, we design a ranking function that takes the detected co-peaks and co-saliency maps as inputs and can select the object proposals to produce the final results. Our method for instance co-segmentation and its variant for object colocalization are evaluated on four datasets, and achieve favorable performance against the state-of-the-art methods. The source codes and the collected datasets are available at https://github.com/KuangJuiHsu/DeepCO3/" @default.
- W2954275231 created "2019-07-12" @default.
- W2954275231 creator A5002217153 @default.
- W2954275231 creator A5006990118 @default.
- W2954275231 creator A5018956110 @default.
- W2954275231 date "2019-06-01" @default.
- W2954275231 modified "2023-09-30" @default.
- W2954275231 title "DeepCO3: Deep Instance Co-Segmentation by Co-Peak Search and Co-Saliency Detection" @default.
- W2954275231 cites W1534510265 @default.
- W2954275231 cites W1919709169 @default.
- W2954275231 cites W1966601141 @default.
- W2954275231 cites W1986916218 @default.
- W2954275231 cites W1989208478 @default.
- W2954275231 cites W1996140089 @default.
- W2954275231 cites W2031489346 @default.
- W2954275231 cites W2117539524 @default.
- W2954275231 cites W2144794286 @default.
- W2954275231 cites W2153760331 @default.
- W2954275231 cites W2160812203 @default.
- W2954275231 cites W2168804568 @default.
- W2954275231 cites W2216125271 @default.
- W2954275231 cites W2464606141 @default.
- W2954275231 cites W2468480815 @default.
- W2954275231 cites W2470909866 @default.
- W2954275231 cites W2511737830 @default.
- W2954275231 cites W2552579943 @default.
- W2954275231 cites W2555182955 @default.
- W2954275231 cites W2557889580 @default.
- W2954275231 cites W2604413995 @default.
- W2954275231 cites W2605482930 @default.
- W2954275231 cites W2605929543 @default.
- W2954275231 cites W2616689446 @default.
- W2954275231 cites W2740660291 @default.
- W2954275231 cites W2744613561 @default.
- W2954275231 cites W2747199123 @default.
- W2954275231 cites W2749895778 @default.
- W2954275231 cites W2750988638 @default.
- W2954275231 cites W2773771410 @default.
- W2954275231 cites W2777511827 @default.
- W2954275231 cites W2777921528 @default.
- W2954275231 cites W2807912089 @default.
- W2954275231 cites W2887503470 @default.
- W2954275231 cites W2892946444 @default.
- W2954275231 cites W2962849746 @default.
- W2954275231 cites W2963150697 @default.
- W2954275231 cites W2963167763 @default.
- W2954275231 cites W2963311325 @default.
- W2954275231 cites W2963430551 @default.
- W2954275231 cites W2963455537 @default.
- W2954275231 cites W2963857746 @default.
- W2954275231 cites W2963915286 @default.
- W2954275231 cites W2964211168 @default.
- W2954275231 doi "https://doi.org/10.1109/cvpr.2019.00905" @default.
- W2954275231 hasPublicationYear "2019" @default.
- W2954275231 type Work @default.
- W2954275231 sameAs 2954275231 @default.
- W2954275231 citedByCount "54" @default.
- W2954275231 countsByYear W29542752312018 @default.
- W2954275231 countsByYear W29542752312019 @default.
- W2954275231 countsByYear W29542752312020 @default.
- W2954275231 countsByYear W29542752312021 @default.
- W2954275231 countsByYear W29542752312022 @default.
- W2954275231 countsByYear W29542752312023 @default.
- W2954275231 crossrefType "proceedings-article" @default.
- W2954275231 hasAuthorship W2954275231A5002217153 @default.
- W2954275231 hasAuthorship W2954275231A5006990118 @default.
- W2954275231 hasAuthorship W2954275231A5018956110 @default.
- W2954275231 hasConcept C115961682 @default.
- W2954275231 hasConcept C124504099 @default.
- W2954275231 hasConcept C134306372 @default.
- W2954275231 hasConcept C153180895 @default.
- W2954275231 hasConcept C154290570 @default.
- W2954275231 hasConcept C154945302 @default.
- W2954275231 hasConcept C160633673 @default.
- W2954275231 hasConcept C162324750 @default.
- W2954275231 hasConcept C177264268 @default.
- W2954275231 hasConcept C186633575 @default.
- W2954275231 hasConcept C187736073 @default.
- W2954275231 hasConcept C189430467 @default.
- W2954275231 hasConcept C199360897 @default.
- W2954275231 hasConcept C25694479 @default.
- W2954275231 hasConcept C2776151529 @default.
- W2954275231 hasConcept C2780451532 @default.
- W2954275231 hasConcept C2781238097 @default.
- W2954275231 hasConcept C31972630 @default.
- W2954275231 hasConcept C33923547 @default.
- W2954275231 hasConcept C41008148 @default.
- W2954275231 hasConcept C65885262 @default.
- W2954275231 hasConcept C89600930 @default.
- W2954275231 hasConceptScore W2954275231C115961682 @default.
- W2954275231 hasConceptScore W2954275231C124504099 @default.
- W2954275231 hasConceptScore W2954275231C134306372 @default.
- W2954275231 hasConceptScore W2954275231C153180895 @default.
- W2954275231 hasConceptScore W2954275231C154290570 @default.
- W2954275231 hasConceptScore W2954275231C154945302 @default.
- W2954275231 hasConceptScore W2954275231C160633673 @default.
- W2954275231 hasConceptScore W2954275231C162324750 @default.
- W2954275231 hasConceptScore W2954275231C177264268 @default.
- W2954275231 hasConceptScore W2954275231C186633575 @default.
- W2954275231 hasConceptScore W2954275231C187736073 @default.