Matches in SemOpenAlex for { <https://semopenalex.org/work/W4310632521> ?p ?o ?g. }
Showing items 1 to 69 of
69
with 100 items per page.
- W4310632521 abstract "Visual recognition of materials and their states is essential for understanding most aspects of the world, from determining whether food is cooked, metal is rusted, or a chemical reaction has occurred. However, current image recognition methods are limited to specific classes and properties and can't handle the vast number of material states in the world. To address this, we present MatSim: the first dataset and benchmark for computer vision-based recognition of similarities and transitions between materials and textures, focusing on identifying any material under any conditions using one or a few examples. The dataset contains synthetic and natural images. The synthetic images were rendered using giant collections of textures, objects, and environments generated by computer graphics artists. We use mixtures and gradual transitions between materials to allow the system to learn cases with smooth transitions between states (like gradually cooked food). We also render images with materials inside transparent containers to support beverage and chemistry lab use cases. We use this dataset to train a siamese net that identifies the same material in different objects, mixtures, and environments. The descriptor generated by this net can be used to identify the states of materials and their subclasses using a single image. We also present the first few-shot material recognition benchmark with images from a wide range of fields, including the state of foods and drinks, types of grounds, and many other use cases. We show that a net trained on the MatSim synthetic dataset outperforms state-of-the-art models like Clip on the benchmark and also achieves good results on other unsupervised material classification tasks." @default.
- W4310632521 created "2022-12-13" @default.
- W4310632521 creator A5021796022 @default.
- W4310632521 creator A5064409029 @default.
- W4310632521 creator A5071495561 @default.
- W4310632521 creator A5083417558 @default.
- W4310632521 creator A5088229898 @default.
- W4310632521 date "2022-12-01" @default.
- W4310632521 modified "2023-10-01" @default.
- W4310632521 title "One-shot recognition of any material anywhere using contrastive learning with physics-based rendering" @default.
- W4310632521 doi "https://doi.org/10.48550/arxiv.2212.00648" @default.
- W4310632521 hasPublicationYear "2022" @default.
- W4310632521 type Work @default.
- W4310632521 citedByCount "0" @default.
- W4310632521 crossrefType "posted-content" @default.
- W4310632521 hasAuthorship W4310632521A5021796022 @default.
- W4310632521 hasAuthorship W4310632521A5064409029 @default.
- W4310632521 hasAuthorship W4310632521A5071495561 @default.
- W4310632521 hasAuthorship W4310632521A5083417558 @default.
- W4310632521 hasAuthorship W4310632521A5088229898 @default.
- W4310632521 hasBestOaLocation W43106325211 @default.
- W4310632521 hasConcept C115961682 @default.
- W4310632521 hasConcept C121684516 @default.
- W4310632521 hasConcept C153180895 @default.
- W4310632521 hasConcept C154945302 @default.
- W4310632521 hasConcept C185798385 @default.
- W4310632521 hasConcept C191897082 @default.
- W4310632521 hasConcept C192562407 @default.
- W4310632521 hasConcept C205649164 @default.
- W4310632521 hasConcept C205711294 @default.
- W4310632521 hasConcept C21442007 @default.
- W4310632521 hasConcept C2778344882 @default.
- W4310632521 hasConcept C2989087649 @default.
- W4310632521 hasConcept C31972630 @default.
- W4310632521 hasConcept C41008148 @default.
- W4310632521 hasConcept C58640448 @default.
- W4310632521 hasConcept C77660652 @default.
- W4310632521 hasConceptScore W4310632521C115961682 @default.
- W4310632521 hasConceptScore W4310632521C121684516 @default.
- W4310632521 hasConceptScore W4310632521C153180895 @default.
- W4310632521 hasConceptScore W4310632521C154945302 @default.
- W4310632521 hasConceptScore W4310632521C185798385 @default.
- W4310632521 hasConceptScore W4310632521C191897082 @default.
- W4310632521 hasConceptScore W4310632521C192562407 @default.
- W4310632521 hasConceptScore W4310632521C205649164 @default.
- W4310632521 hasConceptScore W4310632521C205711294 @default.
- W4310632521 hasConceptScore W4310632521C21442007 @default.
- W4310632521 hasConceptScore W4310632521C2778344882 @default.
- W4310632521 hasConceptScore W4310632521C2989087649 @default.
- W4310632521 hasConceptScore W4310632521C31972630 @default.
- W4310632521 hasConceptScore W4310632521C41008148 @default.
- W4310632521 hasConceptScore W4310632521C58640448 @default.
- W4310632521 hasConceptScore W4310632521C77660652 @default.
- W4310632521 hasLocation W43106325211 @default.
- W4310632521 hasOpenAccess W4310632521 @default.
- W4310632521 hasPrimaryLocation W43106325211 @default.
- W4310632521 hasRelatedWork W1503820821 @default.
- W4310632521 hasRelatedWork W1516974178 @default.
- W4310632521 hasRelatedWork W2033623701 @default.
- W4310632521 hasRelatedWork W2080528351 @default.
- W4310632521 hasRelatedWork W2159411344 @default.
- W4310632521 hasRelatedWork W2166044122 @default.
- W4310632521 hasRelatedWork W2170209930 @default.
- W4310632521 hasRelatedWork W2319989118 @default.
- W4310632521 hasRelatedWork W3192969084 @default.
- W4310632521 hasRelatedWork W2119752710 @default.
- W4310632521 isParatext "false" @default.
- W4310632521 isRetracted "false" @default.
- W4310632521 workType "article" @default.