Matches in SemOpenAlex for { <https://semopenalex.org/work/W2891350675> ?p ?o ?g. }
- W2891350675 abstract "Grounding language in images has shown it can help improve performance on many image-language tasks. To spur research on this topic, this dissertation introduces a new dataset which provides the ground truth annotations of the location of noun phrase chunks in image captions. I begin by introducing a constituent task termed phrase localization, where the goal is to localize an entity known to exist in an image when provided with a natural language query. To address this task, I introduce a model which learns a set of models, each of which capture a different concept which is useful in our task. These concepts can be predefined, such as attributes gleamed from the adjectives, as well as those which are automatically learned in a single-end-to-end neural network. I also address the more challenging detection style task, where the goal is to localize a phrase and determine if it is associated with an image. Multiple applications of the models presented in this work demonstrate their value beyond the phrase localization task." @default.
- W2891350675 created "2018-09-27" @default.
- W2891350675 creator A5061227594 @default.
- W2891350675 date "2018-04-16" @default.
- W2891350675 modified "2023-09-23" @default.
- W2891350675 title "Grounding natural language phrases in images and video" @default.
- W2891350675 cites W114341944 @default.
- W2891350675 cites W125693051 @default.
- W2891350675 cites W13223599 @default.
- W2891350675 cites W1514535095 @default.
- W2891350675 cites W1523385540 @default.
- W2891350675 cites W1527575280 @default.
- W2891350675 cites W1536680647 @default.
- W2891350675 cites W1566289585 @default.
- W2891350675 cites W1584193343 @default.
- W2891350675 cites W1618905105 @default.
- W2891350675 cites W1686810756 @default.
- W2891350675 cites W1773149199 @default.
- W2891350675 cites W1780302016 @default.
- W2891350675 cites W1861492603 @default.
- W2891350675 cites W1891152514 @default.
- W2891350675 cites W1895577753 @default.
- W2891350675 cites W1897761818 @default.
- W2891350675 cites W1905882502 @default.
- W2891350675 cites W1910566948 @default.
- W2891350675 cites W1916445035 @default.
- W2891350675 cites W1924343884 @default.
- W2891350675 cites W1931795219 @default.
- W2891350675 cites W1934863104 @default.
- W2891350675 cites W1947481528 @default.
- W2891350675 cites W1949478088 @default.
- W2891350675 cites W1958932515 @default.
- W2891350675 cites W1960364170 @default.
- W2891350675 cites W1964073652 @default.
- W2891350675 cites W1987835821 @default.
- W2891350675 cites W198983373 @default.
- W2891350675 cites W1996418862 @default.
- W2891350675 cites W2024991751 @default.
- W2891350675 cites W2032342062 @default.
- W2891350675 cites W2035720976 @default.
- W2891350675 cites W2036335323 @default.
- W2891350675 cites W2049705550 @default.
- W2891350675 cites W2070753207 @default.
- W2891350675 cites W2088049833 @default.
- W2891350675 cites W2094998392 @default.
- W2891350675 cites W2095242101 @default.
- W2891350675 cites W2095536970 @default.
- W2891350675 cites W2100235303 @default.
- W2891350675 cites W2102605133 @default.
- W2891350675 cites W2103908291 @default.
- W2891350675 cites W2105174364 @default.
- W2891350675 cites W2106229755 @default.
- W2891350675 cites W2110628941 @default.
- W2891350675 cites W2115857089 @default.
- W2891350675 cites W2119775030 @default.
- W2891350675 cites W2120645068 @default.
- W2891350675 cites W2122146326 @default.
- W2891350675 cites W2123024445 @default.
- W2891350675 cites W2123378748 @default.
- W2891350675 cites W2125560515 @default.
- W2891350675 cites W2131576855 @default.
- W2891350675 cites W2137471889 @default.
- W2891350675 cites W2137918516 @default.
- W2891350675 cites W2139615075 @default.
- W2891350675 cites W2141364309 @default.
- W2891350675 cites W2151103935 @default.
- W2891350675 cites W2153579005 @default.
- W2891350675 cites W2153635508 @default.
- W2891350675 cites W2154652894 @default.
- W2891350675 cites W2155541015 @default.
- W2891350675 cites W2157220174 @default.
- W2891350675 cites W2157331557 @default.
- W2891350675 cites W2158504911 @default.
- W2891350675 cites W2164455818 @default.
- W2891350675 cites W2164587673 @default.
- W2891350675 cites W2167851108 @default.
- W2891350675 cites W2168356304 @default.
- W2891350675 cites W2172191903 @default.
- W2891350675 cites W2184188583 @default.
- W2891350675 cites W2185175083 @default.
- W2891350675 cites W2189070436 @default.
- W2891350675 cites W2194775991 @default.
- W2891350675 cites W2217772701 @default.
- W2891350675 cites W2277195237 @default.
- W2891350675 cites W2284126738 @default.
- W2891350675 cites W2334493732 @default.
- W2891350675 cites W2339712187 @default.
- W2891350675 cites W2463565445 @default.
- W2891350675 cites W2479423890 @default.
- W2891350675 cites W2507009361 @default.
- W2891350675 cites W2546696630 @default.
- W2891350675 cites W2552161745 @default.
- W2891350675 cites W2570343428 @default.
- W2891350675 cites W2583360688 @default.
- W2891350675 cites W2584723080 @default.
- W2891350675 cites W2605991684 @default.
- W2891350675 cites W2606746036 @default.
- W2891350675 cites W2613718673 @default.
- W2891350675 cites W2620365397 @default.
- W2891350675 cites W2769900707 @default.