Sökning: WFRF:(Higuera Nelson) > A Neuro-Symbolic AS...
Fältnamn | Indikatorer | Metadata |
---|---|---|
000 | 03548naa a2200517 4500 | |
001 | oai:DiVA.org:hj-63556 | |
003 | SwePub | |
008 | 240216s2022 | |||||||||||000 ||eng| | |
024 | 7 | a https://urn.kb.se/resolve?urn=urn:nbn:se:hj:diva-635562 URI |
024 | 7 | a https://doi.org/10.1017/S14710684220002292 DOI |
040 | a (SwePub)hj | |
041 | a engb eng | |
042 | 9 SwePub | |
072 | 7 | a ref2 swepub-contenttype |
072 | 7 | a art2 swepub-publicationtype |
100 | 1 | a Eiter, Thomasu Institute of Logic and Computation, Vienna University of Technology (TU Wien), Austria4 aut |
245 | 1 0 | a A Neuro-Symbolic ASP Pipeline for Visual Question Answering |
264 | 1 | b Cambridge University Press,c 2022 |
338 | a print2 rdacarrier | |
520 | a We present a neuro-symbolic visual question answering (VQA) pipeline for CLEVR, which is a well-known dataset that consists of pictures showing scenes with objects and questions related to them. Our pipeline covers (i) training neural networks for object classification and bounding-box prediction of the CLEVR scenes, (ii) statistical analysis on the distribution of prediction values of the neural networks to determine a threshold for high-confidence predictions, and (iii) a translation of CLEVR questions and network predictions that pass confidence thresholds into logic programmes so that we can compute the answers using an answer-set programming solver. By exploiting choice rules, we consider deterministic and non-deterministic scene encodings. Our experiments show that the non-deterministic scene encoding achieves good results even if the neural networks are trained rather poorly in comparison with the deterministic approach. This is important for building robust VQA systems if network predictions are less-than perfect. Furthermore, we show that restricting non-determinism to reasonable choices allows for more efficient implementations in comparison with related neuro-symbolic approaches without losing much accuracy. | |
650 | 7 | a NATURVETENSKAPx Data- och informationsvetenskapx Datavetenskap0 (SwePub)102012 hsv//swe |
650 | 7 | a NATURAL SCIENCESx Computer and Information Sciencesx Computer Sciences0 (SwePub)102012 hsv//eng |
653 | a answer-set programming | |
653 | a neuro-symbolic computation | |
653 | a visual question answering | |
653 | a Computation theory | |
653 | a Encoding (symbols) | |
653 | a Forecasting | |
653 | a Logic programming | |
653 | a Program translators | |
653 | a Answer set programming | |
653 | a Deterministics | |
653 | a Encodings | |
653 | a Network prediction | |
653 | a Neural-networks | |
653 | a Object classification | |
653 | a Question Answering | |
653 | a Symbolic computation | |
653 | a Pipelines | |
700 | 1 | a Higuera, Nelsonu Institute of Logic and Computation, Vienna University of Technology (TU Wien), Austria4 aut |
700 | 1 | a Oetsch, Johannesu Institute of Logic and Computation, Vienna University of Technology (TU Wien), Austria4 aut0 (Swepub:hj)oetjoh |
700 | 1 | a Pritz, Michaelu Institute of Logic and Computation, Vienna University of Technology (TU Wien), Austria4 aut |
710 | 2 | a Institute of Logic and Computation, Vienna University of Technology (TU Wien), Austria4 org |
773 | 0 | t Theory and Practice of Logic Programmingd : Cambridge University Pressg 22:5, s. 739-754q 22:5<739-754x 1471-0684x 1475-3081 |
856 | 4 8 | u https://urn.kb.se/resolve?urn=urn:nbn:se:hj:diva-63556 |
856 | 4 8 | u https://doi.org/10.1017/S1471068422000229 |
Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.