Meta tags:
author=Kushal Kafle;
keywords=RIT, kushalkafle, Kushal Kafle, machine learning, AI, Artificial Intelligence, Computer Vision, Deep learning, Neural Networks, Tigers, Adobe Research, Adobe, Microsoft Research, Microsoft;

Headings (most frequently used words):

and, the, of, answering, question, in, for, visual, to, vqa, christopher, kanan, we, kushal, kafle, paper, algorithms, on, that, research, vision, 2019, our, as, questions, datasets, is, data, understanding, state, language, models, was, accepted, new, answer, an, 2017, at, with, are, art, cvpr, 2018, computer, bibtex, title, author, year, grand, my, this, dvqa, image, about, counting, 2016, robik, shrestha, have, arxiv, here, conference, inproceedings, booktitle, working, algorithm, be, visualizations, propose, dataset, both, ieee, reasoning, but, also, mar, chart, tallyqa, complex, challenges, learning, remind, by, it, than, some, you, adobe, am, only, 2020, them, all, augmentation, future, journal, manoj, acharya, approach, methods, which, review, using, scott, cohen, brian, price, bar, prefil, can, two, more, existing, better, david, hilbert, scientist, novel, not, demonstrate, started, toward, universal, aaai, may, via, analysis, iccv, available, inlg, type, prediction, neural, network, efficient, results, article, bimodal, fusion, proposed, charts, first, these, systems, been, artificial, intelligence, natural, evaluation, current, domains, pattern, recognition, simple, open, ended, project, page, categories, from, erdos, lineage, link, where, dr, develop, robust, interested, grounded, right, feb, successfully, defended, wacv, intern, summer, co, organizing, second, workshop, shortcomings, sivl, nov, proposal, advancement, jul, jun, short, cviu, web, demo, aws, machine, under, your, prevent, catastrophic, forgetting, tyler, hayes, must, incrementally, train, training, work, replay, images, memory, unlike, other, manner, learns, one, time, rather, large, achieves, incremental, cannot, comparison, preprint, cqa, task, embeddings, features, then, given, baselines, used, winter, applications, prospects, tasks, method, should, test, tests, recent, good, performance, into, focuses, require, capable, across, make, possible, do, problem, most, study, relation, networks, baseline, qa, benchmark, when, many, framework, particular, perform, attention, ability, different, difficult, over, including, how, others, international, mohammed, yousefhussien, discuss, combined, model, four, number, impressive, academic, norbert, weiner, advisor, bertrand, russell, advisors, gets, there, if, follow, eventually, encounter, really, big, shot, names, laplace, fourier, poisson, lagrange, dirichlet, talk, standing, shoulder, giants, me, timeline, events, publications, misc, currently, recently, completed, ph, chester, carlson, center, imaging, science, rochester, institute, technology, worked, overarching, goal, developing, specifically, exploring, capacity, reasons, dissertation, sept, describing, appear, will, microsoft, redmond, jan, edition, naacl, thesis, aka, candidacy, july, eccv, recognized, outstanding, reviewer, survey, titled, application, deep, school, scholarship, apr, launched, online, added, well, amazon, services, grant, awarded, 15k, worth, credits, 2015, neuromorphic, perception, laboratory, denotes, equal, contribution, lifelong, agent, updated, knowledge, instead, having, distinct, deployment, phases, convolutional, prior, has, enabled, storing, raw, intensive, ideal, embedded, agents, tensor, quantization, enables, tensors, trained, streaming, meaning, example, batches, containing, multiple, classes, class, imagenet, 1k, generality, pioneering, multi, modal, readily, done, hayes2019remind, 1910, 02509, newly, pie, line, graphs, called, parallel, recurrent, fusing, intelligently, aggregates, learned, despite, its, simplicity, greatly, surpasses, human, figureqa, additionally, reconstruct, tables, asking, series, kafle2020answering, pages, 1498, 1507, often, evaluating, progress, ideally, plethora, capabilities, integrate, however, behaving, turing, studies, demonstrated, achieving, through, flaws, procedures, affairs, outline, path, forward, frontiers, computation, kafle2019challenges, 1904, 09317, split, camps, synthetic, few, tested, compare, five, eight, covering, fair, standardized, much, they, use, same, vocabularies, etc, find, generalize, address, rivals, or, exceeds, code, coming, soon, shrestha2019ramen, no, object, detection, involve, relationships, between, objects, attribute, identification, created, world, largest, uses, region, proposals, lets, efficiently, high, resolution, imagery, yields, compared, howmany, association, acharya2019tallyqa, effective, way, humans, convey, information, each, today, parse, fail, faced, minor, variations, appearance, present, aspects, requires, processing, words, answers, unique, poorly, strong, considerably, serves, important, proxy, several, critical, ai, abilities, such, handle, dynamic, out, vocabulary, oov, labels, kafle2018dvqa, analyzing, comparing, notoriously, opaque, analyze, contains, million, organized, 12, meaningless, schemes, compensate, represented, types, easier, strengths, weaknesses, experiments, establish, helps, certain, determine, explain, mlp, surpass, mcb, simply, easy, kafle2017analysis, describe, means, producing, show, increased, pronounced, increase, remain, problems, generation, kafle2017data, since, release, 2014, additional, released, critically, examine, terms, formulation, metrics, limitations, regard, their, properly, assess, exhaustively, finally, directions, kafle2017visual, build, system, text, based, known, key, insight, predict, form, formulate, solution, bayesian, discriminative, publication, daquar, coco, visual7w, kafle2016answer, what, follows, long, winded, collaboration, hunting, deny, facts, kostas, danilidis, pavel, valtr, paul,

Text of the page (most frequently used words):
and (84), the (44), #answering (36), question (35), for (30), #visual (29), kushal (25), kafle (25), vqa (25), christopher (23), kanan (23), paper (21), algorithms (20), that (17), research (16), vision (15), 2019 (15), our (14), questions (13), datasets (13), state (12), understanding (12), data (12), answer (11), 2017 (11), language (11), new (11), models (11), accepted (11), was (11), title (10), author (10), cvpr (10), year (10), bibtex (10), computer (10), with (10), art (10), 2018 (10), are (9), this (9), image (9), dvqa (9), about (8), 2016 (8), counting (8), shrestha (8), robik (8), have (7), inproceedings (7), booktitle (7), conference (7), arxiv (7), here (6), ieee (6), dataset (6), both (6), propose (6), visualizations (6), working (6), algorithm (6), but (5), grand (5), challenges (5), also (5), than (5), complex (5), learning (5), chart (5), reasoning (5), tallyqa (5), remind (5), mar (5), can (4), which (4), approach (4), future (4), journal (4), review (4), existing (4), augmentation (4), two (4), using (4), methods (4), more (4), price (4), brian (4), cohen (4), scott (4), bar (4), them (4), acharya (4), manoj (4), all (4), 2020 (4), prefil (4), adobe (4), some (3), you (3), erdos (3), only (3), better (3), type (3), prediction (3), pattern (3), recognition (3), open (3), ended (3), results (3), article (3), first (3), been (3), proposed (3), current (3), evaluation (3), inlg (3), natural (3), simple (3), these (3), analysis (3), iccv (3), project (3), page (3), categories (3), via (3), charts (3), aaai (3), artificial (3), intelligence (3), recent (3), systems (3), toward (3), universal (3), domains (3), not (3), efficient (3), bimodal (3), fusion (3), novel (3), demonstrate (3), neural (3), network (3), available (3), started (3), may (3), scientist (3), lineage (2), number (2), from (2), david (2), hilbert (2), link (2), four (2), misc (2), capable (2), images (2), framework (2), when (2), combined (2), model (2), achieves (2), time (2), benchmark (2), cviu (2), many (2), problem (2), particular (2), discuss (2), ability (2), train (2), then (2), possible (2), yousefhussien (2), mohammed (2), international (2), short (2), training (2), performance (2), baseline (2), including (2), one (2), most (2), difficult (2), different (2), over (2), into (2), given (2), make (2), study (2), how (2), attention (2), others (2), work (2), large (2), other (2), cannot (2), tests (2), unlike (2), perform (2), baselines (2), task (2), memory (2), advancement (2), require (2), relation (2), networks (2), method (2), used (2), focuses (2), second (2), test (2), good (2), should (2), manner (2), across (2), comparison (2), features (2), prospects (2), preprint (2), grounded (2), tasks (2), rather (2), winter (2), applications (2), wacv (2), cqa (2), where (2), must (2), learns (2), embeddings (2), your (2), prevent (2), catastrophic (2), forgetting (2), hayes (2), tyler (2), under (2), machine (2), incrementally (2), replay (2), incremental (2), jul (2), web (2), aws (2), proposal (2), demo (2), summer (2), intern (2), jun (2), feb (2), organizing (2), workshop (2), shortcomings (2), sivl (2), nov (2), successfully (2), defended (2), develop (2), robust (2), interested (2), right (2), what, follows, long, winded, collaboration, hunting, deny, facts, advisor, advisors, gets, there, follow, eventually, encounter, really, big, shot, names, talk, standing, shoulder, giants, dirichlet, lagrange, poisson, fourier, laplace, bertrand, russell, norbert, weiner, impressive, academic, paul, pavel, valtr, kostas, danilidis, kafle2016answer, build, system, text, based, known, key, insight, predict, form, formulate, solution, bayesian, discriminative, publication, daquar, coco, visual7w, kafle2017visual, since, release, 2014, additional, released, critically, examine, terms, formulation, metrics, limitations, regard, their, properly, assess, exhaustively, finally, directions, kafle2017data, generation, describe, means, producing, show, increased, pronounced, increase, remain, problems, kafle2017analysis, analyzing, comparing, notoriously, opaque, analyze, contains, million, organized, meaningless, schemes, compensate, represented, types, easier, strengths, weaknesses, experiments, establish, helps, certain, determine, explain, mlp, surpass, mcb, simply, easy, kafle2018dvqa, effective, way, humans, convey, information, each, today, parse, fail, faced, minor, variations, appearance, present, aspects, requires, processing, words, answers, unique, poorly, strong, considerably, serves, important, proxy, several, critical, abilities, such, handle, dynamic, out, vocabulary, oov, labels, acharya2019tallyqa, association, object, detection, involve, relationships, between, objects, attribute, identification, created, world, largest, uses, region, proposals, lets, efficiently, high, resolution, imagery, yields, compared, howmany, shrestha2019ramen, code, coming, soon, split, camps, synthetic, few, tested, compare, five, eight, covering, fair, standardized, much, they, use, same, vocabularies, etc, find, generalize, address, rivals, exceeds, kafle2019challenges, 1904, 09317, frontiers, computation, often, evaluating, progress, ideally, plethora, capabilities, integrate, however, behaving, turing, studies, demonstrated, achieving, through, flaws, procedures, affairs, outline, path, forward, kafle2020answering, pages, 1498, 1507, newly, pie, line, graphs, called, parallel, recurrent, fusing, intelligently, aggregates, learned, despite, its, simplicity, greatly, surpasses, human, figureqa, additionally, reconstruct, tables, asking, series, hayes2019remind, 1910, 02509, lifelong, agent, updated, knowledge, instead, having, distinct, deployment, phases, convolutional, prior, has, enabled, storing, raw, intensive, ideal, embedded, agents, tensor, quantization, enables, tensors, trained, streaming, meaning, example, batches, containing, multiple, classes, class, imagenet, generality, pioneering, multi, modal, readily, done, denotes, equal, contribution, publications, neuromorphic, perception, laboratory, 2015, amazon, services, grant, awarded, 15k, worth, credits, launched, added, well, online, apr, application, scholarship, deep, school, survey, titled, recognized, outstanding, reviewer, eccv, july, thesis, aka, candidacy, edition, naacl, jan, will, microsoft, redmond, describing, appear, sept, dissertation, timeline, events, overarching, goal, developing, specifically, exploring, capacity, reasons, currently, recently, completed, worked, rochester, institute, technology, chester, carlson, center, imaging, science, kushalkafle, gmail, dot, com, home, personal, homepage,

Text of the page (random words):
kushal kafle kushal kafle personal homepage kushal kafle home about recent research misc c v kushal kafle research scientist at adobe research kushalkafle at gmail dot com about me i am currently working at adobe research as a research scientist i recently completed my ph d in chester f carlson center for imaging science at rochester institute of technology where i worked with dr christopher kanan the overarching goal of my research is to develop develop robust vision and language models i am interested in developing novel data and algorithms for language grounded visual understanding and specifically interested in exploring models that not only demonstrate robust visual reasoning capacity but are also right for the right reasons timeline events mar 2020 started working at adobe research as a research scientist feb 2020 i successfully defended my dissertation sept 2019 our paper describing a novel state of the art chart question answering algorithm was accepted to appear at wacv mar 2019 i will be working as a research intern at microsoft research redmond this summer mar 2019 our new paper answer them all toward universal visual question answering models was accepted to cvpr 2019 jan 2019 i am co organizing second edition of workshop on shortcomings in vision and language sivl in naacl 2019 nov 2018 i successfully defended my thesis proposal aka advancement to candidacy nov 2018 our new paper tallyqa answering complex counting questions was accepted to aaai 2019 july 2018 i am co organizing workshop on shortcomings in vision and language sivl in eccv 2018 may 2018 i was recognized as an outstanding reviewer for cvpr 2018 feb 2018 our new paper dvqa understanding data visualizations via question answering was accepted to cvpr 2018 jul 2017 our new paper an analysis of visual question answering was accepted to iccv 2017 also available on arxiv jun 2017 our short paper data augmentation for visual question answering was accepted to inlg 2017 jun 2017 visual question answering vqa survey paper titled visual question answering datasets algorithms and future challenges was accepted to computer vision and image understanding journal cviu also available on arxiv may 2017 started working as research intern at adobe research may 2016 my application to deep learning summer school 2016 was accepted with scholarship apr 2016 launched online web demo for visual question answering new added demo for dvqa as well mar 2016 our paper answer type prediction for visual question answering was accepted to cvpr 2016 mar 2016 our amazon web services aws grant proposal was accepted awarded 15k worth aws credits jul 2015 started working at machine and neuromorphic perception laboratory under dr christopher kanan publications remind your neural network to prevent catastrophic forgetting tyler l hayes kushal kafle robik shrestha manoj acharya and christopher kanan denotes equal contribution in lifelong machine learning an agent must be incrementally updated with new knowledge instead of having distinct train and deployment phases for incrementally training convolutional neural network models prior work has enabled replay by storing raw images but this is memory intensive and not ideal for embedded agents here we propose remind a tensor quantization approach that enables efficient replay with tensors unlike other methods remind is trained in a streaming manner meaning it learns one example at a time rather than in large batches containing multiple classes our approach achieves state of the art results for incremental class learning on the imagenet 1k dataset we demonstrate remind s generality by pioneering multi modal incremental learning for visual question answering vqa which cannot be readily done with comparison models under review available on arxiv 2019 paper bibtex article hayes2019remind title remind your neural network to prevent catastrophic forgetting author hayes tyler l and kafle kushal and shrestha robik and acharya manoj and kanan christopher journal arxiv preprint arxiv 1910 02509 year 2019 answering questions about data visualizations using efficient bimodal fusion kushal kafle robik shrestha scott cohen brian price and christopher kanan chart question answering cqa is a newly proposed visual question answering vqa task where an algorithm must answer questions about data visualizations e g bar charts pie charts and line graphs here we propose a novel cqa algorithm called parallel recurrent fusion of image and language prefil prefil first learns bimodal embeddings by fusing question and image features and then intelligently aggregates these learned embeddings to answer the given question despite its simplicity prefil greatly surpasses state of the art systems and human baselines on both the figureqa and dvqa datasets additionally we demonstrate that prefil can be used to reconstruct tables by asking a series of questions about a chart ieee winter conference on applications of computer vision wacv 2020 paper bibtex inproceedings kafle2020answering title answering questions about data visualizations using efficient bimodal fusion author kafle kushal and shrestha robik and cohen scott and price brian and kanan christopher booktitle the ieee winter conference on applications of computer vision pages 1498 1507 year 2020 challenges and prospects in vision and language research kushal kafle robik shrestha and christopher kanan language grounded image understanding tasks have often been proposed as a method for evaluating progress in artificial intelligence ideally these tasks should test a plethora of capabilities that integrate computer vision reasoning and natural language understanding however rather than behaving as visual turing tests recent studies have demonstrated state of the art systems are achieving good performance through flaws in datasets and evaluation procedures we review the current state of affairs and outline a path forward frontiers in artificial intelligence language and computation accepted 2019 paper bibtex article kafle2019challenges title challenges and prospects in vision and language research author kafle kushal and shrestha robik and kanan christopher journal arxiv preprint arxiv 1904 09317 year 2019 answer them all toward universal visual question answering models robik shrestha kushal kafle and christopher kanan visual question answering vqa research is split into two camps the first focuses on vqa datasets that require natural image understanding and the second focuses on synthetic datasets that test reasoning a good vqa algorithm should be capable of both but only a few vqa algorithms are tested in this manner we compare five state of the art vqa algorithms across eight vqa datasets covering both domains to make the comparison fair all of the models are standardized as much as possible e g they use the same visual features answer vocabularies etc we find that methods do not generalize across the two domains to address this problem we propose a new vqa algorithm that rivals or exceeds the state of the art for both domains ieee conference on computer vision and pattern recognition cvpr 2019 paper code coming soon bibtex inproceedings shrestha2019ramen title answer them all toward universal visual question answering models author shrestha robik and kafle kushal and kanan christopher booktitle cvpr year 2019 tallyqa answering complex counting questions manoj acharya kushal kafle and christopher kanan most counting questions in visual question answering vqa datasets are simple and require no more than object detection here we study algorithms for complex counting questions that involve relationships between objects attribute identification reasoning and more to do this we created tallyqa the world s largest dataset for open ended counting we propose a new algorithm for counting that uses relation networks with region proposals our method lets relation networks be efficiently used with high resolution imagery it yields state of the art results compared to baseline and recent systems on both tallyqa and the howmany qa benchmark association for the advancement of artificial intelligence aaai 2019 paper project page bibtex inproceedings acharya2019tallyqa title tallyqa answering complex counting questions author acharya manoj and kafle kushal and kanan christopher booktitle aaai year 2019 dvqa understanding data visualizations via question answering kushal kafle brian price scott cohen and christopher kanan bar charts are an effective way for humans to convey information to each other but today s algorithms cannot parse them existing methods fail when faced with minor variations in appearance here we present dvqa a dataset that tests many aspects of bar chart understanding in a question answering framework unlike visual question answering vqa dvqa requires processing words and answers that are unique to a particular bar chart state of the art vqa algorithms perform poorly on dvqa and we propose two strong baselines that perform considerably better dvqa also serves as an important proxy task for several critical ai abilities such as attention working memory visual reasoning and an ability to handle dynamic and out of vocabulary oov labels ieee conference on computer vision and pattern recognition cvpr 2018 paper project page bibtex inproceedings kafle2018dvqa title dvqa understanding data visualizations via question answering author kafle kushal and price brian and cohen scott and kanan christopher booktitle cvpr year 2018 an analysis of visual question answering algorithms kushal kafle and christopher kanan analyzing and comparing different vqa algorithms is notoriously opaque and difficult in this paper we analyze existing vqa algorithms using a new dataset that contains over 1 6 million questions organized into 12 different categories including questions that are meaningless for a given image we also propose new evaluation schemes that compensate for over represented question types and make it easier to study the strengths and weaknesses of algorithms our experiments establish how attention helps certain categories more than others determine which models work better than others and explain how simple models e g mlp can surpass more complex models mcb by simply learning to answer large easy question categories the ieee international conference on computer vision iccv 2017 paper project page bibtex inproceedings kafle2017analysis title an analysis of visual question answering algorithms author kafle kushal and kanan christopher booktitle iccv year 2017 data augmentation for visual question answering kushal kafle mohammed yousefhussien and christopher kanan in this short paper we describe two simple means of producing new training data for visual question answering algorithms data augmentation using these methods show increased performance in both baseline and state of the art vqa algorithms including pronounced increase in counting questions which remain one of the most difficult problems in vqa international natural language generation conference inlg 2017 paper bibtex inproceedings kafle2017data title data augmentation for visual question answering author kafle kushal and yousefhussien mohammed and kanan christopher booktitle inlg year 2017 visual question answering datasets algorithms and future challenges kushal kafle and christopher kanan since the release of the first vqa dataset in 2014 additional datasets have been released and many algorithms have been proposed in this review we critically examine the current state of vqa in terms of problem formulation existing datasets evaluation metrics and algorithms in particular we discuss the limitations of current datasets with regard to their ability to properly train and assess vqa algorithms we then exhaustively review existing algorithms for vqa finally we discuss possible future directions for vqa and image understanding research computer vision and image understanding cviu paper bibtex article kafle2017visual title visual question answering datasets algorithms and future challenges author kafle kushal and kanan christopher journal computer vision and image understanding year 2017 answer type prediction for visual question answering kushal kafle and christopher kanan in this paper we build a system capable of answering open ended text based questions about images which is known as visual question answering vqa our approach s key insight is that we can predict the form of the answer from the question we formulate our solution in a bayesian framework when our approach is combined with a discriminative model the combined model achieves state of the art results at the time of publication on four benchmark datasets for open ended vqa daquar coco qa the vqa dataset and visual7w ieee conference on computer vision and pattern recognition cvpr 2016 paper bibtex inproceedings kafle2016answer title answer type prediction for visual question answering author kafle kushal and kanan christopher booktitle cvpr year 2016 misc i have an erdos number of four what follows is some long winded collaboration lineage hunting but you can t deny the facts i have an erdos number of 4 kushal kafle christopher kanan kostas danilidis pavel valtr paul erdos here s the link i have some impressive academic lineage norbert weiner is my grand grand advisor david hilbert and bertrand russell are my grand grand grand advisors it only gets better from there if you follow david hilbert you eventually encounter some really big shot names laplace fourier poisson lagrange dirichlet talk about standing on the shoulder of giants here s the link