Meta tags:
description=;
author=;

Headings (most frequently used words):

news,

Text of the page (most frequently used words):
the (30), paper (18), and (15), for (15), our (15), accepted (14), kate (10), workshop (10), domain (10), learning (10), adaptation (9), was (9), from (8), are (7), deep (7), vision (6), with (6), slides (6), detection (6), 2015 (6), saenko (5), 2017 (5), task (5), object (5), boston (5), iccv (5), group (5), 2016 (5), nips (4), language (4), cvpr (4), dataset (4), available (4), titled (4), talk (4), here (4), new (4), has (4), alignment (4), eccv (4), organizing (3), will (3), tutorial (3), transfer (3), computer (3), now (3), models (3), datasets (3), papers (3), university (3), video (3), action (3), prof (3), research (3), source (2), knowledge (2), bmvc (2), recent (2), virtual (2), domains (2), large (2), scale (2), data (2), science (2), which (2), machine (2), intelligence (2), school (2), december (2), multi (2), return (2), frustratingly (2), easy (2), extended (2), abstract (2), won (2), adaptive (2), two (2), captioning (2), categories (2), coral (2), correlation (2), moving (2), question (2), been (2), more (2), c3d (2), end (2), 2018 (2), distribution (2), using (2), adversarial (2), released (2), github (2), navigation (2), 2019 (2), oral (2), copyright, twitter, held, 2011, grenada, spain, integrating, giving, dong, ivor, tsang, 2012, applications, chairing, located, eccv2014, transferring, adapting, that, achieve, state, art, office, download, decaf, features, 2014, see, also, reality, fast, detectors, real, category, library, may, 30th, open, conference, caffe, june, 11th, future, present, initial, generating, cad, lecture, took, place, petersburg, russia, part2, part1, microsoft, four, some, spotlights, 12th, montreal, canada, trends, perspectives, aaai, best, prize, mit, march, 15th, orals, natural, retrieval, compositional, describing, novel, without, paired, training, assistant, professor, position, this, summer, along, her, stay, tuned, website, department, icip, fine, coarse, low, res, image, classification, accv, combining, texture, shape, cues, minimal, supervision, spotlight, ask, attend, answer, exploring, guided, spatial, attention, visual, answering, honorable, mention, hosting, england, necv, perception, intelligent, transportation, systems, have, announced, october, join, find, out, visda, challenge, winners, corl, robots, grasp, reason, neural, modules, accpeted, wiclr, stable, dual, distance, code, repository, iclr, dropout, regularization, introducing, high, women, world, artificial, several, uncovering, bias, explainable, based, emnlp, strong, weak, iccv2019, moment, matching, icml2019, long, agnostic, disentangled, representations, contains, 345, about, million, images, far, largest, cross, domainnet, limited, labels, pdf, news, phishing, emails, being, sent, name, offer, fake, internships, not, respond, these, messages, learn, scam, alert, contact, projects, teaching, publications, people, toggle,

Text of the page (random words):
prof saenko s research group toggle navigation prof saenko s research group people publications teaching research projects github contact scam alert phishing emails are being sent using prof saenko s name to offer fake internships do not respond to these messages learn more news slides pdf from kate saenko s talk at the iccv 2019 tutorial on learning with limited labels our dataset domainnet has now been released the dataset contains 6 domains 345 categories and about 0 6 million images which is by far the largest cross domain dataset our paper domain agnostic learning with disentangled representations was accepted to icml2019 as a long oral paper our paper moment matching for multi source domain adaptation was accepted to iccv2019 as an oral paper our paper strong weak distribution alignment for adaptive object detection was accepted to cvpr 2019 several new papers on uncovering bias in captioning models eccv 18 emnlp 18 explainable ai bmvc 18 eccv 18 and language based navigation nips 18 introducing high school women to the world of artificial intelligence our paper adversarial dropout regularization was accepted to iclr 2018 code of the iccv 2017 paper r c3d for action detection in video is released in the group s github repository our paper stable distribution alignment using the dual of the adversarial distance was accpeted to wiclr 2018 two papers accepted to iccv 2017 learning to reason end to end neural modules and r c3d for action detection in video our paper on robots learning to grasp is accepted to corl 2017 the visda 2017 challenge winners have been announced on october 10 join us at the task cv workshop to find out more slides from kate s talk at the nips 2016 workshop on machine learning for intelligent transportation systems on december 9 domain adaptation for perception and action we are hosting the 2016 new england computer vision workshop necv at boston university our paper titled deep coral correlation alignment for deep domain adaptation has won the honorable mention paper of the task cv workshop at eccv 2016 our paper ask attend and answer exploring question guided spatial attention for visual question answering is accepted to eccv 2016 here is the video spotlight our paper combining texture and shape cues for object detection with minimal supervision was accepted to accv 16 our paper fine to coarse knowledge transfer for low res image classification was accepted to icip 16 moving to boston university kate has accepted an assistant professor position in the computer science department at boston university and will be moving this summer along with her group stay tuned for the new website deep coral correlation alignment for deep domain adaptation extended abstract two orals accepted to cvpr 2016 deep compositional captioning describing novel object categories without paired training data and natural language object retrieval slides from kate s mit talk on march 15th adaptive deep learning for vision and language our paper titled return of frustratingly easy domain adaptation extended abstract has won the best paper prize of the task cv workshop at iccv 2015 our paper titled return of frustratingly easy domain adaptation was accepted to aaai 16 our group is co organizing the transfer and multi task learning trends and new perspectives workshop at nips 2015 on december 12th 2015 in montreal canada four papers accepted to iccv 2015 here are some spotlights slides from kate s lecture at the microsoft machine learning and intelligence school which took place in st petersburg russia are available here part1 part2 we will present generating large scale datasets from 3d cad models at the workshop initial datasets are available here kate is co organizing the future of datasets in vision workshop at cvpr 2015 on june 11th 2015 in boston ma slides from my recent tutorial on the deep learning library caffe at the open data science conference on may 30th in boston large scale detection by adaptation 7k category detection models are now available our paper titled from virtual to reality fast adaptation of virtual object detectors to real domains was accepted to bmvc 2014 see also slides from a recent talk decaf features that achieve the state of the art on the office domain adaptation dataset are now available for download kate is co chairing the task cv workshop on transferring and adapting source knowledge in computer vision co located with eccv2014 kate will be giving a tutorial on domain transfer learning for vision applications at cvpr 2012 with dong xu and ivor tsang kate is co organizing the workshop on integrating language and vision held at nips 2011 in grenada spain twitter copyright kate saenko 2017