Meta tags:
author=Jon Barron;

Headings (most frequently used words):

-

Text of the page (most frequently used words):
and (20), the (19), 2021 (12), for (11), yang (11), xiao (11), pose (9), project (8), learning (8), code (8), 2020 (8), one (8), nbsp (8), 2019 (7), object (7), accepted (7), from (6), estimation (6), page (6), paper (6), renaud (5), marlet (5), improve (4), image (4), aware (4), objects (4), with (4), few (4), shot (4), viewpoint (4), 2018 (3), research (3), are (3), vision (3), neurips (3), iclr (3), network (3), color (3), segmentation (3), images (3), data (3), deep (3), unseen (3), mathieu (3), aubry (3), bayes (3), eccv (3), detection (3), classes (3), similarity (3), contrastive (3), phd (3), dixite (2), city (2), construction (2), site (2), around (2), which (2), thesis (2), computer (2), spring (2), wang (2), decoding (2), could (2), between (2), performance (2), histological (2), isbi (2), augmentation (2), method (2), model (2), arbitrary (2), bmvc (2), xuchong (2), qiu (2), empirical (2), meta (2), shen (2), shell (2), occlusion (2), better (2), spotlight (2), that (2), wild (2), use (2), unlabeled (2), videos (2), propose (2), based (2), iccv (2), vincent (2), lepetit (2), yuming (2), graph (2), retrieval (2), class (2), agnostic (2), supervised (2), oral (2), 3dv (2), paris (2), last (2), degree (2), university (2), this, website, takes, template, here, initiated, part, french, initiative, answer, challenges, sustainable, focuses, acts, hub, developing, pluridisciplinar, scenarios, automated, digitised, processes, used, construct, maintain, tomorrow, future, machine, robotic, manipulators, teaching, assistance, enpc, reviewing, service, qiuyi, achieved, exploiting, structure, imposed, communication, protocol, packet, headers, icassp, cedric, adjih, michel, kieffer, hand, header, assisted, hélène, burdin, thomas, bornschlögl, françoise, bernerd, emilie, warrick, transfer, training, samples, human, skin, while, labeled, not, sufficient, thérèse, baldeweck, santiago, velasco, forero, etienne, decencière, new, using, cad, input, generalization, ability, towards, seen, pierre, alain, langlois, shape, revisit, hierarchical, formulations, multi, task, can, naturally, applied, andreas, damianou, guillaume, obozinski, neil, lawrence, pablo, moreno, synthetic, gradients, sharper, boundaries, depth, maps, chaohui, pixel, pair, relationship, map, p2orm, formulation, inference, application, popose, simple, yet, effective, framework, outperforms, state, art, methods, both, tasks, explore, instance, global, optimization, approach, video, discovery, segment, given, initial, query, its, top, candidates, module, dubbed, subgraph, refiner, ssr, othman, sbai, ranking, transductive, classification, train, direct, estimator, way, sharing, weights, across, all, introduce, has, three, main, ingredients, pre, trained, self, contrast, features, augmentations, iii, loss, posecontrast, started, covid, arrives, france, two, papers, poster, have, successfully, defended, news, year, student, also, work, closely, received, master, signal, processing, bachelor, optical, electronic, information, update, nov, linkedin, google, scholar, github, email, huazhong, science, technology, sacaly, spent, time, l2s, centralesupelec, cmm, mines, paristech, interests, centered, particular, imagine,

Text of the page (random words):
yang xiao yang xiao 肖洋 i am a last year phd student at imagine supervised by renaud marlet i also work closely with mathieu aubry and vincent lepetit my research interests are centered around deep learning computer vision and object pose estimation in particular i ve spent time at cmm of mines paristech and l2s of centralesupelec i received my master degree in signal and image processing from university paris sacaly and my bachelor degree in optical and electronic information from huazhong university of science and technology last update nov 2021 email nbsp nbsp cv nbsp nbsp github nbsp nbsp google scholar nbsp nbsp linkedin news 10 2021 i have successfully defended my phd thesis 10 2021 one paper is accepted oral at 3dv 2021 09 2021 one paper is accepted at neurips 2021 07 2021 one paper is accepted at iccv 2021 07 2020 two papers one spotlight and one poster are accepted at eccv 2020 03 2020 covid 19 arrives in france 01 2020 one paper is accepted at iclr 2020 07 2019 one paper is accepted at bmvc 2019 04 2019 one paper is accepted at isbi 2019 10 2018 i started my phd in paris research posecontrast class agnostic object viewpoint estimation in the wild with pose aware contrastive learning yang xiao yuming du renaud marlet 3dv 2021 oral project page code we train a direct pose estimator in a class agnostic way by sharing weights across all object classes and we introduce a contrastive learning method that has three main ingredients i the use of pre trained self supervised contrast based features ii pose aware data augmentations iii a pose aware contrastive loss re ranking for image retrieval and transductive few shot classification xi shen yang xiao shell xu hu othman sbai mathieu aubry neurips 2021 project page code given an initial similarity graph between a query and its top candidates in image retrieval we propose a module dubbed subgraph similarity refiner ssr to improve the similarity graph learning to better segment objects from unseen classes with unlabeled videos yuming du yang xiao vincent lepetit iccv 2021 project page code we explore the use of unlabeled videos to improve the performance of instance segmentation model on unseen classes and propose a global optimization approach for video based object discovery few shot object detection and viewpoint estimation for objects in the wild yang xiao renaud marlet eccv 2020 project page code detection code viewpoint we popose a simple yet effective framework for few shot object detection and few shot viewpoint estimation that outperforms state of the art methods on both tasks pixel pair occlusion relationship map p2orm formulation inference application xuchong qiu yang xiao chaohui wang renaud marlet eccv 2020 spotlight project page code sharper occlusion boundaries and better depth maps from color images empirical bayes meta learning with synthetic gradients shell xu hu xi shen yang xiao pablo moreno neil lawrence guillaume obozinski andreas damianou iclr 2020 code we revisit the hierarchical bayes and empirical bayes formulations for multi task learning which can naturally be applied to meta learning pose from shape deep pose estimation for arbitrary 3d objects yang xiao xuchong qiu pierre alain langlois mathieu aubry renaud marlet bmvc 2019 project page code by using image and cad model at network input and pose aware data augmentation we improve object pose estimation generalization ability towards arbitrary objects seen unseen a new color augmentation method for deep learning segmentation of histological images yang xiao etienne decencière santiago velasco forero hélène burdin thomas bornschlögl françoise bernerd emilie warrick thérèse baldeweck isbi 2019 color transfer between training samples could improve performance in the segmentation of histological images of human skin while the labeled data is not sufficient hand header assisted network decoding qiuyi wang yang xiao michel kieffer cedric adjih icassp 2018 network decoding could be achieved by exploiting the structure imposed by the communication protocol on the packet headers service reviewing for neurips iclr teaching assistance for computer vision at enpc spring 2019 spring 2021 thesis project machine vision for robotic manipulators initiated in 2018 dixite is part of i site future a french initiative to answer the challenges of the sustainable city the dixite project focuses on the construction site it acts as a hub for developing pluridisciplinar research around construction scenarios in which automated and digitised processes are used to construct and maintain the city of tomorrow this website takes the template from here