Meta tags:
description=Ph.D. Candidate;

Headings (most frequently used words):

yuchen, fan, 范雨晨, bio, research, highlights, education, working, experiences, professional, activities, honors, and, awards, image, restoration, video, segmentation, speech, synthesis,

Text of the page (most frequently used words):
and (18), the (17), video (14), segmentation (12), for (10), scale (9), yuchen (9), image (8), fan (8), new (8), #restoration (7), paper (7), speaker (7), #research (6), speech (6), tts (6), youtube (6), challenge (5), computer (5), based (5), this (5), with (5), are (5), synthesis (5), dataset (5), winner (4), 2018 (4), 2020 (4), object (4), long (4), dnn (4), neural (4), networks (4), can (4), multiple (4), thomas (4), huang (4), our (4), task (4), wise (4), convolution (4), student (3), 1st (3), ntire (3), 2019 (3), large (3), 2014 (3), 2016 (3), engineering (3), intern (3), summer (3), university (3), illinois (3), modeling (3), term (3), from (3), speakers (3), propose (3), hidden (3), layers (3), yang (3), spatial (3), features (3), called (3), instance (3), tracking (3), method (3), code (3), invariance (3), scales (3), sparse (3), representation (3), sparsity (3), neurons (3), resolution (2), 2nd (2), reviewer (2), ieee (2), transactions (2), neurips (2), iccv (2), eccv (2), aaai (2), activities (2), labs (2), google (2), vision (2), electrical (2), present (2), urbana (2), champaign (2), yao (2), qian (2), frank (2), soong (2), contextual (2), utterance (2), not (2), recurrent (2), bidirectional (2), blstm (2), information (2), constraints (2), training (2), data (2), model (2), different (2), each (2), limited (2), quality (2), ning (2), linjie (2), liang (2), learning (2), temporal (2), tasks (2), end (2), vos (2), sequence (2), detection (2), videos (2), high (2), cnn (2), jiahui (2), ding (2), liu (2), inspired (2), proposed (2), computation (2), prof (2), 范雨晨 (2), asc14, cluster, competition, champion, 2017, nvidia, city, single, super, deblurring, honors, awards, journal, processing, tip, multimedia, conference, iclr, cvpr, wacv, workshop, organizer, professional, visiting, microsoft, asia, consultant, jump, trading, software, waymo, facebook, reality, working, experiences, bachelor, science, acm, honored, class, zhiyuan, college, 2010, shanghai, jiao, tong, education, feng, xie, interspeech, time, span, effect, still, easy, accommodate, due, intrinsic, feed, forward, nature, rnns, short, memory, cells, adopted, capture, correlation, occurrence, between, any, two, instants, parametric, trajectory, generated, rnn, fairly, smooth, dynamic, needed, lstm, lei, icassp, 2015, take, advantage, huge, amount, approach, general, where, same, shared, among, while, output, composed, dependent, nodes, explaining, target, further, transfer, resultant, synthesized, also, achieve, good, naturalness, similarity, multi, adaptation, jianchao, dingcheng, yue, brian, price, scott, cohen, critical, many, analysis, sequential, explore, largely, available, datasets, solve, problem, build, contains, 252, clips, categories, including, common, objects, human, named, goal, simultaneous, instances, facilitate, benchmark, vis, which, consists, 2883, category, label, set, 131k, masks, addition, novel, algorithm, masktrack, introduces, branch, mask, jointly, perform, simultaneously, show, that, properly, into, bring, significant, benefits, performance, shift, convolve, across, learns, dynamically, activate, aggregate, input, residual, building, block, order, exploit, yiqun, mei, yulun, zhang, yun, robustness, efficiency, coding, models, investigate, deep, structurally, enforces, upon, enables, saving, only, operating, non, zero, components, without, hurting, accuracy, meanwhile, magnify, dimensionality, capacity, negligible, additional, cost, highlights, interests, include, understanding, currently, fifth, year, advised, zhi, pei, bio, scholar, candidate, department, yuchenf4, dot, edu, email, homepage,

Text of the page (random words):
homepage yuchen fan 范雨晨 yuchen fan 范雨晨 ph d candidate department of electrical and computer engineering university of illinois at urbana champaign email yuchenf4 at illinois dot edu google scholar bio i am currently a fifth year ph d student advised by prof zhi pei liang and prof thomas s huang my research interests include image restoration video understanding and segmentation and speech research highlights image restoration neural sparse representation for image restoration yuchen fan jiahui yu yiqun mei yulun zhang yun fu ding liu thomas s huang neurips 2020 paper code inspired by the robustness and efficiency of sparse representation in sparse coding based image restoration models we investigate the sparsity of neurons in deep networks our method structurally enforces sparsity constraints upon hidden neurons sparsity in neurons enables computation saving by only operating on non zero components without hurting accuracy meanwhile our method can magnify representation dimensionality and model capacity with negligible additional computation cost scale wise convolution for image restoration yuchen fan jiahui yu ding liu thomas s huang aaai 2020 paper code we show that properly modeling scale invariance into neural networks can bring significant benefits to image restoration performance inspired from spatial wise convolution for shift invariance scale wise convolution is proposed to convolve across multiple scales for scale invariance the proposed scale wise convolution learns to dynamically activate and aggregate features from different input scales in each residual building block in order to exploit contextual information on multiple scales video segmentation video instance segmentation linjie yang yuchen fan ning xu iccv 2019 paper code dataset we present a new computer vision task named video instance segmentation the goal of this new task is simultaneous detection segmentation and tracking of instances in videos to facilitate research on this new task we propose a large scale benchmark called youtube vis which consists of 2883 high resolution youtube videos a 40 category label set and 131k high quality instance masks in addition we propose a novel algorithm called masktrack r cnn for this task our new method introduces a new tracking branch to mask r cnn to jointly perform the detection segmentation and tracking tasks simultaneously youtube vos sequence to sequence video object segmentation ning xu linjie yang yuchen fan jianchao yang dingcheng yue yuchen liang brian price scott cohen thomas s huang eccv 2018 paper dataset learning long term spatial temporal features are critical for many video analysis tasks end to end sequential learning to explore spatial temporal features for video segmentation is largely limited by the scale of available video segmentation datasets to solve this problem we build a new large scale video object segmentation dataset called youtube video object segmentation dataset youtube vos our dataset contains 3 252 youtube video clips and 78 categories including common objects and human activities speech synthesis multi speaker modeling and speaker adaptation for dnn based tts synthesis yuchen fan yao qian frank k soong lei he icassp 2015 paper the dnn based tts synthesis can not take advantage of huge amount of training data from multiple speakers we propose an approach to model multiple speakers tts with a general dnn where the same hidden layers are shared among different speakers while the output layers are composed of speaker dependent nodes explaining the target of each speaker we further transfer the hidden layers for a new speaker with limited training data and the resultant synthesized speech of the new speaker can also achieve a good quality in term of naturalness and speaker similarity tts synthesis with bidirectional lstm based recurrent neural networks yuchen fan yao qian feng long xie frank k soong interspeech 2014 paper long time span contextual effect in a speech utterance is still not easy to accommodate due to the intrinsic feed forward nature in dnn based modeling in this paper recurrent neural networks rnns with bidirectional long short term memory blstm cells are adopted to capture the correlation or co occurrence information between any two instants in a speech utterance for parametric tts synthesis the speech trajectory generated by the blstm rnn tts is fairly smooth and no dynamic constraints are needed education university of illinois at urbana champaign ph d of electrical and computer engineering 2016 present shanghai jiao tong university bachelor of computer science acm honored class zhiyuan college 2010 2014 working experiences facebook reality labs research intern summer 2020 waymo computer vision ml research intern summer 2019 google software engineering intern summer 2018 jump trading labs student consultant 2016 2018 microsoft research asia visiting 2014 2016 professional activities workshop organizer large scale video object segmentation challenge conference reviewer iclr neurips cvpr iccv eccv aaai wacv journal reviewer ieee transactions on image processing tip ieee transactions on multimedia honors and awards 2020 ntire video deblurring challenge winner 2nd 2019 ntire video restoration challenge winner 2nd 2018 ntire single image super resolution challenge winner 1st 2017 nvidia ai city challenge winner 1st asc14 student cluster competition champion 1st