Meta tags:
author=Sai Raj Kishore Perla;

Headings (most frequently used words):

-

Text of the page (most frequently used words):
the (116), and (98), for (39), image (27), sai (21), raj (21), kishore (21), perla (21), texture (21), pose (18), from (17), with (17), mesh (17), using (14), deep (14), our (13), framework (12), estimation (12), texturing (12), this (11), neural (11), occluded (11), code (10), network (10), year (10), are (10), that (10), conference (10), computer (10), training (9), 2019 (9), author (9), title (9), relu (9), activation (9), learning (9), layers (9), bibtex (9), abstract (9), partha (9), vision (9), novel (9), zhang (9), hao (9), detection (8), model (8), single (8), existing (8), bhunia (8), kumar (8), das (8), stage (8), datasets (8), mahdavi (8), amiri (8), ali (8), nbsp (8), input (7), based (7), methods (7), results (7), arxiv (7), roy (7), pratim (7), images (7), which (7), adaptive (7), pedestrian (7), segmentation (7), asia (7), prof (6), github (6), over (6), article (6), function (6), journal (6), doi (6), not (6), also (6), retrieval (6), ayan (6), ieee (6), first (6), information (6), multi (6), recognition (6), word (6), pedestrians (6), end (6), diffusion (6), richard (6), research (6), trained (5), use (5), speech (5), swish (5), international (5), advances (5), pages (5), view (5), has (5), been (5), used (5), work (5), fts (5), performance (5), experimental (5), synthesis (5), hashing (5), booktitle (5), second (5), propose (5), entire (5), text (5), cluenet (5), bhattacharya (5), ujjwal (5), annotations (5), geometry (5), built (4), time (4), large (4), dataset (4), during (4), developed (4), generative (4), video (4), ijain (4), url (4), such (4), although (4), proposed (4), its (4), all (4), inproceedings (4), mukherjee (4), abhirup (4), problem (4), tsn (4), data (4), approach (4), state (4), art (4), processing (4), thumbnails (4), generate (4), any (4), even (4), low (4), scripts (4), adversarial (4), models (4), than (4), sudip (4), studies (4), situations (4), occlusions (4), further (4), visual (4), easi (4), tex (4), aware (4), acm (4), graphics (4), siggraph (4), https (4), objects (4), few (4), 2026 (4), real (3), character (3), level (3), predict (3), including (3), under (3), paper (3), cvpr (3), feature (3), technique (3), while (3), flatten (3), volume (3), number (3), functions (3), negative (3), values (3), through (3), called (3), study (3), recent (3), each (3), dfnns (3), same (3), guided (3), applications (3), scale (3), pre (3), train (3), intermediate (3), manner (3), help (3), new (3), user (3), thumbnail (3), generation (3), convolutions (3), aspect (3), various (3), resource (3), challenging (3), introduce (3), literature (3), strategies (3), afdm (3), features (3), well (3), task (3), estimate (3), two (3), where (3), segment (3), parts (3), 2020 (3), scenes (3), edge (3), sairajk (3), transfer (3), project (3), page (3), non (3), semantic (3), survey (3), review (3), sfu (3), lane (2), language (2), next (2), super (2), resolution (2), diverse (2), completed (2), attention (2), saliency (2), frame (2), interpolation (2), short (2), videos (2), improving (2), fine (2), enhancement (2), baseline (2), projects (2), hock (2), chieng (2), noorhaniza (2), wahid (2), ong (2), pauline (2), thresholded (2), like (2), intelligent (2), informatics (2), 2018 (2), 249 (2), org (2), essential (2), learn (2), complex (2), tasks (2), classification (2), widely (2), across (2), popular (2), however (2), representations (2), mnist (2), five (2), evaluation (2), best (2), overall (2), accuracy (2), there (2), other (2), pranay (2), winter (2), wacv (2), organization (2), efficient (2), have (2), similar (2), generates (2), binary (2), hash (2), enlarged (2), content (2), them (2), representation (2), finally (2), into (2), indicate (2), constrained (2), ghose (2), acoustics (2), signal (2), icassp (2), digital (2), ratio (2), global (2), context (2), gca (2), rpn (2), bounding (2), superior (2), ankan (2), handwriting (2), pattern (2), handwritten (2), spotting (2), variations (2), samples (2), therefore (2), much (2), extracted (2), better (2), enhanced (2), but (2), varying (2), map (2), improve (2), sarathi (2), british (2), machine (2), bmvc (2), about (2), current (2), significant (2), unsupervised (2), employs (2), visible (2), regions (2), these (2), here (2), make (2), kind (2), citypersons (2), coco (2), show (2), 9191147 (2), icip (2), wild (2), outdoor (2), instance (2), cases (2), heavy (2), wang (2), yizhi (2), transactions (2), proceedings (2), publisher (2), york (2), usa (2), 2024 (2), 1145 (2), com (2), present (2), conditioning (2), object (2), can (2), discrepancies (2), their (2), part (2), method (2), stable (2), adapter (2), optimization (2), details (2), vora (2), aditya (2), nag (2), sauradip (2), 2025 (2), controllable (2), annotated (2), space (2), labels (2), practical (2), both (2), eurographics (2), star (2), reports (2), forum (2), meshes (2), modeling (2), pipelines (2), systems (2), worked (2), indian (2), institute (2), webpage, template, adapted, jon, barron, classic, racing, game, nfs, underground, sequence, tensorflow, keras, collection, curation, packaged, easy, gui, internship, iiit, delhi, subramanyam, reproduced, improved, pytorch, 180, stars, pyramid, free, recursive, mid, matching, specialized, baselines, identity, preservation, reducing, drift, longer, sequences, ppo, tuning, pipeline, multichannel, quality, supervised, chime9, echi, pesq, ijain249, 26555, v4i2, http, index, php, perform, rectified, linear, unit, become, default, community, since, 2012, hard, zero, property, heavily, hindering, propagating, consequently, benefited, leverage, benefit, verify, evaluates, several, different, fully, connected, networks, depth, vary, eight, fair, configuration, settings, threshold, value, compared, improves, wider, slimmer, respectively, apart, noticed, converges, twice, fast, evaluated, elects, award, hung, bhunia2019texture, 609, 618, explosion, internet, facilitate, memory, none, works, address, mostly, because, lack, sufficiently, databases, addresses, developing, architecture, codes, takes, patch, outputs, injecting, newer, thus, signifies, encodes, learnt, specific, gathers, channel, wise, combines, progressive, dense, continuous, converted, individual, pairwise, label, patches, augmentation, alleviate, insufficient, experiments, three, public, superiority, kishore2019user, shuvozit, 1677, 1681, world, preview, size, unseen, high, precision, aggregation, modified, region, proposal, selectively, attend, aggregate, candidate, boxes, convolution, eliminates, difficulty, generating, ratios, filter, weights, dynamically, generated, techniques, oral, intl, conf, shovozit, bhunia_2019_cvpr, month, june, field, dealing, possessing, irregular, shapes, design, makes, necessary, extend, order, increase, very, difficult, comprises, preprocessing, seldom, sufficient, cover, possible, deformation, module, learns, ways, elastically, warp, scalable, inserted, between, alternatively, original, boosting, capability, highly, informative, rather, trivial, ones, test, meta, top, frameworks, only, extensive, latin, sparser, indic, record, sizes, observe, generalizes, regime, error, rates, scores, observed, kishore2019cluenet, 30th, helps, gather, activity, instant, behaviour, subject, useful, autonomous, vehicles, augmented, reality, surveillance, etc, available, still, remains, take, step, detect, clues, accurately, box, enclosing, uses, predictions, strategy, mask, additionally, 1446, 1450, 1109, icip40778, particularly, degrees, crowded, most, did, report, moreover, human, figures, provided, relevant, standard, turn, creates, difficulties, required, figure, humans, known, contains, does, include, towards, occlusion, tackle, employ, domain, adaptation, estimating, outperforms, sota, reasonable, benchmark, perla2024easitex, articleno, 3658222, judicious, seamlessly, rgb, given, assume, belong, category, they, proportions, aims, rectify, generator, edges, describing, controlnet, textures, respect, underlying, without, inversion, quickly, personalize, concept, falls, capturing, faithfully, demonstrate, efficiency, effectiveness, coined, preserving, respecting, perla2025asia, papers, 3757377, 3763821, enables, possibly, describable, easier, collect, less, demanding, annotate, more, precise, potentially, ambiguous, descriptions, leverages, rich, priors, segmentations, when, target, differ, significantly, structure, optimize, token, tune, cross, correspondence, loss, inference, renderings, fuse, via, voting, refine, noise, back, onto, provides, generalizable, solution, outperforming, noticeable, margin, quantitative, qualitative, evaluations, 3dv, nectar, track, perla2026neuralmeshtexsurvey, e70392, 1111, cgf, 70392, plays, vital, role, determining, realism, approaches, radiance, fields, gaussian, splatting, produce, textured, assets, directly, polygonal, remain, core, animation, effects, gaming, continues, active, area, comprehensive, covering, completion, summarize, key, foundations, mapping, differentiable, rendering, then, organize, unified, taxonomy, spanning, early, gan, modern, analyze, common, architectures, supervision, protocols, discuss, emerging, commercial, open, challenges, together, insights, provide, structured, perspective, landscape, guide, future, developments, graph, zhuo, ning, negar, hassanpour, bach, blend, composition, harmonization, twitter, linkedin, google, scholar, email, lies, intersection, focus, understanding, multimodal, before, joining, production, analytics, earlier, bachelor, problems, technology, iit, roorkee, statistical, isi, kolkata, staqu, technologies, senior, engineer, phd, student, advised, master, simon, fraser, university,

Text of the page (random words):
ticle perla2026neuralmeshtexsurvey title advances in neural 3d mesh texturing a survey author perla sai raj kishore and zhang hao and mahdavi amiri ali journal eurographics star state of the art reports computer graphics forum pages e70392 year 2026 doi https doi org 10 1111 cgf 70392 url https sairajk github io neural mesh texturing asia adaptive 3d segmentation using few image annotations sai raj kishore perla aditya vora sauradip nag ali mahdavi amiri hao richard zhang siggraph asia 2025 3dv nectar track 2026 abstract code arxiv project page bibtex we introduce asia adaptive 3d segmentation using few image annotations a novel framework that enables segmentation of possibly non semantic and non text describable parts in 3d our segmentation is controllable through a few user annotated in the wild images which are easier to collect than multi view images less demanding to annotate than 3d models and more precise than potentially ambiguous text descriptions our method leverages the rich priors of text to image diffusion models such as stable diffusion sd to transfer segmentations from image space to 3d even when the annotated and target objects differ significantly in geometry or structure during training we optimize a text token for each segment and fine tune our model with a novel cross view part correspondence loss at inference we segment multi view renderings of the 3d mesh fuse the labels in uv space via voting refine them with our novel noise optimization technique and finally map the uv labels back onto the mesh asia provides a practical and generalizable solution for both semantic and non semantic 3d segmentation tasks outperforming existing methods by a noticeable margin in both quantitative and qualitative evaluations article perla2025asia title asia adaptive 3d segmentation using few image annotations author perla sai raj kishore and vora aditya and nag sauradip mahdavi amiri ali and zhang hao journal siggraph asia conference papers publisher acm new york ny usa year 2025 doi 10 1145 3757377 3763821 url https github com sairajk asia easi tex edge aware mesh texturing from single image sai raj kishore perla yizhi wang ali mahdavi amiri hao richard zhang acm transactions on graphics proceedings of siggraph 2024 abstract code arxiv project page bibtex we present a novel approach for single image mesh texturing which employs a diffusion model with judicious conditioning to seamlessly transfer an object s texture from a single rgb image to a given 3d mesh object we do not assume that the two objects belong to the same category and even if they do there can be significant discrepancies in their geometry and part proportions our method aims to rectify the discrepancies by conditioning a pre trained stable diffusion generator with edges describing the mesh through controlnet and features extracted from the input image using ip adapter to generate textures that respect the underlying geometry of the mesh and the input texture without any optimization or training we also introduce image inversion a novel technique to quickly personalize the diffusion model for a single concept using a single image for cases where the pre trained ip adapter falls short in capturing all the details from the input image faithfully experimental results demonstrate the efficiency and effectiveness of our edge aware single image mesh texturing approach coined easi tex in preserving the details of the input texture on diverse 3d objects while respecting their geometry article perla2024easitex title easi tex edge aware mesh texturing from single image author perla sai raj kishore and wang yizhi and mahdavi amiri ali and zhang hao journal acm transactions on graphics proceedings of siggraph publisher acm new york ny usa year 2024 volume 43 number 4 articleno 40 doi 10 1145 3658222 url https github com sairajk easi tex an end to end framework for pose estimation of occluded pedestrians sai raj kishore perla sudip das ujjwal bhattacharya international conference on image processing icip 2020 abstract bibtex pose estimation in the wild is a challenging problem particularly in situations of i occlusions of varying degrees and ii crowded outdoor scenes most of the existing studies of pose estimation did not report the performance in similar situations moreover pose annotations for occluded parts of the human figures have not been provided in any of the relevant standard datasets which in turn creates further difficulties to the required studies for pose estimation of the entire figure for occluded humans well known pedestrian detection datasets such as citypersons contains samples of outdoor scenes but it does not include pose annotations here we propose a novel multi task framework for end to end training towards the entire pose estimation of pedestrians including in situations of any kind of occlusion to tackle this problem we make use of a pose estimation dataset ms coco and employ unsupervised adversarial instance level domain adaptation for estimating the entire pose of occluded pedestrians the experimental studies show that the proposed framework outperforms the sota results for pose estimation instance segmentation and pedestrian detection in cases of heavy occlusions ho and reasonable heavy occlusions r ho on the two benchmark datasets inproceedings 9191147 author das sudip and perla sai raj kishore and bhattacharya ujjwal booktitle ieee international conference on image processing icip title an end to end framework for pose estimation of occluded pedestrians year 2020 pages 1446 1450 doi 10 1109 icip40778 2020 9191147 cluenet a deep framework for occluded pedestrian pose estimation sai raj kishore perla sudip das partha sarathi mukherjee ujjwal bhattacharya british machine vision conference bmvc 2019 abstract bibtex pose estimation of a pedestrian helps to gather information about the current activity or the instant behaviour of the subject such information is useful for autonomous vehicles augmented reality video surveillance etc although a large volume of pedestrian detection studies are available in the literature detection of the same in situations of significant occlusions still remains a challenging task in this work we take a step further to propose a novel deep learning framework called cluenet to detect as well as estimate the entire pose of occluded pedestrians in an unsupervised manner cluenet is a two stage framework where the first stage generates visual clues for the second stage to accurately estimate the pose of occluded pedestrians the first stage employs a multi task network to segment the visible parts and predict a bounding box enclosing the visible and occluded regions for each pedestrian the second stage uses these predictions from the first stage for pose estimation here we propose a novel strategy called mask and predict to train our cluenet to estimate the pose even for occluded regions additionally we make use of various other training strategies to further improve our results the proposed work is first of its kind and the experimental results on citypersons and ms coco datasets show the superior performance of our approach over existing methods article kishore2019cluenet title cluenet a deep framework for occluded pedestrian pose estimation author perla sai raj kishore and das sudip and mukherjee partha sarathi and bhattacharya ujjwal booktitle 30th british machine vision conference bmvc year 2019 handwriting recognition in low resource scripts using adversarial learning ayan kumar bhunia abhirup das ankan kumar bhunia sai raj kishore perla partha pratim roy conference on computer vision and pattern recognition cvpr 2019 abstract code arxiv bibtex handwritten word recognition and spotting is a challenging field dealing with handwritten text possessing irregular and complex shapes the design of deep neural network models makes it necessary to extend training datasets in order to introduce variations and increase the number of samples word retrieval is therefore very difficult in low resource scripts much of the existing literature comprises preprocessing strategies which are seldom sufficient to cover all possible variations we propose an adversarial feature deformation module afdm that learns ways to elastically warp extracted features in a scalable manner the afdm is inserted between intermediate layers and trained alternatively with the original framework boosting its capability to better learn highly informative features rather than trivial ones we test our meta framework which is built on top of popular word spotting and word recognition frameworks and enhanced by afdm not only on extensive latin word datasets but also on sparser indic scripts we record results for varying sizes of training data and observe that our enhanced network generalizes much better in the low data regime the overall word error rates and map scores are observed to improve as well inproceedings bhunia_2019_cvpr author bhunia ayan kumar and das abhirup and bhunia ankan kumar and perla sai raj kishore and roy partha pratim title handwriting recognition in low resource scripts using adversarial learning booktitle ieee conference on computer vision and pattern recognition cvpr month june year 2019 user constrained thumbnail generation using adaptive convolutions sai raj kishore perla ayan kumar bhunia shovozit ghose partha pratim roy intl conf on acoustics speech and signal processing icassp 2019 oral abstract code arxiv bibtex thumbnails are widely used all over the world as a preview for digital images in this work we propose a deep neural framework to generate thumbnails of any size and aspect ratio even for unseen values during training with high accuracy and precision we use global context aggregation gca and a modified region proposal network rpn with adaptive convolutions to generate thumbnails in real time gca is used to selectively attend and aggregate the global context information from the entire image while the rpn is used to generate candidate bounding boxes for the thumbnail image adaptive convolution eliminates the difficulty of generating thumbnails of various aspect ratios by using filter weights dynamically generated from the aspect ratio information the experimental results indicate the superior performance of the proposed model 1 over existing state of the art techniques inproceedings kishore2019user title user constrained thumbnail generation using adaptive convolutions author perla sai raj kishore and bhunia ayan kumar and ghose shuvozit and roy partha pratim booktitle ieee international conference on acoustics speech and signal processing icassp pages 1677 1681 year 2019 organization ieee texture synthesis guided deep hashing for texture image retrieval ayan kumar bhunia sai raj kishore perla pranay mukherjee abhirup das partha pratim roy winter conference on applications of computer vision wacv 2019 abstract arxiv bibtex with the large scale explosion of images and videos over the internet efficient hashing methods have been developed to facilitate memory and time efficient retrieval of similar images however none of the existing works use hashing to address texture image retrieval mostly because of the lack of sufficiently large texture image databases our work addresses this problem by developing a novel deep learning architecture that generates binary hash codes for input texture images for this we first pre train a texture synthesis network tsn which takes a texture patch as input and outputs an enlarged view of the texture by injecting newer texture content thus it signifies that the tsn encodes the learnt texture specific information in its intermediate layers in the next stage a second network gathers the multi scale feature representations from the tsn s intermediate layers using channel wise attention combines them in a progressive manner to a dense continuous representation which is finally converted into a binary hash code with the help of individual and pairwise label information the new enlarged texture patches from the tsn also help in data augmentation to alleviate the problem of insufficient texture data and are used to train the second stage of the network experiments on three public texture image retrieval datasets indicate the superiority of our texture synthesis guided hashing approach over existing state of the art methods inproceedings bhunia2019texture title texture synthesis guided deep hashing for texture image retrieval author bhunia ayan kumar and perla sai raj kishore and mukherjee pranay and das abhirup and roy partha pratim booktitle ieee winter conference on applications of computer vision wacv pages 609 618 year 2019 organization ieee flatten t swish a thresholded relu swish like activation function for deep learning hock hung chieng noorhaniza wahid ong pauline sai raj kishore perla international journal of advances in intelligent informatics ijain 2018 best paper award abstract code arxiv bibtex activation functions are essential for deep learning methods to learn and perform complex tasks such as image classification rectified linear unit relu has been widely used and become the default activation function across the deep learning community since 2012 although relu has been popular however the hard zero property of the relu has heavily hindering the negative values from propagating through the network consequently the deep neural network has not been benefited from the negative representations in this work an activation function called flatten t swish fts that leverage the benefit of the negative values is proposed to verify its performance this study evaluates fts with relu and several recent activation functions each activation function is trained using mnist dataset on five different deep fully connected neural networks dfnns with depth vary from five to eight layers for a fair evaluation all dfnns are using the same configuration settings based on the experimental results fts with a threshold value t 0 20 has the best overall performance as compared with relu fts t 0 20 improves mnist classification accuracy by 0 13 0 70 0 67 1 07 and 1 15 on wider 5 layers slimmer 5 layers 6 layers 7 layers and 8 layers dfnns respectively apart from this the study also noticed that fts converges twice as fast as relu although there are other existing activation functions are also evaluated this study elects relu as the baseline activation function article ijain249 author hock chieng and noorhaniza wahid and ong pauline and sai raj kishore perla title flatten t swish a thresholded relu swish like activation function for deep learning journal international journal of advances in intelligent informatics volume 4 number 2 year 2018 pages 76 86 doi 10 26555 ijain v4i2 249 url http ijain org index php ijain article view 249 projects rl based speech enhancement developed a ppo based fine tuning pipeline for multichannel speech enhancement improving speech quality pesq by 5 3 over a supervised b...