Meta tags:
author=Alireza Heidari;
description=Personal website of Alireza Heidari, a computing science Ph.D. student working on computer vision, computer graphics, and machine learning. ;
keywords=alireza heidari, computer vision, computer graphics, machine learning, academic website;

Headings (most frequently used words):

alireza, heidari, selected, publications,

Text of the page (most frequently used words):
and (31), the (26), learning (10), from (8), #alireza (7), heidari (7), our (7), unlabeled (6), data (6), for (6), hair (6), 2026 (5), conference (5), domain (5), generalization (5), framework (5), supervised (5), computer (5), with (4), international (4), amir (4), out (4), where (4), samples (4), can (4), aware (4), images (4), representations (3), robust (3), non (3), distribution (3), also (3), two (3), using (3), siggraph (3), hairport (3), context (3), transfer (3), reference (3), publications (3), machine (3), publisher (2), 2024 (2), year (2), twelfth (2), booktitle (2), saberi (2), hossein (2), najafi (2), author (2), improves (2), title (2), inproceedings (2), semi (2), classification (2), self (2), training (2), result (2), time (2), mixture (2), labeled (2), true (2), set (2), are (2), that (2), error (2), isotropic (2), when (2), html (2), bib (2), abs (2), more (2), authors (2), computing (2), acm (2), papers (2), alimohammadi (2), lira (2), michel (2), pinto (2), mahdavi (2), amiri (2), import (2), graphics (2), vision (2), under (2), viewpoint (2), hairstyle (2), image (2), first (2), source (2), engineer (2), medal (2), olympiad (2), current (2), research (2), modeling (2), theory (2), university (2), repositories (2), copyright, powered, theme, hosted, photos, unsplash, github, pages, folio, jekyll, https, openreview, net, forum, bo6gpq3b9a, url, movasaghinia, mohammad, hosein, motahari, abolfazl, khalaj, babak, saberi2024outofdomain, propose, novel, incorporating, into, problems, scenarios, involving, minimization, either, adversarially, loss, functions, have, been, considered, notably, allow, deviate, slightly, total, variation, sense, core, idea, behind, combine, distributionally, optimization, dro, leverage, efficient, polynomial, algorithms, stage, theoretical, standpoint, apply, problem, gaussians, addition, independent, usually, given, well, only, known, bounded, however, method, both, gaussian, models, one, derive, new, analytically, explicit, asymptotic, bounds, which, show, substantial, improvement, compared, erm, results, underscore, significant, insights, even, harnessed, narrow, gap, provided, adheres, form, cluster, assumption, paradigm, regarded, special, case, there, distributional, shifts, validate, claims, through, experiments, conducted, variety, synthetic, real, world, datasets, pdf, iclr, association, machinery, 1145, 3799902, 3811046, doi, bar, lev, heidari2026hairport, transferring, hairstyles, between, important, but, challenging, task, visual, effects, most, prior, works, operate, best, small, pose, gaps, fall, short, large, scale, differences, missing, content, must, synthesized, rather, than, transferred, present, single, staged, pipeline, removes, while, preserving, facial, identity, then, reconstructs, renders, target, finally, synthesizes, flow, matching, conditioned, bald, aligned, rendering, code, selected, before, sfu, spent, years, software, scientist, was, awarded, silver, 2019, after, earning, gold, ranking, iran, national, astronomy, astrophysics, tapsi, focuses, work, part, vanityai, team, previously, earned, engineering, worked, multimodal, sharif, technology, marz, student, science, interests, include, generative, representation, ali, simon, fraser, submenus, about, toggle, navigation,

Text of the page (random words):
alireza heidari toggle navigation about current publications repositories cv submenus publications repositories cv alireza heidari i am a ph d student in computing science at simon fraser university supervised by dr ali mahdavi amiri my research interests include computer vision computer graphics generative modeling self supervised learning machine learning theory and representation learning my current research focuses on 3d aware hair modeling from images and i also work part time as a machine learning engineer with the vanityai team at marz previously i earned my b sc in computer engineering from sharif university of technology where i worked on multimodal learning and machine learning theory before sfu i spent two years at tapsi as a software engineer and data scientist i was also awarded a silver medal at the 13 th international olympiad on astronomy and astrophysics in 2019 after earning a gold medal and ranking first in iran s national olympiad selected publications siggraph hairport in context 3d aware hair import and transfer for images alireza heidari a alimohammadi w michel pinto lira and 2 more authors in acm siggraph 2026 conference papers 2026 abs bib html code transferring hairstyles between images is an important but challenging task in computer graphics computer vision and visual effects most prior works operate best under small pose gaps and fall short under large viewpoint and scale differences where missing hair content must be synthesized rather than transferred we present hairport a 3d aware framework for in context hairstyle transfer from a single reference image our staged pipeline first removes the source hair while preserving facial identity then reconstructs and re renders the reference hairstyle from the target viewpoint and finally synthesizes the result using flow matching conditioned on the bald source the aligned hair rendering and the reference image inproceedings heidari2026hairport title hairport in context 3d aware hair import and transfer for images author heidari alireza and alimohammadi a and lira w michel pinto and bar lev a and mahdavi amiri a booktitle acm siggraph 2026 conference papers year 2026 doi 10 1145 3799902 3811046 publisher association for computing machinery iclr unlabeled out of domain data improves generalization amir hossein saberi amir najafi alireza heidari and 3 more authors in the twelfth international conference on learning representations 2024 abs bib html pdf we propose a novel framework for incorporating unlabeled data into semi supervised classification problems where scenarios involving the minimization of either i adversarially robust or ii non robust loss functions have been considered notably we allow the unlabeled samples to deviate slightly in total variation sense from the in domain distribution the core idea behind our framework is to combine distributionally robust optimization dro with self supervised training as a result we also leverage efficient polynomial time algorithms for the training stage from a theoretical standpoint we apply our framework on the classification problem of a mixture of two gaussians in ℝd where in addition to the m independent and labeled samples from the true distribution a set of n usually with n m out of domain and unlabeled samples are given as well using only the labeled data it is known that the generalization error can be bounded by d m 1 2 however using our method on both isotropic and non isotropic gaussian mixture models one can derive a new set of analytically explicit and non asymptotic bounds which show substantial improvement on the generalization error compared to erm our results underscore two significant insights 1 out of domain samples even when unlabeled can be harnessed to narrow the generalization gap provided that the true data distribution adheres to a form of the cluster assumption and 2 the semi supervised learning paradigm can be regarded as a special case of our framework when there are no distributional shifts we validate our claims through experiments conducted on a variety of synthetic and real world datasets inproceedings saberi2024outofdomain title unlabeled out of domain data improves generalization author saberi amir hossein and najafi amir and heidari alireza and movasaghinia mohammad hosein and motahari abolfazl and khalaj babak booktitle the twelfth international conference on learning representations year 2024 url https openreview net forum id bo6gpq3b9a publisher international conference on learning representations copyright 2026 alireza heidari powered by jekyll with al folio theme hosted by github pages photos from unsplash