Meta tags:

Headings (most frequently used words):

bipasha, sen, research, interest,

Text of the page (most frequently used words):
the (38), and (28), for (18), video (16), #bipasha (14), sen (14), that (12), using (11), aditya (9), agarwal (9), propose (7), with (7), krishna (7), project (7), page (7), lipreading (6), planning (6), 2023 (6), face (6), learning (6), 2024 (5), our (5), vinay (5), namboodiri (5), jawahar (5), perception (5), icra (5), madhava (5), arxiv (5), representation (5), nerf (5), diffusion (5), data (5), patient (4), approach (4), paper (4), 2022 (4), swapping (4), tasks (4), singh (4), srinath (4), sridhar (4), scenes (4), cost (4), network (3), als (3), high (3), top (3), also (3), rudrabha (3), mukhopadhyay (3), this (3), robotic (3), perform (3), pose (3), system (3), inr (3), space (3), based (3), generative (3), multi (3), scarp (3), shape (3), features (3), gaurav (3), improved (3), priors (3), over (3), objects (3), world (3), cgdf (3), constrained (3), grasp (3), manipulation (3), research (3), personalized (2), one (2), shot (2), relying (2), table (2), rearrangement (2), challenging (2), challenges (2), work (2), extensive (2), ocrtoc (2), challenge (2), vishal (2), reddy (2), mandadi (2), brojeshwar (2), bhowmick (2), end (2), training (2), platform (2), art (2), talking (2), models (2), quality (2), existing (2), wacv (2), towards (2), train (2), v2v (2), novel (2), task (2), can (2), target (2), faceoff (2), two (2), videos (2), learns (2), continuous (2), model (2), arbitrary (2), objective (2), grasping (2), generalizable (2), has (2), address (2), hyp (2), method (2), edmp (2), prior (2), scene (2), costs (2), such (2), ensemble (2), corl (2), advising (2), capacity (2), guided (2), robots (2), conceptgraphs (2), open (2), vocabulary (2), without (2), need (2), datasets (2), florian (2), shkurti (2), liam (2), paull (2), generalizes (2), grasps (2), part (2), complex (2), dual (2), arm (2), lives (2), day (2), collecting (2), prof (2), have (2), worked (2), email (2), used (2), youtube (2), pianist (2), mit (2), powered, fork, minimal, mistakes, academicpages, jekyll, lipread, only, examples, significantly, improves, achieves, 5accuracy, accuracy, compared, achieved, comparable, methods, apart, from, evaluating, extend, people, hearing, impairment, extensively, lip, movements, communicate, portal, bmvc, 2021, problem, relies, heavily, excellent, stack, present, comprehensive, overview, discuss, different, associated, module, result, involvement, 3rd, shankara, narayanan, approaches, automated, pipeline, state, heading, generator, networks, text, speech, computer, vision, techniques, then, human, evaluation, carefully, thought, out, exercises, validate, designed, against, platforms, moocs, synthetic, heads, humans, scale, introduce, preserve, identity, expressions, source, actor, background, double, operates, robust, blending, operation, merge, following, constraints, above, parameterizes, implicit, neural, representations, inrs, layered, perceptron, predicts, rgb, value, each, input, pixel, location, openreview, tmlr, performs, completion, poses, given, partial, pointcloud, object, disentangled, feature, rotationally, equivariant, geometric, trained, tasking, rss, hape, ompletion, bitrary, oses, categories, been, due, dimensionality, weight, limitations, generalization, view, consistency, improve, latent, conditioning, category, level, hypernetworks, rohith, agaram, neurips, hypernetwork, combines, strength, classical, deep, leveraging, policy, learn, kinematically, valid, trajectories, guide, directly, time, inference, specific, collision, instead, single, multiple, functions, guidance, capture, variations, across, thereby, generalizing, diverse, kallol, saha, jayaram, ajit, srikanth, arun, motion, wide, variety, they, require, semantically, rich, yet, compact, efficient, driven, graph, structured, generalize, semantic, classes, collect, large, finetune, qiao, ali, kuwajerwala, sacha, morin, murthy, jatavallabhula, kirsty, ellis, celso, miguel, melo, corban, rivera, william, paul, rama, chellappa, chuang, gan, joshua, tenenbaum, antonio, torralba, graphs, fields, geometries, well, generates, dense, regions, uses, enables, get, sample, efficiency, explicitly, massive, constraint, augmented, stable, especially, useful, settings, sanket, kalwar, faizal, karim, nagamanikandan, govindan, iros, dof, generation, shapes, equal, authors, highlighted, papers, selected, what, drives, idea, seeing, become, commonplace, daily, imbibed, ability, interact, manipulate, environment, order, build, generic, enough, most, scaling, needed, them, believe, primary, robotics, addressing, rethinking, kind, should, scalable, hardware, building, these, directions, hoping, make, collection, seemless, possible, interest, first, year, advised, supported, grateful, some, best, researchers, around, including, was, led, segment, recommendation, suggestion, team, biggest, enterprise, facing, client, outlook, product, are, more, than, 100, million, users, per, month, musician, sing, play, guitar, toured, performed, several, places, previous, band, love, traveling, create, travel, vlogs, music, covers, amazing, taken, channel, now, insen, outdoor, brother, andrometa, creative, outlet, scientist, microsoft, experience, madhav, ida, green, fellowship, pulkit, agrawal, csail, linkedin, google, scholar, github, twitter, hyderabad, india, follow, blog, updates,

Text of the page (random words):
bipasha sen bipasha sen updates blog my art cv bipasha sen ph d at mit follow hyderabad india twitter github youtube google scholar linkedin email i am a first year ph d at the csail mit advised by prof pulkit agrawal i am supported by the ida green fellowship i am grateful to have worked with some of the best researchers around the world including prof c v jawahar vinay namboodiri k madhav krishna srinath sridhar liam paull and florian shkurti prior experience i was also a data scientist at microsoft i led a segment of the recommendation and suggestion team for the world s biggest enterprise facing email client outlook the product features i worked on are used by more than 100 million users per month creative outlet i am a musician i sing and play guitar i have toured and performed at several places with my previous band andrometa i also love traveling and used to create travel vlogs and music covers on youtube my brother is an amazing pianist and has taken over the channel now insen outdoor pianist research interest what drives my research is the idea of seeing robots become a commonplace a part of our daily lives imbibed with the ability to interact and manipulate the environment it lives in in order to build such a generic enough robotic system that can perform most day to day tasks scaling up the data needed to train them is i believe the primary challenge that we need to address in robotics my approach to addressing this is rethinking 1 the kind of data we should be collecting i e the learning objective and 2 the method of collecting this data i e scalable hardware i am building towards the these two directions and hoping to make data collection for robotic manipulation as seemless as possible selected research equal authors highlighted papers constrained 6 dof grasp generation on complex shapes for improved dual arm manipulation gaurav singh sanket kalwar md faizal karim bipasha sen in advising capacity nagamanikandan govindan srinath sridhar and k madhava krishna iros 2024 project page arxiv cgdf constrained grasp diffusion fields is a diffusion based grasp generative model that generalizes to objects with arbitrary geometries as well as generates dense grasps on the target regions cgdf uses a part guided diffusion approach that enables it to get high sample efficiency in constrained grasping without explicitly training on massive constraint augmented datasets cgdf generalizes to stable grasps on complex objects especially useful for dual arm manipulation settings conceptgraphs open vocabulary 3d scene graphs for perception and planning qiao gu ali kuwajerwala sacha morin krishna murthy jatavallabhula bipasha sen aditya agarwal kirsty ellis celso miguel de melo corban rivera william paul rama chellappa chuang gan joshua b tenenbaum antonio torralba florian shkurti liam paull icra 2024 corl w 2024 project page arxiv for robots to perform a wide variety of tasks they require a 3d representation of the world that is semantically rich yet compact and efficient for task driven perception and planning conceptgraphs is an open vocabulary graph structured representation for 3d scenes that generalize to novel semantic classes without the need to collect large 3d datasets or finetune models edmp ensemble of costs guided diffusion for motion planning kallol saha vishal mandadi jayaram reddy ajit srikanth aditya agarwal bipasha sen in advising capacity arun singh madhava krishna icra 2024 corl w 2023 project page arxiv edmp combines the strength of classical planning and deep learning by leveraging a diffusion policy to learn a prior over kinematically valid trajectories and guide it directly at the time of inference using scene specific costs such as collision cost instead of using a single cost we propose using multiple cost functions ensemble of cost guidance to capture variations across scenes thereby generalizing to diverse scenes hyp nerf learning improved nerf priors using a hypernetwork bipasha sen gaurav singh aditya agarwal rohith agaram madhava krishna srinath sridhar neurips 2023 project page arxiv learning generalizable nerf priors over categories of scenes or objects has been challenging due to the high dimensionality of network weight space to address the limitations of existing work on generalization multi view consistency and to improve quality we propose hyp nerf a latent conditioning method for learning generalizable category level nerf priors using hypernetworks scarp 3d s hape c ompletion in ar bitrary p oses for improved grasping bipasha sen aditya agarwal gaurav singh brojeshwar bhowmick srinath sridhar madhava krishna icra 2023 rss w 2023 project page video we propose scarp a model that performs shape completion in arbitrary poses given a partial pointcloud of an object scarp learns a disentangled feature representation of pose and shape by relying on rotationally equivariant pose features and geometric shape features trained using a multi tasking objective inr v a continuous representation space for video based generative tasks bipasha sen aditya agarwal vinay namboodiri c v jawahar tmlr 2022 openreview project page video we propose inr v a video representation network that learns a continuous space for video based generative tasks inr v parameterizes videos using implicit neural representations inrs a multi layered perceptron that predicts an rgb value for each input pixel location of the video faceoff a video to video face swapping system aditya agarwal bipasha sen rudrabha mukhopadhyay vinay namboodiri c v jawahar wacv 2023 project page paper video we introduce video to video v2v face swapping a novel task of face swapping that can preserve 1 the identity and expressions of the source actor face video and 2 the background and pose of the target double video we propose faceoff a v2v face swapping system that operates by learning a robust blending operation to merge two face videos following the constraints above towards moocs for lipreading using synthetic talking heads to train humans in lipreading at scale aditya agarwal bipasha sen rudrabha mukhopadhyay vinay namboodiri c v jawahar wacv 2023 paper we propose an end to end automated pipeline to a lipreading training platform using state of the art talking heading video generator networks text to speech models and computer vision techniques we then perform an extensive human evaluation using carefully thought out lipreading exercises to validate the quality of our designed platform against the existing lipreading platforms approaches and challenges in robotic perception for table top rearrangement and planning aditya agarwal bipasha sen shankara narayanan v vishal reddy mandadi brojeshwar bhowmick k madhava krishna arxiv 2022 paper video 3rd in icra 2022 ocrtoc table top rearrangement and planning is a challenging problem that relies heavily on an excellent perception stack we present a comprehensive overview and discuss the different challenges associated with the perception module this work is a result of our extensive involvement in the icra 2022 ocrtoc challenge personalized one shot lipreading for an als patient bipasha sen aditya agarwal rudrabha mukhopadhyay vinay namboodiri c v jawahar bmvc 2021 paper video portal we propose a personalized network to lipread an als patient using only one shot examples our approach significantly improves and achieves high top 5accuracy with 83 2 accuracy compared to 62 6 achieved by comparable methods for the patient apart from evaluating our approach on the als patient we also extend it to people with hearing impairment relying extensively on lip movements to communicate 2024 bipasha sen powered by jekyll academicpages a fork of minimal mistakes