Zobrazeno 1 - 10
of 38
pro vyhledávání: '"Bhattacharya, Uttaran"'
Publikováno v:
In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 1st Workshop on Human Motion Generation, 2024, Seattle, Washington, USA
We present a multimodal learning-based method to simultaneously synthesize co-speech facial expressions and upper-body gestures for digital characters using RGB video data captured using commodity cameras. Our approach learns from sparse face landmar
Externí odkaz:
http://arxiv.org/abs/2406.18068
Autor:
Maharaj, Akash V., Qian, Kun, Bhattacharya, Uttaran, Fang, Sally, Galatanu, Horia, Garg, Manas, Hanessian, Rachel, Kapoor, Nishant, Russell, Ken, Vaithyanathan, Shivakumar, Li, Yunyao
The development of conversational AI assistants is an iterative process with multiple components. As such, the evaluation and continual improvement of these assistants is a complex and multifaceted problem. This paper introduces the challenges in eva
Externí odkaz:
http://arxiv.org/abs/2407.12003
Autor:
Narasimhaswamy, Supreeth, Bhattacharya, Uttaran, Chen, Xiang, Dasgupta, Ishita, Mitra, Saayan, Hoai, Minh
Text-to-image generative models can generate high-quality humans, but realism is lost when generating hands. Common artifacts include irregular hand poses, shapes, incorrect numbers of fingers, and physically implausible finger orientations. To gener
Externí odkaz:
http://arxiv.org/abs/2403.01693
Recent advancements in language-model-based video understanding have been progressing at a remarkable pace, spurred by the introduction of Large Language Models (LLMs). However, the focus of prior research has been predominantly on devising a project
Externí odkaz:
http://arxiv.org/abs/2312.02310
Autor:
Khandelwal, Ashmit, Agrawal, Aditya, Bhattacharyya, Aanisha, Singla, Yaman K, Singh, Somesh, Bhattacharya, Uttaran, Dasgupta, Ishita, Petrangeli, Stefano, Shah, Rajiv Ratn, Chen, Changyou, Krishnamurthy, Balaji
Shannon and Weaver's seminal information theory divides communication into three levels: technical, semantic, and effectiveness. While the technical level deals with the accurate reconstruction of transmitted symbols, the semantic and effectiveness l
Externí odkaz:
http://arxiv.org/abs/2309.00359
We present DanceAnyWay, a generative learning method to synthesize beat-guided dances of 3D human characters synchronized with music. Our method learns to disentangle the dance movements at the beat frames from the dance movements at all the remainin
Externí odkaz:
http://arxiv.org/abs/2303.03870
Autor:
Bhattacharya, Uttaran, Wu, Gang, Petrangeli, Stefano, Swaminathan, Viswanathan, Manocha, Dinesh
Publikováno v:
In Proceedings of the 30th ACM International Conference on Multimedia, 2022, Lisboa, Portugal
We propose a method to detect individualized highlights for users on given target videos based on their preferred highlight clips marked on previous videos they have watched. Our method explicitly leverages the contents of both the preferred clips an
Externí odkaz:
http://arxiv.org/abs/2207.08352
Autor:
Bhattacharya, Uttaran, Wu, Gang, Petrangeli, Stefano, Swaminathan, Viswanathan, Manocha, Dinesh
We present a domain- and user-preference-agnostic approach to detect highlightable excerpts from human-centric videos. Our method works on the graph-based representation of multiple observable human-centric modalities in the videos, such as poses and
Externí odkaz:
http://arxiv.org/abs/2110.01774
We present a generative adversarial network to synthesize 3D pose sequences of co-speech upper-body gestures with appropriate affective expressions. Our network consists of two components: a generator to synthesize gestures from a joint embedding spa
Externí odkaz:
http://arxiv.org/abs/2108.00262
Autor:
Bhattacharya, Uttaran, Rewkowski, Nicholas, Banerjee, Abhishek, Guhan, Pooja, Bera, Aniket, Manocha, Dinesh
Publikováno v:
IEEEVR 2021, pp. 1-10
We present Text2Gestures, a transformer-based learning method to interactively generate emotive full-body gestures for virtual agents aligned with natural language text inputs. Our method generates emotionally expressive gestures by utilizing the rel
Externí odkaz:
http://arxiv.org/abs/2101.11101