2 code implementations • 18 Nov 2023 • Di Chang, Yichun Shi, Quankai Gao, Jessica Fu, Hongyi Xu, Guoxian Song, Qing Yan, Yizhe Zhu, Xiao Yang, Mohammad Soleymani
In this work, we propose MagicPose, a diffusion-based model for 2D human pose and facial expression retargeting.
1 code implementation • CVPR 2019 • Yale Song, Mohammad Soleymani
In this work, we introduce Polysemous Instance Embedding Networks (PIE-Nets) that compute multiple and diverse representations of an instance by combining global context with locally-guided features via multi-head self-attention and residual learning.
Ranked #33 on Cross-Modal Retrieval on COCO 2014
1 code implementation • 18 Aug 2023 • Di Chang, Yufeng Yin, Zongjian Li, Minh Tran, Mohammad Soleymani
Facial expression analysis is an important tool for human-computer interaction.
1 code implementation • Findings (EMNLP) 2021 • Zihao He, Leili Tavabi, Kristina Lerman, Mohammad Soleymani
Dialogue Act (DA) classification is the task of classifying utterances with respect to the function they serve in a dialogue.
Ranked #2 on Dialogue Act Classification on Switchboard corpus
1 code implementation • EMNLP 2021 • Junyan Cheng, Iordanis Fostiropoulos, Barry Boehm, Mohammad Soleymani
We evaluate our model with three sentiment analysis datasets and achieve comparable or superior performance compared with the existing methods, with a 90% reduction in the number of parameters.
1 code implementation • 23 Aug 2023 • Yufeng Yin, Di Chang, Guoxian Song, Shen Sang, Tiancheng Zhi, Jing Liu, Linjie Luo, Mohammad Soleymani
The proposed FG-Net achieves a strong generalization ability for heatmap-based AU detection thanks to the generalizable and semantic-rich features extracted from the pre-trained generative model.
1 code implementation • 23 Aug 2021 • Minh Tran, Ellen Bradley, Michelle Matvey, Joshua Woolley, Mohammad Soleymani
Facial action unit (FAU) intensities are popular descriptors for the analysis of facial behavior.
1 code implementation • 26 Mar 2022 • Minh Tran, Mohammad Soleymani
Privacy and security are major concerns when communicating speech signals to cloud services such as automatic speech recognition (ASR) and speech emotion recognition (SER).
Automatic Speech Recognition Automatic Speech Recognition (ASR) +7
no code implementations • 12 Apr 2018 • Yale Song, Mohammad Soleymani
Traditional cross-modal retrieval assumes explicit association of concepts across modalities, where there is no ambiguity in how the concepts are linked to each other, e. g., when we do the image search with a query "dogs", we expect to see dog images.
no code implementations • 10 Jul 2019 • Fabien Ringeval, Björn Schuller, Michel Valstar, NIcholas Cummins, Roddy Cowie, Leili Tavabi, Maximilian Schmitt, Sina Alisamir, Shahin Amiriparian, Eva-Maria Messner, Siyang Song, Shuo Liu, Ziping Zhao, Adria Mallol-Ragolta, Zhao Ren, Mohammad Soleymani, Maja Pantic
The Audio/Visual Emotion Challenge and Workshop (AVEC 2019) "State-of-Mind, Detecting Depression with AI, and Cross-cultural Affect Recognition" is the ninth competition event aimed at the comparison of multimedia processing and machine learning methods for automatic audiovisual health and emotion analysis, with all participants competing strictly under the same conditions.
no code implementations • 3 Oct 2019 • Sicheng Zhao, Shangfei Wang, Mohammad Soleymani, Dhiraj Joshi, Qiang Ji
Affective computing (AC) of these data can help to understand human behaviors and enable wide applications.
no code implementations • COLING 2020 • Minh Tran, YiPeng Zhang, Mohammad Soleymani
Offensive and abusive language is a pressing problem on social media platforms.
no code implementations • 28 Jan 2020 • Mohammad Soleymani, Ignacio Santamaria, Peter J. Schreier
This paper investigates the performance of improper Gaussian signaling (IGS) for the $K$-user multiple-input, multiple-output (MIMO) interference channel (IC) with hardware impairments (HWI).
no code implementations • NAACL (CLPsych) 2021 • Leili Tavabi, Trang Tran, Kalin Stefanov, Brian Borsari, Joshua Woolley, Stefan Scherer, Mohammad Soleymani
Analysis of client and therapist behavior in counseling sessions can provide helpful insights for assessing the quality of the session and consequently, the client’s behavioral outcome.
no code implementations • 23 Jan 2022 • Minh Tran, Mohammad Soleymani
In this paper, we introduce a pretrained audio-visual Transformer trained on more than 500k utterances from nearly 4000 celebrities from the VoxCeleb2 dataset for human behavior understanding.
no code implementations • 19 Mar 2023 • Yufeng Yin, Minh Tran, Di Chang, Xinrui Wang, Mohammad Soleymani
Facial action unit detection has emerged as an important task within facial expression analysis, aimed at detecting specific pre-defined, objective facial expressions, such as lip tightening and cheek raising.
no code implementations • 5 Sep 2023 • Minh Tran, Yufeng Yin, Mohammad Soleymani
There are individual differences in expressive behaviors driven by cultural norms and personality.
no code implementations • 26 Oct 2023 • Minh Tran, Mohammad Soleymani
In this paper, we present a novel framework to anonymize utterance-level speech embeddings generated by pre-trained encoders and show its effectiveness for a range of speech classification tasks.
no code implementations • 6 Jan 2024 • Zhonghao Shi, Allison O'Connell, Zongjian Li, SiQi Liu, Jennifer Ayissi, Guy Hoffman, Mohammad Soleymani, Maja J. Matarić
We hope that this work will contribute toward accessible and engaging AI education in human-AI interaction for college and high school students.
no code implementations • 23 Jan 2024 • Emily Zhou, Mohammad Soleymani, Maja J. Matarić
To address this ambiguity, we evaluated the generalizability of physiological features that have been shown to be correlated with anxiety and stress to high-arousal emotions.
no code implementations • 14 Mar 2024 • Minh Tran, Di Chang, Maksim Siniukov, Mohammad Soleymani
Hence, an effective model for generating listener nonverbal behaviors requires understanding the dyadic context and interaction.
no code implementations • 15 Mar 2024 • Liupei Lu, Yufeng Yin, Yuming Gu, Yizhen Wu, Pratusha Prasad, Yajie Zhao, Mohammad Soleymani
Then, we use MSDA to transfer the AU detection knowledge from a real dataset and the synthetic dataset to a target dataset.