Alert button
Picture for Krishna Somandepalli

Krishna Somandepalli

Alert button

VideoPoet: A Large Language Model for Zero-Shot Video Generation

Dec 21, 2023
Dan Kondratyuk, Lijun Yu, Xiuye Gu, José Lezama, Jonathan Huang, Rachel Hornung, Hartwig Adam, Hassan Akbari, Yair Alon, Vighnesh Birodkar, Yong Cheng, Ming-Chang Chiu, Josh Dillon, Irfan Essa, Agrim Gupta, Meera Hahn, Anja Hauth, David Hendon, Alonso Martinez, David Minnen, David Ross, Grant Schindler, Mikhail Sirotenko, Kihyuk Sohn, Krishna Somandepalli, Huisheng Wang, Jimmy Yan, Ming-Hsuan Yang, Xuan Yang, Bryan Seybold, Lu Jiang

Viaarxiv icon

LanSER: Language-Model Supported Speech Emotion Recognition

Sep 07, 2023
Taesik Gong, Josh Belanich, Krishna Somandepalli, Arsha Nagrani, Brian Eoff, Brendan Jou

Figure 1 for LanSER: Language-Model Supported Speech Emotion Recognition
Figure 2 for LanSER: Language-Model Supported Speech Emotion Recognition
Figure 3 for LanSER: Language-Model Supported Speech Emotion Recognition
Figure 4 for LanSER: Language-Model Supported Speech Emotion Recognition
Viaarxiv icon

MM-AU:Towards Multimodal Understanding of Advertisement Videos

Aug 27, 2023
Digbalay Bose, Rajat Hebbar, Tiantian Feng, Krishna Somandepalli, Anfeng Xu, Shrikanth Narayanan

Figure 1 for MM-AU:Towards Multimodal Understanding of Advertisement Videos
Figure 2 for MM-AU:Towards Multimodal Understanding of Advertisement Videos
Figure 3 for MM-AU:Towards Multimodal Understanding of Advertisement Videos
Figure 4 for MM-AU:Towards Multimodal Understanding of Advertisement Videos
Viaarxiv icon

Contextually-rich human affect perception using multimodal scene information

Mar 13, 2023
Digbalay Bose, Rajat Hebbar, Krishna Somandepalli, Shrikanth Narayanan

Figure 1 for Contextually-rich human affect perception using multimodal scene information
Figure 2 for Contextually-rich human affect perception using multimodal scene information
Figure 3 for Contextually-rich human affect perception using multimodal scene information
Figure 4 for Contextually-rich human affect perception using multimodal scene information
Viaarxiv icon

Heterogeneous Graph Learning for Acoustic Event Classification

Mar 12, 2023
Amir Shirian, Mona Ahmadian, Krishna Somandepalli, Tanaya Guha

Figure 1 for Heterogeneous Graph Learning for Acoustic Event Classification
Figure 2 for Heterogeneous Graph Learning for Acoustic Event Classification
Figure 3 for Heterogeneous Graph Learning for Acoustic Event Classification
Viaarxiv icon

A dataset for Audio-Visual Sound Event Detection in Movies

Feb 14, 2023
Rajat Hebbar, Digbalay Bose, Krishna Somandepalli, Veena Vijai, Shrikanth Narayanan

Figure 1 for A dataset for Audio-Visual Sound Event Detection in Movies
Figure 2 for A dataset for Audio-Visual Sound Event Detection in Movies
Figure 3 for A dataset for Audio-Visual Sound Event Detection in Movies
Figure 4 for A dataset for Audio-Visual Sound Event Detection in Movies
Viaarxiv icon

Visually-aware Acoustic Event Detection using Heterogeneous Graphs

Jul 16, 2022
Amir Shirian, Krishna Somandepalli, Victor Sanchez, Tanaya Guha

Figure 1 for Visually-aware Acoustic Event Detection using Heterogeneous Graphs
Figure 2 for Visually-aware Acoustic Event Detection using Heterogeneous Graphs
Figure 3 for Visually-aware Acoustic Event Detection using Heterogeneous Graphs
Viaarxiv icon

Multitask vocal burst modeling with ResNets and pre-trained paralinguistic Conformers

Jun 24, 2022
Josh Belanich, Krishna Somandepalli, Brian Eoff, Brendan Jou

Figure 1 for Multitask vocal burst modeling with ResNets and pre-trained paralinguistic Conformers
Figure 2 for Multitask vocal burst modeling with ResNets and pre-trained paralinguistic Conformers
Viaarxiv icon

To train or not to train adversarially: A study of bias mitigation strategies for speaker recognition

Mar 17, 2022
Raghuveer Peri, Krishna Somandepalli, Shrikanth Narayanan

Figure 1 for To train or not to train adversarially: A study of bias mitigation strategies for speaker recognition
Figure 2 for To train or not to train adversarially: A study of bias mitigation strategies for speaker recognition
Figure 3 for To train or not to train adversarially: A study of bias mitigation strategies for speaker recognition
Figure 4 for To train or not to train adversarially: A study of bias mitigation strategies for speaker recognition
Viaarxiv icon

Self-supervised Graphs for Audio Representation Learning with Limited Labeled Data

Jan 31, 2022
Amir Shirian, Krishna Somandepalli, Tanaya Guha

Figure 1 for Self-supervised Graphs for Audio Representation Learning with Limited Labeled Data
Figure 2 for Self-supervised Graphs for Audio Representation Learning with Limited Labeled Data
Figure 3 for Self-supervised Graphs for Audio Representation Learning with Limited Labeled Data
Figure 4 for Self-supervised Graphs for Audio Representation Learning with Limited Labeled Data
Viaarxiv icon