Picture for Rishibha Bansal

Rishibha Bansal

Read it to me: An emotionally aware Speech Narration Application

Add code
Sep 06, 2022
Rishibha Bansal

Figure 1 for Read it to me: An emotionally aware Speech Narration Application
Figure 2 for Read it to me: An emotionally aware Speech Narration Application
Figure 3 for Read it to me: An emotionally aware Speech Narration Application
Figure 4 for Read it to me: An emotionally aware Speech Narration Application

In this work we try to perform emotional style transfer on audios. In particular, MelGAN-VC architecture is explored for various emotion-pair transfers. The generated audio is then classified using an LSTM-based emotion classifier for audio. We find that "sad" audio is generated well as compared to "happy" or "anger" as people have similar expressions of sadness.

Viaarxiv icon
Github IconAccess Paper or Ask Questions
Twitter IconFacebook IconLinkedin IconWhatsapp IconMessenger Icon

SAVCHOI: Detecting Suspicious Activities using Dense Video Captioning with Human Object Interactions

Add code
Jul 24, 2022
Ansh Mittal, Shuvam Ghosal, Rishibha Bansal, Dat Ngyuyen

Figure 1 for SAVCHOI: Detecting Suspicious Activities using Dense Video Captioning with Human Object Interactions
Figure 2 for SAVCHOI: Detecting Suspicious Activities using Dense Video Captioning with Human Object Interactions
Figure 3 for SAVCHOI: Detecting Suspicious Activities using Dense Video Captioning with Human Object Interactions
Figure 4 for SAVCHOI: Detecting Suspicious Activities using Dense Video Captioning with Human Object Interactions

Detecting suspicious activities in surveillance videos has been a longstanding problem, which can further lead to difficulties in detecting crimes. The authors propose a novel approach for detecting and summarizing the suspicious activities going on in the surveillance videos. They also create ground truth summaries for the UCF-Crime video dataset. Further, the authors test existing state-of-the-art algorithms for Dense Video Captioning for a subset of this dataset and propose a model for this task by leveraging Human-Object Interaction models for the Visual features. They observe that this formulation for Dense Captioning achieves large gains over earlier approaches by a significant margin. The authors also perform an ablative analysis of the dataset and the model and report their findings.

* 11 pages, 4 figures, 5 tables 
Viaarxiv icon
Github IconAccess Paper or Ask Questions
Twitter IconFacebook IconLinkedin IconWhatsapp IconMessenger Icon