Traditional Automatic Video Dubbing (AVD) pipeline consists of three key modules, namely, Automatic Speech Recognition (ASR), Neural Machine Translation (NMT), and Text-to-Speech (TTS). Within AVD pipelines, isometric-NMT algorithms are employed to regulate the length of the synthesized output text. This is done to guarantee synchronization with respect to the alignment of video and audio subsequent to the dubbing process. Previous approaches have focused on aligning the number of characters and words in the source and target language texts of Machine Translation models. However, our approach aims to align the number of phonemes instead, as they are closely associated with speech duration. In this paper, we present the development of an isometric NMT system using Reinforcement Learning (RL), with a focus on optimizing the alignment of phoneme counts in the source and target language sentence pairs. To evaluate our models, we propose the Phoneme Count Compliance (PCC) score, which is a measure of length compliance. Our approach demonstrates a substantial improvement of approximately 36% in the PCC score compared to the state-of-the-art models when applied to English-Hindi language pairs. Moreover, we propose a student-teacher architecture within the framework of our RL approach to maintain a trade-off between the phoneme count and translation quality.
Deep learning methods have led to significant improvements in the performance on the facial landmark detection (FLD) task. However, detecting landmarks in challenging settings, such as head pose changes, exaggerated expressions, or uneven illumination, continue to remain a challenge due to high variability and insufficient samples. This inadequacy can be attributed to the model's inability to effectively acquire appropriate facial structure information from the input images. To address this, we propose a novel image augmentation technique specifically designed for the FLD task to enhance the model's understanding of facial structures. To effectively utilize the newly proposed augmentation technique, we employ a Siamese architecture-based training mechanism with a Deep Canonical Correlation Analysis (DCCA)-based loss to achieve collective learning of high-level feature representations from two different views of the input images. Furthermore, we employ a Transformer + CNN-based network with a custom hourglass module as the robust backbone for the Siamese framework. Extensive experiments show that our approach outperforms multiple state-of-the-art approaches across various benchmark datasets.
Semi-supervised object detection (SSOD) has made significant progress with the development of pseudo-label-based end-to-end methods. However, many of these methods face challenges due to class imbalance, which hinders the effectiveness of the pseudo-label generator. Furthermore, in the literature, it has been observed that low-quality pseudo-labels severely limit the performance of SSOD. In this paper, we examine the root causes of low-quality pseudo-labels and present novel learning mechanisms to improve the label generation quality. To cope with high false-negative and low precision rates, we introduce an adaptive thresholding mechanism that helps the proposed network to filter out optimal bounding boxes. We further introduce a Jitter-Bagging module to provide accurate information on localization to help refine the bounding boxes. Additionally, two new losses are introduced using the background and foreground scores predicted by the teacher and student networks to improvise the pseudo-label recall rate. Furthermore, our method applies strict supervision to the teacher network by feeding strong & weak augmented data to generate robust pseudo-labels so that it can detect small and complex objects. Finally, the extensive experiments show that the proposed network outperforms state-of-the-art methods on MS-COCO and Pascal VOC datasets and allows the baseline network to achieve 100% supervised performance with much less (i.e., 20%) labeled data.
Emotion Recognition in Conversations (ERC) is crucial in developing sympathetic human-machine interaction. In conversational videos, emotion can be present in multiple modalities, i.e., audio, video, and transcript. However, due to the inherent characteristics of these modalities, multi-modal ERC has always been considered a challenging undertaking. Existing ERC research focuses mainly on using text information in a discussion, ignoring the other two modalities. We anticipate that emotion recognition accuracy can be improved by employing a multi-modal approach. Thus, in this study, we propose a Multi-modal Fusion Network (M2FNet) that extracts emotion-relevant features from visual, audio, and text modality. It employs a multi-head attention-based fusion mechanism to combine emotion-rich latent representations of the input data. We introduce a new feature extractor to extract latent features from the audio and visual modality. The proposed feature extractor is trained with a novel adaptive margin-based triplet loss function to learn emotion-relevant features from the audio and visual data. In the domain of ERC, the existing methods perform well on one benchmark dataset but not on others. Our results show that the proposed M2FNet architecture outperforms all other methods in terms of weighted average F1 score on well-known MELD and IEMOCAP datasets and sets a new state-of-the-art performance in ERC.
Biometric-based verification is widely employed on the smartphones for various applications, including financial transactions. In this work, we present a new multimodal biometric dataset (face, voice, and periocular) acquired using a smartphone. The new dataset is comprised of 150 subjects that are captured in six different sessions reflecting real-life scenarios of smartphone assisted authentication. One of the unique features of this dataset is that it is collected in four different geographic locations representing a diverse population and ethnicity. Additionally, we also present a multimodal Presentation Attack (PA) or spoofing dataset using a low-cost Presentation Attack Instrument (PAI) such as print and electronic display attacks. The novel acquisition protocols and the diversity of the data subjects collected from different geographic locations will allow developing a novel algorithm for either unimodal or multimodal biometrics. Further, we also report the performance evaluation of the baseline biometric verification and Presentation Attack Detection (PAD) on the newly collected dataset.