Srinivas Parthasarathy

Rajat Koner, Zhipeng Wang, Srinivas Parthasarathy et al.

Online video segmentation methods excel at handling long sequences and capturing gradual changes, making them ideal for real-world applications. However, achieving temporally consistent predictions remains a challenge, especially with gradual accumulation of noise or drift in on-line propagation, abrupt occlusions and scene transitions. This paper introduces Local2Global, an online framework, for video instance segmentation, exhibiting state-of-the-art performance with simple baseline and training purely in online fashion. Leveraging the DETR-based query propagation framework, we introduce two novel sets of queries:(1) local queries that capture initial object-specific spatial features from each frame and (2) global queries containing past spatio-temporal representations. We propose the L2G-aligner, a novel lightweight transformer decoder, to facilitate an early alignment between local and global queries. This alignment allows our model to effectively utilize current frame information while maintaining temporal consistency, producing a smooth transition between frames. Furthermore, L2G-aligner is integrated within the segmentation model, without relying on additional complex heuristics, or memory mechanisms. Extensive experiments across various challenging VIS and VPS datasets showcase the superiority of our method with simple online training, surpassing current benchmarks without bells and rings. For instance, we achieve 54.3 and 49.4 AP on Youtube-VIS-19/-21 datasets and 37.0 AP on OVIS dataset respectively withthe ResNet-50 backbone.

Raghuveer Peri, Srinivas Parthasarathy, Charles Bradshaw et al.

Deep learning models trained on audio-visual data have been successfully used to achieve state-of-the-art performance for emotion recognition. In particular, models trained with multitask learning have shown additional performance improvements. However, such multitask models entangle information between the tasks, encoding the mutual dependencies present in label distributions in the real world data used for training. This work explores the disentanglement of multimodal signal representations for the primary task of emotion recognition and a secondary person identification task. In particular, we developed a multitask framework to extract low-dimensional embeddings that aim to capture emotion specific information, while containing minimal information related to person identity. We evaluate three different techniques for disentanglement and report results of up to 13% disentanglement while maintaining emotion recognition performance.

Srinivas Parthasarathy, Shiva Sundaram

Developing machine learning algorithms to understand person-to-person engagement can result in natural user experiences for communal devices such as Amazon Alexa. Among other cues such as voice activity and gaze, a person's audio-visual expression that includes tone of the voice and facial expression serves as an implicit signal of engagement between parties in a dialog. This study investigates deep-learning algorithms for audio-visual detection of user's expression. We first implement an audio-visual baseline model with recurrent layers that shows competitive results compared to current state of the art. Next, we propose the transformer architecture with encoder layers that better integrate audio-visual features for expressions tracking. Performance on the Aff-Wild2 database shows that the proposed methods perform better than baseline architecture with recurrent layers with absolute gains approximately 2% for arousal and valence descriptors. Further, multimodal architectures show significant improvements over models trained on single modalities with gains of up to 3.6%. Ablation studies show the significance of the visual modality for the expression detection on the Aff-Wild2 database.

Aparna Khare, Srinivas Parthasarathy, Shiva Sundaram

Emotion recognition is a challenging task due to limited availability of in-the-wild labeled datasets. Self-supervised learning has shown improvements on tasks with limited labeled datasets in domains like speech and natural language. Models such as BERT learn to incorporate context in word embeddings, which translates to improved performance in downstream tasks like question answering. In this work, we extend self-supervised training to multi-modal applications. We learn multi-modal representations using a transformer trained on the masked language modeling task with audio, visual and text features. This model is fine-tuned on the downstream task of emotion recognition. Our results on the CMU-MOSEI dataset show that this pre-training technique can improve the emotion recognition performance by up to 3% compared to the baseline.

Srinivas Parthasarathy, Shiva Sundaram

Automatic audio-visual expression recognition can play an important role in communication services such as tele-health, VOIP calls and human-machine interaction. Accuracy of audio-visual expression recognition could benefit from the interplay between the two modalities. However, most audio-visual expression recognition systems, trained in ideal conditions, fail to generalize in real world scenarios where either the audio or visual modality could be missing due to a number of reasons such as limited bandwidth, interactors' orientation, caller initiated muting. This paper studies the performance of a state-of-the art transformer when one of the modalities is missing. We conduct ablation studies to evaluate the model in the absence of either modality. Further, we propose a strategy to randomly ablate visual inputs during training at the clip or frame level to mimic real world scenarios. Results conducted on in-the-wild data, indicate significant generalization in proposed models trained on missing cues, with gains up to 17% for frame level ablations, showing that these training strategies cope better with the loss of input modalities.

Aparna Khare, Srinivas Parthasarathy, Shiva Sundaram

General embeddings like word2vec, GloVe and ELMo have shown a lot of success in natural language tasks. The embeddings are typically extracted from models that are built on general tasks such as skip-gram models and natural language generation. In this paper, we extend the work from natural language understanding to multi-modal architectures that use audio, visual and textual information for machine learning tasks. The embeddings in our network are extracted using the encoder of a transformer model trained using multi-task training. We use person identification and automatic speech recognition as the tasks in our embedding generation framework. We tune and evaluate the embeddings on the downstream task of emotion recognition and demonstrate that on the CMU-MOSEI dataset, the embeddings can be used to improve over previous state of the art results.

Georgios Paraskevopoulos, Srinivas Parthasarathy, Aparna Khare et al.

This paper presents an audio visual automatic speech recognition (AV-ASR) system using a Transformer-based architecture. We particularly focus on the scene context provided by the visual information, to ground the ASR. We extract representations for audio features in the encoder layers of the transformer and fuse video features using an additional crossmodal multihead attention layer. Additionally, we incorporate a multitask training criterion for multiresolution ASR, where we train the model to generate both character and subword level transcriptions. Experimental results on the How2 dataset, indicate that multiresolution training can speed up convergence by around 50% and relatively improves word error rate (WER) performance by upto 18% over subword prediction models. Further, incorporating visual information improves performance with relative gains upto 3.76% over audio only models. Our results are comparable to state-of-the-art Listen, Attend and Spell-based architectures.

Srinivas Parthasarathy, Carlos Busso

Recognizing emotions using few attribute dimensions such as arousal, valence and dominance provides the flexibility to effectively represent complex range of emotional behaviors. Conventional methods to learn these emotional descriptors primarily focus on separate models to recognize each of these attributes. Recent work has shown that learning these attributes together regularizes the models, leading to better feature representations. This study explores new forms of regularization by adding unsupervised auxiliary tasks to reconstruct hidden layer representations. This auxiliary task requires the denoising of hidden representations at every layer of an auto-encoder. The framework relies on ladder networks that utilize skip connections between encoder and decoder layers to learn powerful representations of emotional dimensions. The results show that ladder networks improve the performance of the system compared to baselines that individually learn each attribute, and conventional denoising autoencoders. Furthermore, the unsupervised auxiliary tasks have promising potential to be used in a semi-supervised setting, where few labeled sentences are available.