FGA: Fourier-Guided Attention Network for Crowd Count Estimation

Crowd counting is gaining societal relevance, particularly in domains of Urban Planning, Crowd Management, and Public Safety. This paper introduces Fourier-guided attention (FGA), a novel attention mechanism for crowd count estimation designed to address the inefficient full-scale global pattern capture in existing works on convolution-based attention networks. FGA efficiently captures multi-scale information, including full-scale global patterns, by utilizing Fast-Fourier Transformations (FFT) along with spatial attention for global features and convolutions with channel-wise attention for semi-global and local features. The architecture of FGA involves a dual-path approach: (1) a path for processing full-scale global features through FFT, allowing for efficient extraction of information in the frequency domain, and (2) a path for processing remaining feature maps for semi-global and local features using traditional convolutions and channel-wise attention. This dual-path architecture enables FGA to seamlessly integrate frequency and spatial information, enhancing its ability to capture diverse crowd patterns. We apply FGA in the last layers of two popular crowd-counting works, CSRNet and CANNet, to evaluate the module's performance on benchmark datasets such as ShanghaiTech-A, ShanghaiTech-B, UCF-CC-50, and JHU++ crowd. The experiments demonstrate a notable improvement across all datasets based on Mean-Squared-Error (MSE) and Mean-Absolute-Error (MAE) metrics, showing comparable performance to recent state-of-the-art methods. Additionally, we illustrate the interpretability using qualitative analysis, leveraging Grad-CAM heatmaps, to show the effectiveness of FGA in capturing crowd patterns.

AVR: Synergizing Foundation Models for Audio-Visual Humor Detection

In this work, we present, AVR application for audio-visual humor detection. While humor detection has traditionally centered around textual analysis, recent advancements have spotlighted multimodal approaches. However, these methods lean on textual cues as a modality, necessitating the use of ASR systems for transcribing the audio-data. This heavy reliance on ASR accuracy can pose challenges in real-world applications. To address this bottleneck, we propose an innovative audio-visual humor detection system that circumvents textual reliance, eliminating the need for ASR models. Instead, the proposed approach hinges on the intricate interplay between audio and visual content for effective humor detection.

Towards Multilingual Audio-Visual Question Answering

In this paper, we work towards extending Audio-Visual Question Answering (AVQA) to multilingual settings. Existing AVQA research has predominantly revolved around English and replicating it for addressing AVQA in other languages requires a substantial allocation of resources. As a scalable solution, we leverage machine translation and present two multilingual AVQA datasets for eight languages created from existing benchmark AVQA datasets. This prevents extra human annotation efforts of collecting questions and answers manually. To this end, we propose, MERA framework, by leveraging state-of-the-art (SOTA) video, audio, and textual foundation models for AVQA in multiple languages. We introduce a suite of models namely MERA-L, MERA-C, MERA-T with varied model architectures to benchmark the proposed datasets. We believe our work will open new research directions and act as a reference benchmark for future works in multilingual AVQA.

PERSONA: An Application for Emotion Recognition, Gender Recognition and Age Estimation

Emotion Recognition (ER), Gender Recognition (GR), and Age Estimation (AE) constitute paralinguistic tasks that rely not on the spoken content but primarily on speech characteristics such as pitch and tone. While previous research has made significant strides in developing models for each task individually, there has been comparatively less emphasis on concurrently learning these tasks, despite their inherent interconnectedness. As such in this demonstration, we present PERSONA, an application for predicting ER, GR, and AE with a single model in the backend. One notable point is we show that representations from speaker recognition pre-trained model (PTM) is better suited for such a multi-task learning format than the state-of-the-art (SOTA) self-supervised (SSL) PTM by carrying out a comparative study. Our methodology obviates the need for deploying separate models for each task and can potentially conserve resources and time during the training and deployment phases.

The Reasonable Effectiveness of Speaker Embeddings for Violence Detection

In this paper, we focus on audio violence detection (AVD). AVD is necessary for several reasons, especially in the context of maintaining safety, preventing harm, and ensuring security in various environments. This calls for accurate AVD systems. Like many related applications in audio processing, the most common approach for improving the performance, would be by leveraging self-supervised (SSL) pre-trained models (PTMs). However, as these SSL models are very large models with million of parameters and this can hinder real-world deployment especially in compute-constraint environment. To resolve this, we propose the usage of speaker recognition models which are much smaller compared to the SSL models. Experimentation with speaker recognition model embeddings with SVM & Random Forest as classifiers, we show that speaker recognition model embeddings perform the best in comparison to state-of-the-art (SOTA) SSL models and achieve SOTA results.

ComFeAT: Combination of Neural and Spectral Features for Improved Depression Detection

In this work, we focus on the detection of depression through speech analysis. Previous research has widely explored features extracted from pre-trained models (PTMs) primarily trained for paralinguistic tasks. Although these features have led to sufficient advances in speech-based depression detection, their performance declines in real-world settings. To address this, in this paper, we introduce ComFeAT, an application that employs a CNN model trained on a combination of features extracted from PTMs, a.k.a. neural features and spectral features to enhance depression detection. Spectral features are robust to domain variations, but, they are not as good as neural features in performance, suprisingly, combining them shows complementary behavior and improves over both neural and spectral features individually. The proposed method also improves over previous state-of-the-art (SOTA) works on E-DAIC benchmark.

CoLLAB: A Collaborative Approach for Multilingual Abuse Detection

In this study, we investigate representations from paralingual Pre-Trained model (PTM) for Audio Abuse Detection (AAD), which has not been explored for AAD. Our results demonstrate their superiority compared to other PTM representations on the ADIMA benchmark. Furthermore, combining PTM representations enhances AAD performance. Despite these improvements, challenges with cross-lingual generalizability still remain, and certain languages require training in the same language. This demands individual models for different languages, leading to scalability, maintenance, and resource allocation issues and hindering the practical deployment of AAD systems in linguistically diverse real-world environments. To address this, we introduce CoLLAB, a novel framework that doesn't require training and allows seamless merging of models trained in different languages through weight-averaging. This results in a unified model with competitive AAD performance across multiple languages.

BB-Patch: BlackBox Adversarial Patch-Attack using Zeroth-Order Optimization

Deep Learning has become popular due to its vast applications in almost all domains. However, models trained using deep learning are prone to failure for adversarial samples and carry a considerable risk in sensitive applications. Most of these adversarial attack strategies assume that the adversary has access to the training data, the model parameters, and the input during deployment, hence, focus on perturbing the pixel level information present in the input image. Adversarial Patches were introduced to the community which helped in bringing out the vulnerability of deep learning models in a much more pragmatic manner but here the attacker has a white-box access to the model parameters. Recently, there has been an attempt to develop these adversarial attacks using black-box techniques. However, certain assumptions such as availability large training data is not valid for a real-life scenarios. In a real-life scenario, the attacker can only assume the type of model architecture used from a select list of state-of-the-art architectures while having access to only a subset of input dataset. Hence, we propose an black-box adversarial attack strategy that produces adversarial patches which can be applied anywhere in the input image to perform an adversarial attack.

Heterogeneity over Homogeneity: Investigating Multilingual Speech Pre-Trained Models for Detecting Audio Deepfake

In this work, we investigate multilingual speech Pre-Trained models (PTMs) for Audio deepfake detection (ADD). We hypothesize that multilingual PTMs trained on large-scale diverse multilingual data gain knowledge about diverse pitches, accents, and tones, during their pre-training phase and making them more robust to variations. As a result, they will be more effective for detecting audio deepfakes. To validate our hypothesis, we extract representations from state-of-the-art (SOTA) PTMs including monolingual, multilingual as well as PTMs trained for speaker and emotion recognition, and evaluated them on ASVSpoof 2019 (ASV), In-the-Wild (ITW), and DECRO benchmark databases. We show that representations from multilingual PTMs, with simple downstream networks, attain the best performance for ADD compared to other PTM representations, which validates our hypothesis. We also explore the possibility of fusion of selected PTM representations for further improvements in ADD, and we propose a framework, MiO (Merge into One) for this purpose. With MiO, we achieve SOTA performance on ASV and ITW and comparable performance on DECRO with current SOTA works.

SONIC: Synergizing VisiON Foundation Models for Stress RecogNItion from ECG signals

Stress recognition through physiological signals such as Electrocardiogram (ECG) signals has garnered significant attention. Traditionally, research in this field predominantly focused on utilizing handcrafted features or raw signals as inputs for learning algorithms. However, there is now a burgeoning interest within the community in leveraging large-scale vision foundation models (VFMs) like ResNet50, VGG19, and others. These VFMs are increasingly preferred due to their ability to capture complex features, enhancing the accuracy and effectiveness of stress recognition systems. However, no particular focus has been given on combining these VFMs. The combination of VFMs offers promising benefits by harnessing their collective knowledge to extract richer representations for improved stress recognition. So, to mitigate this research gap, we focus on combining different VFMs for stress recognition from ECG and propose SONIC, a novel framework that combines VFMs through their logits and training a fully connected network on the combined logits. Through extensive experimentation, SONIC showed the top performance against individual VFMs performance on the WESAD benchmark. With SONIC, we report state-of-the-art (SOTA) performance in WESAD with 99.36% and 99.24% (stress vs non-stress) and 97.66% and 97.10% (amusement vs stress vs baseline) in accuracy and F1 respectively.