Search

Graph based representation has been widely used in modelling spatio-temporal relationships in video understanding. Although effective, existing graph-based approaches focus on capturing the human-object relationships while ignoring fine-grained semantic properties of the action components. These semantic properties are crucial for understanding the current situation, such as where does the action takes place, what tools are used and functional properties of the objects. In this work, we propose a graph-based representation called Situational Scene Graph (SSG) to encode both human-object relationships and the corresponding semantic properties. The semantic details are represented as predefined roles and values inspired by situation frame, which is originally designed to represent a single action. Based on our proposed representation, we introduce the task of situational scene graph generation and propose a multi-stage pipeline Interactive and Complementary Network (InComNet) to address the task. Given that the existing datasets are not applicable to the task, we further introduce a SSG dataset whose annotations consist of semantic role-value frames for human, objects and verb predicates of human-object relations. Finally, we demonstrate the effectiveness of our proposed SSG representation by testing on different downstream tasks. Experimental results show that the unified representation can not only benefit predicate classification and semantic role-value classification, but also benefit reasoning tasks on human-centric situation understanding. We will release the code and the dataset soon., Comment: Accepted for WACV 2025

Wearable Internet of Things (IoT) devices are gaining ground for continuous physiological data acquisition and health monitoring. These physiological signals can be used for security applications to achieve continuous authentication and user convenience due to passive data acquisition. This paper investigates an electrocardiogram (ECG) based biometric user authentication system using features derived from the Convolutional Neural Network (CNN) and self-supervised contrastive learning. Contrastive learning enables us to use large unlabeled datasets to train the model and establish its generalizability. We propose approaches enabling the CNN encoder to extract appropriate features that distinguish the user from other subjects. When evaluated using the PTB ECG database with 290 subjects, the proposed technique achieved an authentication accuracy of 99.15%. To test its generalizability, we applied the model to two new datasets, the MIT-BIH Arrhythmia Database and the ECG-ID Database, achieving over 98.5% accuracy without any modifications. Furthermore, we show that repeating the authentication step three times can increase accuracy to nearly 100% for both PTBDB and ECGIDDB. This paper also presents model optimizations for embedded device deployment, which makes the system more relevant to real-world scenarios. To deploy our model in IoT edge sensors, we optimized the model complexity by applying quantization and pruning. The optimized model achieves 98.67% accuracy on PTBDB, with 0.48% accuracy loss and 62.6% CPU cycles compared to the unoptimized model. An accuracy-vs-time-complexity tradeoff analysis is performed, and results are presented for different optimization levels.

In this paper, we study the oriented diameter of power graphs of groups. We show that a $2$-edge connected power graph of a finite group has oriented diameter at most $4$. We prove that the power graph of the cyclic group of order $n$ has oriented diameter $2$ for all $n\neq 1,2,4,6$. For non-cyclic finite nilpotent groups, we show that the oriented diameter of corresponding power graphs is at least $3$. Moreover, we provide necessary and sufficient conditions for the oriented diameter of $2$-edge connected power graphs of finite non-cyclic nilpotent groups to be either $3$ or $4$. This, in turn, gives an algorithm for computing the oriented diameter of the power graph of a given nilpotent group that runs in time polynomial in the size of the group., Comment: 25 pages, Corrected typos and references, and Revised some statements

High-resolution Vision-Language Models (VLMs) have been widely used in multimodal tasks to enhance accuracy by preserving detailed image information. However, these models often generate excessive visual tokens due to encoding multiple partitions of the input image. Processing these excessive visual tokens is computationally challenging, especially in resource-constrained environments with commodity GPUs. To support high-resolution images while meeting resource constraints, we propose High-Resolution Early Dropping (HiRED), a token-dropping scheme that operates within a fixed token budget before the Large Language Model (LLM) stage. HiRED can be integrated with existing high-resolution VLMs in a plug-and-play manner, as it requires no additional training while still maintaining superior accuracy. We strategically use the vision encoder's attention in the initial layers to assess the visual content of each image partition and allocate the token budget accordingly. Then, using the attention in the final layer, we select the most important visual tokens from each partition within the allocated budget, dropping the rest. Empirically, when applied to LLaVA-Next-7B on NVIDIA TESLA P40 GPU, HiRED with a 20% token budget increases token generation throughput by 4.7, reduces first-token generation latency by 15 seconds, and saves 2.3 GB of GPU memory for a single inference., Comment: Preprint

This paper explores the adaptation of Transformerbased models for edge devices through the quantisation and hardware acceleration of the ARM Keyword Transformer (KWT) model on a RISC-V platform. The model was targeted to run on 64kB RAM in bare-metal C using a custom-developed edge AI library. KWT-1 was retrained to be 369 times smaller, with only a 10% loss in accuracy through reducing output classes from 35 to 2. The retraining and quantisation reduced model size from 2.42 MB to 1.65 kB. The integration of custom RISC-V instructions that accelerated GELU and SoftMax operations enabled a 5x speedup and thus ~5x power reduction in inference, with inference clock cycle counts decreasing from 26 million to 5.5 million clock cycles while incurring a small area overhead of approximately 29%. The results demonstrate a viable method for porting and accelerating Transformer-based models in low-power IoT devices., Comment: 6 pages, 7 figures, accepted to be published in the IEEE SOCC 2024 conference

The DIarization of SPeaker and LAnguage in Conversational Environments (DISPLACE) 2024 challenge is the second in the series of DISPLACE challenges, which involves tasks of speaker diarization (SD) and language diarization (LD) on a challenging multilingual conversational speech dataset. In the DISPLACE 2024 challenge, we also introduced the task of automatic speech recognition (ASR) on this dataset. The dataset containing 158 hours of speech, consisting of both supervised and unsupervised mono-channel far-field recordings, was released for LD and SD tracks. Further, 12 hours of close-field mono-channel recordings were provided for the ASR track conducted on 5 Indian languages. The details of the dataset, baseline systems and the leader board results are highlighted in this paper. We have also compared our baseline models and the team's performances on evaluation data of DISPLACE-2023 to emphasize the advancements made in this second version of the challenge., Comment: 5 pages, 3 figures, Interspeech 2024

The intricate interplay between spin and lattice degrees of freedom in two-dimensional magnetic materials plays a pivotal role in modifying their magnetic characteristics, engendering hybrid quasiparticles, and implementing functional devices. Herein, we present our comprehensive and in-depth investigations on magnetic and lattice excitations of MnPSe3-xSx (x = 0, 0.5, and 1.5) alloys, utilizing temperature- and polarization-dependent Raman scattering. Our experimental results reveal the occurrence of multiple phase transitions, evidenced by notable changes in phonon self-energy and the appearance or splitting of phonon modes. These emergent phases are tied to the development of long and short-range spin-spin correlations, as well as to spin reorientations or magnetic instabilities. Our analysis of two-magnon excitations as a function of temperature and composition showcases their hybridization with phonons whose degree weakens with increasing x. Moreover, the suppression of spin-dependent phonon intensity in chemically most-disordered MnPSe3-xSx (x = 1.5) suggests that chalcogen substitution offers a control knob of tuning spin and phonon dynamics by modulating concurrently superexchange pathways and a degree of trigonal distortions.

This paper introduces TinySaver, an early-exit-like dynamic model compression approach which employs tiny models to substitute large models adaptively. Distinct from traditional compression techniques, dynamic methods like TinySaver can leverage the difficulty differences to allow certain inputs to complete their inference processes early, thereby conserving computational resources. Most existing early exit designs are implemented by attaching additional network branches to the model's backbone. Our study, however, reveals that completely independent tiny models can replace a substantial portion of the larger models' job with minimal impact on performance. Employing them as the first exit can remarkably enhance computational efficiency. By searching and employing the most appropriate tiny model as the computational saver for a given large model, the proposed approaches work as a novel and generic method to model compression. This finding will help the research community in exploring new compression methods to address the escalating computational demands posed by rapidly evolving AI models. Our evaluation of this approach in ImageNet-1k classification demonstrates its potential to reduce the number of compute operations by up to 90\%, with only negligible losses in performance, across various modern vision models.

Conventional deep learning (DL) model compression and scaling methods focus on altering the model's components, impacting the results across all samples uniformly. However, since samples vary in difficulty, a dynamic model that adapts computation based on sample complexity offers a novel perspective for compression and scaling. Despite this potential, existing dynamic models are typically monolithic and model-specific, limiting their generalizability as broad compression and scaling methods. Additionally, most deployed DL systems are fixed, unable to adjust their scale once deployed and, therefore, cannot adapt to the varying real-time demands. This paper introduces DyCE, a dynamically configurable system that can adjust the performance-complexity trade-off of a DL model at runtime without requiring re-initialization or redeployment on inference hardware. DyCE achieves this by adding small exit networks to intermediate layers of the original model, allowing computation to terminate early if acceptable results are obtained. DyCE also decouples the design of an efficient dynamic model, facilitating easy adaptation to new base models and potential general use in compression and scaling. We also propose methods for generating optimized configurations and determining the types and positions of exit networks to achieve desired performance and complexity trade-offs. By enabling simple configuration switching, DyCE provides fine-grained performance tuning in real-time. We demonstrate the effectiveness of DyCE through image classification tasks using deep convolutional neural networks (CNNs). DyCE significantly reduces computational complexity by 23.5% for ResNet152 and 25.9% for ConvNextv2-tiny on ImageNet, with accuracy reductions of less than 0.5%.

Audio-visual deepfake detection scrutinizes manipulations in public video using complementary multimodal cues. Current methods, which train on fused multimodal data for multimodal targets face challenges due to uncertainties and inconsistencies in learned representations caused by independent modality manipulations in deepfake videos. To address this, we propose cross-modality and within-modality regularization to preserve modality distinctions during multimodal representation learning. Our approach includes an audio-visual transformer module for modality correspondence and a cross-modality regularization module to align paired audio-visual signals, preserving modality distinctions. Simultaneously, a within-modality regularization module refines unimodal representations with modality-specific targets to retain modal-specific details. Experimental results on the public audio-visual dataset, FakeAVCeleb, demonstrate the effectiveness and competitiveness of our approach., Comment: Accepted by ICASSP 2024

Phase transitions with lowering temperature is a manifestation of decreased entropy and within the Landau theoretical framework these are accompanied by the symmetry breaking. Whenever a symmetry is broken weakly or strongly, it leaves its trail and the same may be captured indirectly using renormalization of the quasi-particle excitations. Cr2Ge2Te6, a quasi-two-dimensional magnetic material, provides a rich playground to probe dynamics of the quasi-particle excitations as well as multiple phase transitions with lowering temperature intimately linked with the lattice and spin degrees of freedom. Here, we report in-depth inelastic light scattering measurements on single crystals of Cr2Ge2Te6 as a function of temperature, from 6 K to 330 K, and polarization. Our measurements reveal the long as well as short range ordering of the spins below Tc (~ 60 K) and T* (~ 180 K), respectively; setting the stage for broken rotational and time reversal symmetry, gauged via the distinct renormalization of the phonon self-energy parameters along with the modes intensity. Our measurements also uncovered an intriguing dependence of the interaction strength between discrete state (phonon here) and the underlying continuum, quantified using the Fano asymmetry parameter, as a function of the scattered light polarization. Our results suggest the possibility of tuning the interaction strength using controlled scattered light and symmetry in this 2D magnet.

In multi-lingual societies, where multiple languages are spoken in a small geographic vicinity, informal conversations often involve mix of languages. Existing speech technologies may be inefficient in extracting information from such conversations, where the speech data is rich in diversity with multiple languages and speakers. The DISPLACE (DIarization of SPeaker and LAnguage in Conversational Environments) challenge constitutes an open-call for evaluating and bench-marking the speaker and language diarization technologies on this challenging condition. The challenge entailed two tracks: Track-1 focused on speaker diarization (SD) in multilingual situations while, Track-2 addressed the language diarization (LD) in a multi-speaker scenario. Both the tracks were evaluated using the same underlying audio data. To facilitate this evaluation, a real-world dataset featuring multilingual, multi-speaker conversational far-field speech was recorded and distributed. Furthermore, a baseline system was made available for both SD and LD task which mimicked the state-of-art in these tasks. The challenge garnered a total of $42$ world-wide registrations and received a total of $19$ combined submissions for Track-1 and Track-2. This paper describes the challenge, details of the datasets, tasks, and the baseline system. Additionally, the paper provides a concise overview of the submitted systems in both tracks, with an emphasis given to the top performing systems. The paper also presents insights and future perspectives for SD and LD tasks, focusing on the key challenges that the systems need to overcome before wide-spread commercial deployment on such conversations.

Unsupervised learning methods have become increasingly important in deep learning due to their demonstrated large utilization of datasets and higher accuracy in computer vision and natural language processing tasks. There is a growing trend to extend unsupervised learning methods to other domains, which helps to utilize a large amount of unlabelled data. This paper proposes an unsupervised pre-training technique based on masked autoencoder (MAE) for electrocardiogram (ECG) signals. In addition, we propose a task-specific fine-tuning to form a complete framework for ECG analysis. The framework is high-level, universal, and not individually adapted to specific model architectures or tasks. Experiments are conducted using various model architectures and large-scale datasets, resulting in an accuracy of 94.39% on the MITDB dataset for ECG arrhythmia classification task. The result shows a better performance for the classification of previously unseen data for the proposed approach compared to fully supervised methods., Comment: Accepted by IEEE Biomedical Circuits and Systems (BIOCAS) 2023

In recent years, two competitive time series classification models, namely, ROCKET and MINIROCKET, have garnered considerable attention due to their low training cost and high accuracy. However, they rely on a large number of random 1-D convolutional kernels to comprehensively capture features, which is incompatible with resource-constrained devices. Despite the development of heuristic algorithms designed to recognize and prune redundant kernels, the inherent time-consuming nature of evolutionary algorithms hinders efficient evaluation. To efficiently prune models, this paper eliminates feature groups contributing minimally to the classifier, thereby discarding the associated random kernels without direct evaluation. To this end, we incorporate both group-level ($l_{2,1}$-norm) and element-level ($l_2$-norm) regularizations to the classifier, formulating the pruning challenge as a group elastic net classification problem. An ADMM-based algorithm is initially introduced to solve the problem, but it is computationally intensive. Building on the ADMM-based algorithm, we then propose our core algorithm, POCKET, which significantly speeds up the process by dividing the task into two sequential stages. In Stage 1, POCKET utilizes dynamically varying penalties to efficiently achieve group sparsity within the classifier, removing features associated with zero weights and their corresponding kernels. In Stage 2, the remaining kernels and features are used to refit a $l_2$-regularized classifier for enhanced performance. Experimental results on diverse time series datasets show that POCKET prunes up to 60% of kernels without a significant reduction in accuracy and performs 11$\times$ faster than its counterparts. Our code is publicly available at https://github.com/ShaowuChen/POCKET.

With the significant advancements in artificial intelligence (AI) technologies and powerful computational capabilities, generative AI (GAI) has become a pivotal digital content generation technique for offering superior digital services. However, directing GAI towards desired outputs still suffer the inherent instability of the AI model. In this paper, we design a novel framework that utilizes wireless perception to guide GAI (WiPe-GAI) for providing digital content generation service, i.e., AI-generated content (AIGC), in resource-constrained mobile edge networks. Specifically, we first propose a new sequential multi-scale perception (SMSP) algorithm to predict user skeleton based on the channel state information (CSI) extracted from wireless signals. This prediction then guides GAI to provide users with AIGC, such as virtual character generation. To ensure the efficient operation of the proposed framework in resource constrained networks, we further design a pricing-based incentive mechanism and introduce a diffusion model based approach to generate an optimal pricing strategy for the service provisioning. The strategy maximizes the user's utility while enhancing the participation of the virtual service provider (VSP) in AIGC provision. The experimental results demonstrate the effectiveness of the designed framework in terms of skeleton prediction and optimal pricing strategy generation comparing with other existing solutions.

Training multimodal networks requires a vast amount of data due to their larger parameter space compared to unimodal networks. Active learning is a widely used technique for reducing data annotation costs by selecting only those samples that could contribute to improving model performance. However, current active learning strategies are mostly designed for unimodal tasks, and when applied to multimodal data, they often result in biased sample selection from the dominant modality. This unfairness hinders balanced multimodal learning, which is crucial for achieving optimal performance. To address this issue, we propose three guidelines for designing a more balanced multimodal active learning strategy. Following these guidelines, a novel approach is proposed to achieve more fair data selection by modulating the gradient embedding with the dominance degree among modalities. Our studies demonstrate that the proposed method achieves more balanced multimodal learning by avoiding greedy sample selection from the dominant modality. Our approach outperforms existing active learning strategies on a variety of multimodal classification tasks. Overall, our work highlights the importance of balancing sample selection in multimodal active learning and provides a practical solution for achieving more balanced active learning for multimodal classification., Comment: 12 pages, accepted by ACMMM 2023

Multimodal learning aims to imitate human beings to acquire complementary information from multiple modalities for various downstream tasks. However, traditional aggregation-based multimodal fusion methods ignore the inter-modality relationship, treat each modality equally, suffer sensor noise, and thus reduce multimodal learning performance. In this work, we propose a novel multimodal contrastive method to explore more reliable multimodal representations under the weak supervision of unimodal predicting. Specifically, we first capture task-related unimodal representations and the unimodal predictions from the introduced unimodal predicting task. Then the unimodal representations are aligned with the more effective one by the designed multimodal contrastive method under the supervision of the unimodal predictions. Experimental results with fused features on two image-text classification benchmarks UPMC-Food-101 and N24News show that our proposed Unimodality-Supervised MultiModal Contrastive UniS-MMC learning method outperforms current state-of-the-art multimodal methods. The detailed ablation study and analysis further demonstrate the advantage of our proposed method., Comment: ACL 2023 Findings

In multilingual societies, social conversations often involve code-mixed speech. The current speech technology may not be well equipped to extract information from multi-lingual multi-speaker conversations. The DISPLACE challenge entails a first-of-kind task to benchmark speaker and language diarization on the same data, as the data contains multi-speaker conversations in multilingual code-mixed speech. The challenge attempts to highlight outstanding issues in speaker diarization (SD) in multilingual settings with code-mixing. Further, language diarization (LD) in multi-speaker settings also introduces new challenges, where the system has to disambiguate speaker switches with code switches. For this challenge, a natural multilingual, multi-speaker conversational dataset is distributed for development and evaluation purposes. The systems are evaluated on single-channel far-field recordings. We also release a baseline system and report the highlights of the system submissions.

Resonance Raman scattering, a very effective and sensitive technique for atomically thin semiconducting transition metal dichalcogenide, can be used to observe the phonons from the entire Brillouin zone. In addition to the significance of resonance effect on the Raman spectrum it may also be used to probe the electron-phonon coupling. Our study is devoted to understand the phonons in layered MoS2, especially for very low frequency range (i.e. below 100 cm-1), as a function of temperature under the resonance effect. Understanding the phonon-phonon and electron-phonon coupling and the effects of temperature on the Raman spectrum are the central points of the present study. We observe the anomalous softening and broadening of a very low frequency phonon mode P3 (~34 cm-1) at low temperature ( i.e below 150 K). We attributed the observed anomalous trend in frequency and linewidth of this low frequency phonon to the electron-phonon coupling. Furthermore, our work also highlights the temperature induced tuning of resonance condition via understanding the intensity of phonon modes as a function of temperature.