Multimodal Emotion Recognition in Conversation aims to identify emotions within a dialogue with multimodal data, including audio, visual, and textual features.While existing methods have made significant improvements, there are two fundamental limitations to be addressed.From the modality fusion perspective, current approaches treat all modalities as functionally equivalent during fusion, overlooking their distinct communicative roles and information capacities, in which text conveys explicit semantic meaning while audio provides paralinguistic cues.From the emotion label perspective, many works ignore the continuous structure of emotion characterized by psychological theory and apply uniform penalties regardless of affective proximity.To address these limitations, we propose EMART, EMotion-Wheel-Guided Audio-Referred Text Representation for ERC, specifically focusing on audio and text modalities.First, we propose a modality-aware fusion strategy capturing linguistic features from text as the primary source and audio as a complementary component.Secondly, we propose an emotion-wheelguided supervised contrastive loss to encode emotional proximity based on Russell's circumplex model.Experimental results on IEMO-CAP and MELD demonstrate outstanding performance.The code is available at: https: //github.com/DILAB-HYU/EMART.git.

We address a joint trajectory planning, user association, resource allocation, and power control problem to maximize proportional fairness in the aerial IoT network, considering practical end-to-end quality-of-service (QoS) and communication schedules. Though the problem is rather ancient, apart from the fact that the previous approaches have never considered user- and time-specific QoS, we point out a prevalent mistake in coordinate optimization approaches adopted by the majority of the literature. Coordinate optimization approaches, which repetitively optimize radio resources for a fixed trajectory and vice versa, generally converge to local optima when all variables are differentiable. However, these methods often stagnate at a non-stationary point, significantly degrading the network utility in mixed-integer problems such as joint trajectory and radio resource optimization. We detour this problem by converting the formulated problem into the Markov decision process (MDP). Exploiting the beneficial characteristics of the MDP, we design a non-iterative framework that cooperatively optimizes trajectory and radio resources without initial trajectory choice. The proposed framework can incorporate various trajectory-planning algorithms such as the genetic algorithm, tree search, and reinforcement learning. Extensive comparisons with diverse baselines verify that the proposed framework significantly outperforms the state-of-the-art method, nearly achieving the global optimum. Our implementation code is available athttps://github.com/hslyu/dbspf.

With the widespread adoption of IoT, wearable devices, and sensors, time series data from human subjects are significantly increasing in the healthcare domain. Due to the laborious nature of manual annotation in time series data and the requirement for human experts, self-supervised learning methods are attempted to alleviate the limited label situations. While existing self-supervised methods have been successful to achieve comparable performance to the fully supervised methods, there are still some limitations that need to be addressed, considering the nature of time series data from human subjects: In real-world clinical settings, data labels (e.g., sleep stages) are usually annotated by subject-level, and there is a substantial variation in patterns between subjects. Thus, a model should be designed to deal with not only the label scarcity but also subject-wise nature of data to ensure high performance in real-world scenarios. To mitigate these issues, we propose a novel self-supervised learning framework for human subject time series data: Subject-Aware Time Series Clustering (SA-TSC). In the unsupervised representation learning phase, SA-TSC adopts a subject-wise learning strategy rather than instance-wise learning which randomly samples data instances from different subjects within the batch during training. Specifically, we generate subject-graphs with our graph construction method based on Gumbel-Softmax and perform graph spectral clustering on each subject-graph. In addition, we utilize graph neural networks to capture dependencies between channels and design our own graph learning module motivated from self-supervised loss. Experimental results show the outstanding performance of our SA-TSC with the limited & subject-wise label setting, leading to its high applicability to the healthcare industry. The code is available at: https://github.com/DILAB-HYU/SA-TSC

Deep Neural Networks (DNNs) tend to perform poorly on unseen domains due to domain shifts. Domain Generalization (DG) aims to improve the performance on such scenarios by minimizing the distribution discrepancy between source domains. Among many studies, dropout-based DG approaches which remove domain-specific features have gained attention. However, they are limited in minimizing the upper bound of generalization risk because they do not explicitly consider the distribution discrepancy when discarding features. In this paper, we propose a novel Discrepancy-guided Channel Dropout (DgCD) for DG that explicitly derives the discrepancy between domains and drops the channels with significant distribution discrepancy. Given a training batch, we perform two ways of standardization: (1) based on the variance/mean of the batch (i.e., sampled from all source domains) and (2) based on the variance/mean of domain-wise samples in the batch. With the two normal distributions, we explicitly derive the discrepancy using KL-divergence and backpropagate it towards each channel. A channel with a higher contribution to the discrepancy is more likely to be dropped. Experimental results show the superiority of DgCD over the state-of-the-art DG baselines, demonstrating the effectiveness of our dropout strategy which is directly coupled to reducing the domain discrepancy. Our code is available at: https://github.com/gyeomo/DgCD

Sleep staging is an important task that enables sleep quality assessment and disorder diagnosis. Due to dependency on manually labeled data, many researches have turned from supervised approaches to self-supervised learning (SSL) for sleep staging. While existing SSL methods have made significant progress in terms of its comparable performance to supervised methods, there are still some limitations. Contrastive learning could potentially lead to false negative pair assignments in sleep signal data. Moreover, existing data augmentation techniques directly modify the original signal data, making it likely to lose important information. To mitigate these issues, we propose Self-Supervised Learning with Attention-aided Positive Pairs (SSLAPP). Instead of the contrastive learning, SSLAPP carefully draws high-quality positive pairs and exploits them in representation learning. Here, we propose attention-based latent signal augmentation, which plays a key role by capturing important features without losing valuable signal information. Experimental results show that our proposed method achieves state-of-the-art performance in sleep stage classification with limited labeled data. The code is available at: https://github.com/DILAB-HYU/SSLAPP

To maximize the spectral efficiency while satisfying the increasing mobile traffic demand, LTE can offload downlink traffics to unlicensed UNII bands at 5GHz via the standardized technology LTE-LAA (Licensed Assisted Access). In the scenario where LTE-LAA inevitably coexists with already pervasive WiFi devices which were designed without the consideration of LTE-LAA, recent studies have reported that the asymmetric hidden terminal (AHT) problem, caused by the difference in the listen-before-talk clear-channel-assessment (CCA) thresholds of WiFi and LTE-LAA, severely degrades the throughput and delay performance of both LTE-LAA and WiFi. As a remedy to the AHT problem, we propose a multi-antenna multi-user transmit precoding and power control techniques for LTE-LAA base stations to make neighboring Wi-Fi APs defer their new transmissions, thereby peacefully coexisting with them. The proposed scheme does not require any technical amendment or extra work on the conventional Wi-Fi. Based on our realistic simulator with essential MAC and PHY functions implemented, it is confirmed that the proposed scheme improves the throughput and delay performance of LTE-LAA while maintaining or even improving that of Wi-Fi.

As smart cameras are becoming ubiquitous in mobile robot systems, there is an increasing concern in camera devices invading people's privacy by recording unwanted images. We want to fundamentally protect privacy by blurring unwanted blocks in images, such as faces, yet ensure that the robots can understand the video for their perception. In this paper, we propose a novel mobile robot framework with a deep learning-based privacy-preserving camera system. The proposed camera system detects privacy-sensitive blocks, i.e., human face, from extreme low resolution (LR) images, and then dynamically enhances the resolution of only privacy-insensitive blocks, e.g., backgrounds. Keeping all the face blocks to be extreme LR of 15x15 pixels, we can guarantee that human faces are never at high resolution (HR) in any of processing or memory, thus yielding strong privacy protection even from cracking or backdoors. Our camera system produces an image on a real-time basis, the human faces of which are in extreme LR while the backgrounds are in HR. We experimentally confirm that our proposed face detection camera system outperforms the state-of-the-art small face detection algorithm, while the robot performs ORB-SLAM2 well even with videos of extreme LR faces. Therefore, with the proposed system, we do not too much sacrifice robot perception performance to protect privacy.

Since License Assisted Access LTE (LAA-LTE) employs a conservative energy detection (ED) threshold for transmission to coexist with Wi-Fi in unlicensed bands, the spatial spectrum reuse of LAA-LTE can be significantly impaired. Such non-flexible thresholding has been introduced mainly due to ED's incapability of differentiating Wi-Fi frames from LTE frames. As a remedy, we design and develop an LAA-LTE transmitter based on a software-defined radio system proposing lightweight but effective Wi-Fi frame detection with which an LAA-LTE device can capture a Wi-Fi preamble by only using LTE's own time-domain samples. Experiments confirm the efficacy of the developed system.

License Assisted Access (LAA) LTE (LAA-LTE) is a new type of LTE that aggregates the licensed LTE bands with the unlicensed bands via carrier aggregation. To operate in unlicensed bands, LAA-LTE adopts the listen-before-talk policy and designs its channel access mechanism similar to WLAN's DCF. This paper considers an LAA-LTE eNB coexisting withasymmetric hiddenWi-Fi APs where the eNB can detect the APs while the APs cannot, which is caused by the asymmetric CCA thresholds. The behavior of such a network is modeled by a joint Markov chain (MC), using which steady-state probabilities, throughput, and channel access delay are derived analytically. An extensive evaluation confirms that the proposed analysis correctly models the dynamics of LAA-WLAN coexistence, and identifies important design guidelines for fair coexistence as follows. First, LAA-LTE should enable channel access priority class 4 to exploit its large contention window (CW). Second, LAA-LTE should re-design its CW doubling policy to restore the balance between LAA-LTE and WLAN in throughput and channel access delay. Third, to protect Wi-Fi, the maximum CW stage should be used more times by increasing the retry count.