This paper investigates the orthogonal time frequency space (OTFS) transmission for enabling ultra-reliable low-latency communications (URLLC). To guarantee excellent reliability performance, pragmatic precoder design is an effective and indispensable solution. However, the design requires accurate instantaneous channel state information at the transmitter (ICSIT) which is not always available in practice. Motivated by this, we adopt a deep learning (DL) approach to exploit implicit features from estimated historical delay-Doppler domain channels (DDCs) to directly predict the precoder to be adopted in the next time frame for minimizing the frame error rate (FER), that can further improve the system reliability without the acquisition of ICSIT. To this end, we first establish a predictive transmission protocol and formulate a general problem for the precoder design where a closed-form theoretical FER expression is derived serving as the objective function to characterize the system reliability. Then, we propose a DL-based predictive precoder design framework which exploits an unsupervised learning mechanism to improve the practicability of the proposed scheme. As a realization of the proposed framework, we design a DDCs-aware convolutional long short-term memory (CLSTM) network for the precoder design, where both the convolutional neural network and LSTM modules are adopted to facilitate the spatial-temporal feature extraction from the estimated historical DDCs to further enhance the precoder performance. Simulation results demonstrate that the proposed scheme facilitates a flexible reliability-latency tradeoff and achieves an excellent FER performance that approaches the lower bound obtained by a genie-aided benchmark requiring perfect ICSI at both the transmitter and receiver.
We propose a Spiking Neural Network (SNN)-based explicit numerical scheme for long time integration of time-dependent Ordinary and Partial Differential Equations (ODEs, PDEs). The core element of the method is a SNN, trained to use spike-encoded information about the solution at previous timesteps to predict spike-encoded information at the next timestep. After the network has been trained, it operates as an explicit numerical scheme that can be used to compute the solution at future timesteps, given a spike-encoded initial condition. A decoder is used to transform the evolved spiking-encoded solution back to function values. We present results from numerical experiments of using the proposed method for ODEs and PDEs of varying complexity.
Robot navigation in dynamic environments shared with humans is an important but challenging task, which suffers from performance deterioration as the crowd grows. In this paper, multi-subgoal robot navigation approach based on deep reinforcement learning is proposed, which can reason about more comprehensive relationships among all agents (robot and humans). Specifically, the next position point is planned for the robot by introducing history information and interactions in our work. Firstly, based on subgraph network, the history information of all agents is aggregated before encoding interactions through a graph neural network, so as to improve the ability of the robot to anticipate the future scenarios implicitly. Further consideration, in order to reduce the probability of unreliable next position points, the selection module is designed after policy network in the reinforcement learning framework. In addition, the next position point generated from the selection module satisfied the task requirements better than that obtained directly from the policy network. The experiments demonstrate that our approach outperforms state-of-the-art approaches in terms of both success rate and collision rate, especially in crowded human environments.
We study critical systems that allocate scarce resources to satisfy basic needs, such as homeless services that provide housing. These systems often support communities disproportionately affected by systemic racial, gender, or other injustices, so it is crucial to design these systems with fairness considerations in mind. To address this problem, we propose a framework for evaluating fairness in contextual resource allocation systems that is inspired by fairness metrics in machine learning. This framework can be applied to evaluate the fairness properties of a historical policy, as well as to impose constraints in the design of new (counterfactual) allocation policies. Our work culminates with a set of incompatibility results that investigate the interplay between the different fairness metrics we propose. Notably, we demonstrate that: 1) fairness in allocation and fairness in outcomes are usually incompatible; 2) policies that prioritize based on a vulnerability score will usually result in unequal outcomes across groups, even if the score is perfectly calibrated; 3) policies using contextual information beyond what is needed to characterize baseline risk and treatment effects can be fairer in their outcomes than those using just baseline risk and treatment effects; and 4) policies using group status in addition to baseline risk and treatment effects are as fair as possible given all available information. Our framework can help guide the discussion among stakeholders in deciding which fairness metrics to impose when allocating scarce resources.
This paper presents a portrait stylization method designed for real-time mobile applications with limited style examples available. Previous learning based stylization methods suffer from the geometric and semantic gaps between portrait domain and style domain, which obstacles the style information to be correctly transferred to the portrait images, leading to poor stylization quality. Based on the geometric prior of human facial attributions, we propose to utilize geometric alignment to tackle this issue. Firstly, we apply Thin-Plate-Spline (TPS) on feature maps in the generator network and also directly to style images in pixel space, generating aligned portrait-style image pairs with identical landmarks, which closes the geometric gaps between two domains. Secondly, adversarial learning maps the textures and colors of portrait images to the style domain. Finally, geometric aware cycle consistency preserves the content and identity information unchanged, and deformation invariant constraint suppresses artifacts and distortions. Qualitative and quantitative comparison validate our method outperforms existing methods, and experiments proof our method could be trained with limited style examples (100 or less) in real-time (more than 40 FPS) on mobile devices. Ablation study demonstrates the effectiveness of each component in the framework.
Analyzing defenses in team sports is generally challenging because of the limited event data. Researchers have previously proposed methods to evaluate football team defense by predicting the events of ball gain and being attacked using locations of all players and the ball. However, they did not consider the importance of the events, assumed the perfect observation of all 22 players, and did not fully investigated the influence of the diversity (e.g., nationality and sex). Here, we propose a generalized valuation method of defensive teams by score-scaling the predicted probabilities of the events. Using the open-source location data of all players in broadcast video frames in football games of men's Euro 2020 and women's Euro 2022, we investigated the effect of the number of players on the prediction and validated our approach by analyzing the games. Results show that for the predictions of being attacked, scoring, and conceding, all players' information was not necessary, while that of ball gain required information on three to four offensive and defensive players. With game analyses we explained the excellence in defense of finalist teams in Euro 2020. Our approach might be applicable to location data from broadcast video frames in football games.
Recently, binaural audio synthesis (BAS) has emerged as a promising research field for its applications in augmented and virtual realities. Binaural audio helps us to orient ourselves and establish immersion by providing the brain with interaural time differences reflecting spatial information. However, existing methods are limited in terms of phase estimation, which is crucial for spatial hearing. In this paper, we propose the DopplerBAS method to explicitly address the Doppler effect of the moving sound source. Specifically, we calculate the radial relative velocity of the moving speaker in spherical coordinates, which further guides the synthesis of binaural audio. This simple method neither introduces any additional hyper-parameters nor modifies the loss functions, and is plug-and-play: it scales well to different types of backbones. DopplerBAS distinctly improves WarpNet and BinauralGrad in the phase error metric and reaches a new state-of-the-art: 0.780 (vs. the current state-of-the-art 0.807). Experiments and ablation studies demonstrate the effectiveness of our method.
Autonomous vehicles are being deployed with a spectrum of capability, extending from driver assistance features for the highway in personal vehicles (SAE Level 2+) to fully autonomous fleet ride sharing services operating in complex city environments (SAE Level 4+). This spectrum of autonomy often operates in different physical environments with different degrees of assumed driver in-the-loop oversight and hence have very different system and subsystem requirements. At the heart of SAE Level 2 to 5 systems is localization and mapping, which ranges from road determination for feature geofencing or high-level routing, through lane determination for advanced driver assistance, to where-in-lane positioning for full vehicle control. We assess localization and mapping requirements for different levels of autonomy and supported features. This work provides a framework for system decomposition, including the level of redundancy needed to achieve the target level of safety. We examine several representative autonomous and assistance features and make recommendations on positioning requirements as well map georeferencing and information integrity.
FullSubNet has shown its promising performance on speech enhancement by utilizing both fullband and subband information. However, the relationship between fullband and subband in FullSubNet is achieved by simply concatenating the output of fullband model and subband units. It only supplements the subband units with a small quantity of global information and has not considered the interaction between fullband and subband. This paper proposes a fullband-subband cross-attention (FSCA) module to interactively fuse the global and local information and applies it to FullSubNet. This new framework is called as FS-CANet. Moreover, different from FullSubNet, the proposed FS-CANet optimize the fullband extractor by temporal convolutional network (TCN) blocks to further reduce the model size. Experimental results on DNS Challenge - Interspeech 2021 dataset show that the proposed FS-CANet outperforms other state-of-the-art speech enhancement approaches, and demonstrate the effectiveness of fullband-subband cross-attention.
Video Question Answering methods focus on commonsense reasoning and visual cognition of objects or persons and their interactions over time. Current VideoQA approaches ignore the textual information present in the video. Instead, we argue that textual information is complementary to the action and provides essential contextualisation cues to the reasoning process. To this end, we propose a novel VideoQA task that requires reading and understanding the text in the video. To explore this direction, we focus on news videos and require QA systems to comprehend and answer questions about the topics presented by combining visual and textual cues in the video. We introduce the ``NewsVideoQA'' dataset that comprises more than $8,600$ QA pairs on $3,000+$ news videos obtained from diverse news channels from around the world. We demonstrate the limitations of current Scene Text VQA and VideoQA methods and propose ways to incorporate scene text information into VideoQA methods.