JoTR: A Joint Transformer and Reinforcement Learning Framework for Dialog Policy Learning

Dialogue policy learning (DPL) is a crucial component of dialogue modelling. Its primary role is to determine the appropriate abstract response, commonly referred to as the "dialogue action". Traditional DPL methodologies have treated this as a sequential decision problem, using pre-defined action candidates extracted from a corpus. However, these incomplete candidates can significantly limit the diversity of responses and pose challenges when dealing with edge cases, which are scenarios that occur only at extreme operating parameters. To address these limitations, we introduce a novel framework, JoTR. This framework is unique as it leverages a text-to-text Transformer-based model to generate flexible dialogue actions. Unlike traditional methods, JoTR formulates a word-level policy that allows for a more dynamic and adaptable dialogue action generation, without the need for any action templates. This setting enhances the diversity of responses and improves the system's ability to handle edge cases effectively. In addition, JoTR employs reinforcement learning with a reward-shaping mechanism to efficiently finetune the word-level dialogue policy, which allows the model to learn from its interactions, improving its performance over time. We conducted an extensive evaluation of JoTR to assess its effectiveness. Our extensive evaluation shows that JoTR achieves state-of-the-art performance on two benchmark dialogue modelling tasks, as assessed by both user simulators and human evaluators.

Retrieving Continuous Time Event Sequences using Neural Temporal Point Processes with Learnable Hashing

Temporal sequences have become pervasive in various real-world applications. Consequently, the volume of data generated in the form of continuous time-event sequence(s) or CTES(s) has increased exponentially in the past few years. Thus, a significant fraction of the ongoing research on CTES datasets involves designing models to address downstream tasks such as next-event prediction, long-term forecasting, sequence classification etc. The recent developments in predictive modeling using marked temporal point processes (MTPP) have enabled an accurate characterization of several real-world applications involving the CTESs. However, due to the complex nature of these CTES datasets, the task of large-scale retrieval of temporal sequences has been overlooked by the past literature. In detail, by CTES retrieval we mean that for an input query sequence, a retrieval system must return a ranked list of relevant sequences from a large corpus. To tackle this, we propose NeuroSeqRet, a first-of-its-kind framework designed specifically for end-to-end CTES retrieval. Specifically, NeuroSeqRet introduces multiple enhancements over standard retrieval frameworks and first applies a trainable unwarping function on the query sequence which makes it comparable with corpus sequences, especially when a relevant query-corpus pair has individually different attributes. Next, it feeds the unwarped query sequence and the corpus sequence into MTPP-guided neural relevance models. We develop four variants of the relevance model for different kinds of applications based on the trade-off between accuracy and efficiency. We also propose an optimization framework to learn binary sequence embeddings from the relevance scores, suitable for the locality-sensitive hashing. Our experiments show the significant accuracy boost of NeuroSeqRet as well as the efficacy of our hashing mechanism.

MTS2Graph: Interpretable Multivariate Time Series Classification with Temporal Evolving Graphs

Conventional time series classification approaches based on bags of patterns or shapelets face significant challenges in dealing with a vast amount of feature candidates from high-dimensional multivariate data. In contrast, deep neural networks can learn low-dimensional features efficiently, and in particular, Convolutional Neural Networks (CNN) have shown promising results in classifying Multivariate Time Series (MTS) data. A key factor in the success of deep neural networks is this astonishing expressive power. However, this power comes at the cost of complex, black-boxed models, conflicting with the goals of building reliable and human-understandable models. An essential criterion in understanding such predictive deep models involves quantifying the contribution of time-varying input variables to the classification. Hence, in this work, we introduce a new framework for interpreting multivariate time series data by extracting and clustering the input representative patterns that highly activate CNN neurons. This way, we identify each signal's role and dependencies, considering all possible combinations of signals in the MTS input. Then, we construct a graph that captures the temporal relationship between the extracted patterns for each layer. An effective graph merging strategy finds the connection of each node to the previous layer's nodes. Finally, a graph embedding algorithm generates new representations of the created interpretable time-series features. To evaluate the performance of our proposed framework, we run extensive experiments on eight datasets of the UCR/UEA archive, along with HAR and PAM datasets. The experiments indicate the benefit of our time-aware graph-based representation in MTS classification while enriching them with more interpretability.

Multi-agent Coordination Under Temporal Logic Tasks and Team-Wise Intermittent Communication

Multi-agent systems outperform single agent in complex collaborative tasks. However, in large-scale scenarios, ensuring timely information exchange during decentralized task execution remains a challenge. This work presents an online decentralized coordination scheme for multi-agent systems under complex local tasks and intermittent communication constraints. Unlike existing strategies that enforce all-time or intermittent connectivity, our approach allows agents to join or leave communication networks at aperiodic intervals, as deemed optimal by their online task execution. This scheme concurrently determines local plans and refines the communication strategy, i.e., where and when to communicate as a team. A decentralized potential game is modeled among agents, for which a Nash equilibrium is generated iteratively through online local search. It guarantees local task completion and intermittent communication constraints. Extensive numerical simulations are conducted against several strong baselines.

HashReID: Dynamic Network with Binary Codes for Efficient Person Re-identification

Biometric applications, such as person re-identification (ReID), are often deployed on energy constrained devices. While recent ReID methods prioritize high retrieval performance, they often come with large computational costs and high search time, rendering them less practical in real-world settings. In this work, we propose an input-adaptive network with multiple exit blocks, that can terminate computation early if the retrieval is straightforward or noisy, saving a lot of computation. To assess the complexity of the input, we introduce a temporal-based classifier driven by a new training strategy. Furthermore, we adopt a binary hash code generation approach instead of relying on continuous-valued features, which significantly improves the search process by a factor of 20. To ensure similarity preservation, we utilize a new ranking regularizer that bridges the gap between continuous and binary features. Extensive analysis of our proposed method is conducted on three datasets: Market1501, MSMT17 (Multi-Scene Multi-Time), and the BGC1 (BRIAR Government Collection). Using our approach, more than 70% of the samples with compact hash codes exit early on the Market1501 dataset, saving 80% of the networks computational cost and improving over other hash-based methods by 60%. These results demonstrate a significant improvement over dynamic networks and showcase comparable accuracy performance to conventional ReID methods. Code will be made available.

Finding the Perfect Fit: Applying Regression Models to ClimateBench v1.0

Climate projections using data driven machine learning models acting as emulators, is one of the prevailing areas of research to enable policy makers make informed decisions. Use of machine learning emulators as surrogates for computationally heavy GCM simulators reduces time and carbon footprints. In this direction, ClimateBench [1] is a recently curated benchmarking dataset for evaluating the performance of machine learning emulators designed for climate data. Recent studies have reported that despite being considered fundamental, regression models offer several advantages pertaining to climate emulations. In particular, by leveraging the kernel trick, regression models can capture complex relationships and improve their predictive capabilities. This study focuses on evaluating non-linear regression models using the aforementioned dataset. Specifically, we compare the emulation capabilities of three non-linear regression models. Among them, Gaussian Process Regressor demonstrates the best-in-class performance against standard evaluation metrics used for climate field emulation studies. However, Gaussian Process Regression suffers from being computational resource hungry in terms of space and time complexity. Alternatively, Support Vector and Kernel Ridge models also deliver competitive results and but there are certain trade-offs to be addressed. Additionally, we are actively investigating the performance of composite kernels and techniques such as variational inference to further enhance the performance of the regression models and effectively model complex non-linear patterns, including phenomena like precipitation.

Automated Conversion of Music Videos into Lyric Videos

Musicians and fans often produce lyric videos, a form of music videos that showcase the song's lyrics, for their favorite songs. However, making such videos can be challenging and time-consuming as the lyrics need to be added in synchrony and visual harmony with the video. Informed by prior work and close examination of existing lyric videos, we propose a set of design guidelines to help creators make such videos. Our guidelines ensure the readability of the lyric text while maintaining a unified focus of attention. We instantiate these guidelines in a fully automated pipeline that converts an input music video into a lyric video. We demonstrate the robustness of our pipeline by generating lyric videos from a diverse range of input sources. A user study shows that lyric videos generated by our pipeline are effective in maintaining text readability and unifying the focus of attention.

CPFES: Physical Fitness Evaluation Based on Canadian Agility and Movement Skill Assessment

In recent years, the assessment of fundamental movement skills integrated with physical education has focused on both teaching practice and the feasibility of assessment. The object of assessment has shifted from multiple ages to subdivided ages, while the content of assessment has changed from complex and time-consuming to concise and efficient. Therefore, we apply deep learning to physical fitness evaluation, we propose a system based on the Canadian Agility and Movement Skill Assessment (CAMSA) Physical Fitness Evaluation System (CPFES), which evaluates children's physical fitness based on CAMSA, and gives recommendations based on the scores obtained by CPFES to help children grow. We have designed a landmark detection module and a pose estimation module, and we have also designed a pose evaluation module for the CAMSA criteria that can effectively evaluate the actions of the child being tested. Our experimental results demonstrate the high accuracy of the proposed system.

PV-SSD: A Projection and Voxel-based Double Branch Single-Stage 3D Object Detector

LIDAR-based 3D object detection and classification is crucial for autonomous driving. However, inference in real-time from extremely sparse 3D data poses a formidable challenge. To address this issue, a common approach is to project point clouds onto a bird's-eye or perspective view, effectively converting them into an image-like data format. However, this excessive compression of point cloud data often leads to the loss of information. This paper proposes a 3D object detector based on voxel and projection double branch feature extraction (PV-SSD) to address the problem of information loss. We add voxel features input containing rich local semantic information, which is fully fused with the projected features in the feature extraction stage to reduce the local information loss caused by projection. A good performance is achieved compared to the previous work. In addition, this paper makes the following contributions: 1) a voxel feature extraction method with variable receptive fields is proposed; 2) a feature point sampling method by weight sampling is used to filter out the feature points that are more conducive to the detection task; 3) the MSSFA module is proposed based on the SSFA module. To verify the effectiveness of our method, we designed comparison experiments.

Diffusion Inertial Poser: Human Motion Reconstruction from Arbitrary Sparse IMU Configurations

Motion capture from a limited number of inertial measurement units (IMUs) has important applications in health, human performance, and virtual reality. Real-world limitations and application-specific goals dictate different IMU configurations (i.e., number of IMUs and chosen attachment body segments), trading off accuracy and practicality. Although recent works were successful in accurately reconstructing whole-body motion from six IMUs, these systems only work with a specific IMU configuration. Here we propose a single diffusion generative model, Diffusion Inertial Poser (DiffIP), which reconstructs human motion in real-time from arbitrary IMU configurations. We show that DiffIP has the benefit of flexibility with respect to the IMU configuration while being as accurate as the state-of-the-art for the commonly used six IMU configuration. Our system enables selecting an optimal configuration for different applications without retraining the model. For example, when only four IMUs are available, DiffIP found that the configuration that minimizes errors in joint kinematics instruments the thighs and forearms. However, global translation reconstruction is better when instrumenting the feet instead of the thighs. Although our approach is agnostic to the underlying model, we built DiffIP based on physiologically realistic musculoskeletal models to enable use in biomedical research and health applications.