Yan Zhao

Xubo Liu, Qiuqiang Kong, Yan Zhao et al. · bytedance

Language-queried audio source separation (LASS) is a new paradigm for computational auditory scene analysis (CASA). LASS aims to separate a target sound from an audio mixture given a natural language query, which provides a natural and scalable interface for digital audio applications. Recent works on LASS, despite attaining promising separation performance on specific sources (e.g., musical instruments, limited classes of audio events), are unable to separate audio concepts in the open domain. In this work, we introduce AudioSep, a foundation model for open-domain audio source separation with natural language queries. We train AudioSep on large-scale multimodal datasets and extensively evaluate its capabilities on numerous tasks including audio event separation, musical instrument separation, and speech enhancement. AudioSep demonstrates strong separation performance and impressive zero-shot generalization ability using audio captions or text labels as queries, substantially outperforming previous audio-queried and language-queried sound separation models. For reproducibility of this work, we will release the source code, evaluation benchmark and pre-trained model at: https://github.com/Audio-AGI/AudioSep.

Rui Wang, Yan Zhao, Li Song et al.

The rapid development of large language models(LLMs) has led to remarkable advances in natural language processing. However, the increasing scale of these models introduces substantial challenges in terms of storage, transmission, and deployment. Though great efforts have been devoted to model compression and quantization, existing methods often rely on fine-tuning or calibration data, which exhibit limited generalization across different tensor types. In this paper, we argue that video codecs offer a promising solution for LLM compression, due to their inherent compatibility with matrix structured data, configurable compression strategies, and the availability of highly optimized, off-the-shelf implementations. Therefore, we present LLMCodec, a video codec-based LLM compression method that integrates affine quantization with the recent VVC/H.266 video codec. Beyond VVC, we further compare a range of video codecs and encoding profiles to evaluate their impact on compression performance. Experiments on different models demonstrate the robustness and generality of LLMCodec. Notably, on LLaMA-3-8B at 2-bit precision, LLMCodec reduces perplexity by over 1.5x and improves downstream task accuracy by 21% compared with the existing method.

Tung Kieu, Bin Yang, Chenjuan Guo et al.

Time series data occurs widely, and outlier detection is a fundamental problem in data mining, which has numerous applications. Existing autoencoder-based approaches deliver state-of-the-art performance on challenging real-world data but are vulnerable to outliers and exhibit low explainability. To address these two limitations, we propose robust and explainable unsupervised autoencoder frameworks that decompose an input time series into a clean time series and an outlier time series using autoencoders. Improved explainability is achieved because clean time series are better explained with easy-to-understand patterns such as trends and periodicities. We provide insight into this by means of a post-hoc explainability analysis and empirical studies. In addition, since outliers are separated from clean time series iteratively, our approach offers improved robustness to outliers, which in turn improves accuracy. We evaluate our approach on five real-world datasets and report improvements over the state-of-the-art approaches in terms of robustness and explainability. This is an extended version of "Robust and Explainable Autoencoders for Unsupervised Time Series Outlier Detection", to appear in IEEE ICDE 2022.

Cheng Lu, Wenming Zheng, Hailun Lian et al.

Spectrogram is commonly used as the input feature of deep neural networks to learn the high(er)-level time-frequency pattern of speech signal for speech emotion recognition (SER). \textcolor{black}{Generally, different emotions correspond to specific energy activations both within frequency bands and time frames on spectrogram, which indicates the frequency and time domains are both essential to represent the emotion for SER. However, recent spectrogram-based works mainly focus on modeling the long-term dependency in time domain, leading to these methods encountering the following two issues: (1) neglecting to model the emotion-related correlations within frequency domain during the time-frequency joint learning; (2) ignoring to capture the specific frequency bands associated with emotions.} To cope with the issues, we propose an attentive time-frequency neural network (ATFNN) for SER, including a time-frequency neural network (TFNN) and time-frequency attention. Specifically, aiming at the first issue, we design a TFNN with a frequency-domain encoder (F-Encoder) based on the Transformer encoder and a time-domain encoder (T-Encoder) based on the Bidirectional Long Short-Term Memory (Bi-LSTM). The F-Encoder and T-Encoder model the correlations within frequency bands and time frames, respectively, and they are embedded into a time-frequency joint learning strategy to obtain the time-frequency patterns for speech emotions. Moreover, to handle the second issue, we also adopt time-frequency attention with a frequency-attention network (F-Attention) and a time-attention network (T-Attention) to focus on the emotion-related frequency band ranges and time frame ranges, which can enhance the discriminability of speech emotion features.

Dalin Zhang, Kaixuan Chen, Yan Zhao et al.

Deep learning technologies have demonstrated remarkable effectiveness in a wide range of tasks, and deep learning holds the potential to advance a multitude of applications, including in edge computing, where deep models are deployed on edge devices to enable instant data processing and response. A key challenge is that while the application of deep models often incurs substantial memory and computational costs, edge devices typically offer only very limited storage and computational capabilities that may vary substantially across devices. These characteristics make it difficult to build deep learning solutions that unleash the potential of edge devices while complying with their constraints. A promising approach to addressing this challenge is to automate the design of effective deep learning models that are lightweight, require only a little storage, and incur only low computational overheads. This survey offers comprehensive coverage of studies of design automation techniques for deep learning models targeting edge computing. It offers an overview and comparison of key metrics that are used commonly to quantify the proficiency of models in terms of effectiveness, lightness, and computational costs. The survey then proceeds to cover three categories of the state-of-the-art of deep model design automation techniques: automated neural architecture search, automated model compression, and joint automated design and compression. Finally, the survey covers open issues and directions for future research.

Yan Zhao, Jincen Wang, Yuan Zong et al.

In this paper, we propose a novel deep transfer learning method called deep implicit distribution alignment networks (DIDAN) to deal with cross-corpus speech emotion recognition (SER) problem, in which the labeled training (source) and unlabeled testing (target) speech signals come from different corpora. Specifically, DIDAN first adopts a simple deep regression network consisting of a set of convolutional and fully connected layers to directly regress the source speech spectrums into the emotional labels such that the proposed DIDAN can own the emotion discriminative ability. Then, such ability is transferred to be also applicable to the target speech samples regardless of corpus variance by resorting to a well-designed regularization term called implicit distribution alignment (IDA). Unlike widely-used maximum mean discrepancy (MMD) and its variants, the proposed IDA absorbs the idea of sample reconstruction to implicitly align the distribution gap, which enables DIDAN to learn both emotion discriminative and corpus invariant features from speech spectrums. To evaluate the proposed DIDAN, extensive cross-corpus SER experiments on widely-used speech emotion corpora are carried out. Experimental results show that the proposed DIDAN can outperform lots of recent state-of-the-art methods in coping with the cross-corpus SER tasks.

Yan Zhao, Liwei Deng, Xuanhao Chen et al.

The continued digitization of societal processes translates into a proliferation of time series data that cover applications such as fraud detection, intrusion detection, and energy management, where anomaly detection is often essential to enable reliability and safety. Many recent studies target anomaly detection for time series data. Indeed, area of time series anomaly detection is characterized by diverse data, methods, and evaluation strategies, and comparisons in existing studies consider only part of this diversity, which makes it difficult to select the best method for a particular problem setting. To address this shortcoming, we introduce taxonomies for data, methods, and evaluation strategies, provide a comprehensive overview of unsupervised time series anomaly detection using the taxonomies, and systematically evaluate and compare state-of-the-art traditional as well as deep learning techniques. In the empirical study using nine publicly available datasets, we apply the most commonly-used performance evaluation metrics to typical methods under a fair implementation standard. Based on the structuring offered by the taxonomies, we report on empirical studies and provide guidelines, in the form of comparative tables, for choosing the methods most suitable for particular application settings. Finally, we propose research directions for this dynamic field.

Yuchen Zhuang, Xin Shen, Yan Zhao et al. · amazon-science, tsinghua

Sequential recommendation requires understanding the dynamic patterns of users' behaviors, contexts, and preferences from their historical interactions. Most existing works focus on modeling user-item interactions only from the item level, ignoring that they are driven by latent shopping intentions (e.g., ballpoint pens, miniatures, etc). The detection of the underlying shopping intentions of users based on their historical interactions is a crucial aspect for e-commerce platforms, such as Amazon, to enhance the convenience and efficiency of their customers' shopping experiences. Despite its significance, the area of main shopping intention detection remains under-investigated in the academic literature. To fill this gap, we propose a graph-regularized stochastic Transformer method, G-STO. By considering intentions as sets of products and user preferences as compositions of intentions, we model both of them as stochastic Gaussian embeddings in the latent representation space. Instead of training the stochastic representations from scratch, we develop a global intention relational graph as prior knowledge for regularization, allowing relevant shopping intentions to be distributionally close. Finally, we feed the newly regularized stochastic embeddings into Transformer-based models to encode sequential information from the intention transitions. We evaluate our main shopping intention identification model on three different real-world datasets, where G-STO achieves significantly superior performances to the baselines by 18.08% in Hit@1, 7.01% in Hit@10, and 6.11% in NDCG@10 on average.

Weizhu Qian, Dalin Zhang, Yan Zhao et al.

Uncertainty is an essential consideration for time series forecasting tasks. In this work, we specifically focus on quantifying the uncertainty of traffic forecasting. To achieve this, we develop Deep Spatio-Temporal Uncertainty Quantification (DeepSTUQ), which can estimate both aleatoric and epistemic uncertainty. We first leverage a spatio-temporal model to model the complex spatio-temporal correlations of traffic data. Subsequently, two independent sub-neural networks maximizing the heterogeneous log-likelihood are developed to estimate aleatoric uncertainty. For estimating epistemic uncertainty, we combine the merits of variational inference and deep ensembling by integrating the Monte Carlo dropout and the Adaptive Weight Averaging re-training methods, respectively. Finally, we propose a post-processing calibration approach based on Temperature Scaling, which improves the model's generalization ability to estimate uncertainty. Extensive experiments are conducted on four public datasets, and the empirical results suggest that the proposed method outperforms state-of-the-art methods in terms of both point prediction and uncertainty quantification.

Zhichen Lai, Dalin Zhang, Huan Li et al.

Correlated time series (CTS) forecasting plays an essential role in many practical applications, such as traffic management and server load control. Many deep learning models have been proposed to improve the accuracy of CTS forecasting. However, while models have become increasingly complex and computationally intensive, they struggle to improve accuracy. Pursuing a different direction, this study aims instead to enable much more efficient, lightweight models that preserve accuracy while being able to be deployed on resource-constrained devices. To achieve this goal, we characterize popular CTS forecasting models and yield two observations that indicate directions for lightweight CTS forecasting. On this basis, we propose the LightCTS framework that adopts plain stacking of temporal and spatial operators instead of alternate stacking that is much more computationally expensive. Moreover, LightCTS features light temporal and spatial operator modules, called L-TCN and GL-Former, that offer improved computational efficiency without compromising their feature extraction capabilities. LightCTS also encompasses a last-shot compression scheme to reduce redundant temporal features and speed up subsequent computations. Experiments with single-step and multi-step forecasting benchmark datasets show that LightCTS is capable of nearly state-of-the-art accuracy at much reduced computational and storage overheads.

Yan Zhao, Ruihai Wu, Zhehuan Chen et al.

It is essential yet challenging for future home-assistant robots to understand and manipulate diverse 3D objects in daily human environments. Towards building scalable systems that can perform diverse manipulation tasks over various 3D shapes, recent works have advocated and demonstrated promising results learning visual actionable affordance, which labels every point over the input 3D geometry with an action likelihood of accomplishing the downstream task (e.g., pushing or picking-up). However, these works only studied single-gripper manipulation tasks, yet many real-world tasks require two hands to achieve collaboratively. In this work, we propose a novel learning framework, DualAfford, to learn collaborative affordance for dual-gripper manipulation tasks. The core design of the approach is to reduce the quadratic problem for two grippers into two disentangled yet interconnected subtasks for efficient learning. Using the large-scale PartNet-Mobility and ShapeNet datasets, we set up four benchmark tasks for dual-gripper manipulation. Experiments prove the effectiveness and superiority of our method over three baselines.

Junwei You, Pei Li, Zhuoyu Jiang et al.

Multimodal large language models (MLLMs) have shown strong potential for autonomous driving, yet existing benchmarks remain largely ego-centric and therefore cannot systematically assess model performance in infrastructure-centric and cooperative driving conditions. In this work, we introduce V2X-QA, a real-world dataset and benchmark for evaluating MLLMs across vehicle-side, infrastructure-side, and cooperative viewpoints. V2X-QA is built around a view-decoupled evaluation protocol that enables controlled comparison under vehicle-only, infrastructure-only, and cooperative driving conditions within a unified multiple-choice question answering (MCQA) framework. The benchmark is organized into a twelve-task taxonomy spanning perception, prediction, and reasoning and planning, and is constructed through expert-verified MCQA annotation to enable fine-grained diagnosis of viewpoint-dependent capabilities. Benchmark results across ten representative state-of-the-art proprietary and open-source models show that viewpoint accessibility substantially affects performance, and infrastructure-side reasoning supports meaningful macroscopic traffic understanding. Results also indicate that cooperative reasoning remains challenging since it requires cross-view alignment and evidence integration rather than simply additional visual input. To address these challenges, we introduce V2X-MoE, a benchmark-aligned baseline with explicit view routing and viewpoint-specific LoRA experts. The strong performance of V2X-MoE further suggests that explicit viewpoint specialization is a promising direction for multi-view reasoning in autonomous driving. Overall, V2X-QA provides a foundation for studying multi-perspective reasoning, reliability, and cooperative physical intelligence in connected autonomous driving. The dataset and V2X-MoE resources are publicly available at: https://github.com/junwei0001/V2X-QA.

Ruihai Wu, Chenrui Tie, Yushi Du et al.

Shape assembly aims to reassemble parts (or fragments) into a complete object, which is a common task in our daily life. Different from the semantic part assembly (e.g., assembling a chair's semantic parts like legs into a whole chair), geometric part assembly (e.g., assembling bowl fragments into a complete bowl) is an emerging task in computer vision and robotics. Instead of semantic information, this task focuses on geometric information of parts. As the both geometric and pose space of fractured parts are exceptionally large, shape pose disentanglement of part representations is beneficial to geometric shape assembly. In our paper, we propose to leverage SE(3) equivariance for such shape pose disentanglement. Moreover, while previous works in vision and robotics only consider SE(3) equivariance for the representations of single objects, we move a step forward and propose leveraging SE(3) equivariance for representations considering multi-part correlations, which further boosts the performance of the multi-part assembly. Experiments demonstrate the significance of SE(3) equivariance and our proposed method for geometric shape assembly. Project page: https://crtie.github.io/SE-3-part-assembly/

Sunan Li, Hailun Lian, Cheng Lu et al.

The emotion recognition has attracted more attention in recent decades. Although significant progress has been made in the recognition technology of the seven basic emotions, existing methods are still hard to tackle compound emotion recognition that occurred commonly in practical application. This article introduces our achievements in the 7th Field Emotion Behavior Analysis (ABAW) competition. In the competition, we selected pre trained ResNet18 and Transformer, which have been widely validated, as the basic network framework. Considering the continuity of emotions over time, we propose a time pyramid structure network for frame level emotion prediction. Furthermore. At the same time, in order to address the lack of data in composite emotion recognition, we utilized fine-grained labels from the DFEW database to construct training data for emotion categories in competitions. Taking into account the characteristics of valence arousal of various complex emotions, we constructed a classification framework from coarse to fine in the label space.

Yan Zhao, Zhengxue Cheng, Junxuan Zhang et al.

Lossless compression is essential for efficient data storage and transmission. Although learning-based lossless compressors achieve strong results, most of them are designed for a single modality, leading to redundant compressor deployments in multi-modal settings. Designing a unified multi-modal compressor is critical yet challenging, as different data types vary largely in format, dimension, and statistics. Multi-modal large language models offer a promising resolution but remain too complex for practical use. Thus, we propose \textbf{OmniZip}, \textbf{a unified and lightweight lossless compressor for multi-modal data (like image, text, speech, tactile, database, and gene sequence)}. Built on a lightweight backbone, OmniZip incorporates three key components to enable efficient multi-modal lossless compression: a modality-unified tokenizer that reversibly transforms diverse data into tokens, a modality-routing context learning mechanism that enables flexible multi-modal context modeling, and a modality-routing feedforward design that further enhances the model's nonlinear representation flexibility. A reparameterization training strategy is used to enhance model capacity. OmniZip outperforms or matches other state-of-the-art compressors on multiple modalities, achieving 42\%, 57\%, 62\% and 42\%, 53\% higher compression efficiency than gzip on CLIC-M, TouchandGo, enwik9, LibriSpeech, and WikiSQL datasets, respectively. It also supports near real-time inference on resource-constrained edge devices, reaching about 1MB/s on MacBook CPUs and iPhone NPUs. Our code is released at https://github.com/adminasmi/OmniZip-CVPR2026.

Shichen Zhan, Yebo Wu, Chunlin Tian et al.

Federated learning (FL) coordinates multiple devices to collaboratively train a shared model while preserving data privacy. However, large memory footprint and high energy consumption during the training process excludes the low-end devices from contributing to the global model with their own data, which severely deteriorates the model performance in real-world scenarios. In this paper, we propose FedStitch, a hierarchical coordination framework for heterogeneous federated learning with pre-trained blocks. Unlike the traditional approaches that train the global model from scratch, for a new task, FedStitch composes the global model via stitching pre-trained blocks. Specifically, each participating client selects the most suitable block based on their local data from the candidate pool composed of blocks from pre-trained models. The server then aggregates the optimal block for stitching. This process iterates until a new stitched network is generated. Except for the new training paradigm, FedStitch consists of the following three core components: 1) an RL-weighted aggregator, 2) a search space optimizer deployed on the server side, and 3) a local energy optimizer deployed on each participating client. The RL-weighted aggregator helps to select the right block in the non-IID scenario, while the search space optimizer continuously reduces the size of the candidate block pool during stitching. Meanwhile, the local energy optimizer is designed to minimize energy consumption of each client while guaranteeing the overall training progress. The results demonstrate that compared to existing approaches, FedStitch improves the model accuracy up to 20.93%. At the same time, it achieves up to 8.12% speedup, reduces the memory footprint up to 79.5%, and achieves 89.41% energy saving at most during the learning procedure.

Chen Zheng, Huan Zhang, Yan Zhao et al.

Coherence is a crucial aspect of evaluating text readability and can be assessed through two primary factors when evaluating an essay in a scoring scenario. The first factor is logical coherence, characterized by the appropriate use of discourse connectives and the establishment of logical relationships between sentences. The second factor is the appropriateness of punctuation, as inappropriate punctuation can lead to confused sentence structure. To address these concerns, we propose a coherence scoring model consisting of a regression model with two feature extractors: a local coherence discriminative model and a punctuation correction model. We employ gradient-boosting regression trees as the regression model and impose monotonicity constraints on the input features. The results show that our proposed model better generalizes unseen data. The model achieved third place in track 1 of NLPCC 2023 shared task 7. Additionally, we briefly introduce our solution for the remaining tracks, which achieves second place for track 2 and first place for both track 3 and track 4.

Junxuan Zhang, Zhengxue Cheng, Yan Zhao et al.

Learning-based probabilistic models can be combined with an entropy coder for data compression. However, due to the high complexity of learning-based models, their practical application as text compressors has been largely overlooked. To address this issue, our work focuses on a low-complexity design while maintaining compression performance. We introduce a novel Learned Lossless Low-complexity Text Compression method (L3TC). Specifically, we conduct extensive experiments demonstrating that RWKV models achieve the fastest decoding speed with a moderate compression ratio, making it the most suitable backbone for our method. Second, we propose an outlier-aware tokenizer that uses a limited vocabulary to cover frequent tokens while allowing outliers to bypass the prediction and encoding. Third, we propose a novel high-rank reparameterization strategy that enhances the learning capability during training without increasing complexity during inference. Experimental results validate that our method achieves 48% bit saving compared to gzip compressor. Besides, L3TC offers compression performance comparable to other learned compressors, with a 50x reduction in model parameters. More importantly, L3TC is the fastest among all learned compressors, providing real-time decoding speeds up to megabytes per second. Our code is available at https://github.com/alipay/L3TC-leveraging-rwkv-for-learned-lossless-low-complexity-text-compression.git.

Zhengxue Cheng, Yan Zhao, Keyu Wang et al.

Tactile sensing is crucial for embodied intelligence, providing fine-grained perception and control in complex environments. However, efficient tactile data compression, which is essential for real-time robotic applications under strict bandwidth constraints, remains underexplored. The inherent heterogeneity and spatiotemporal complexity of tactile data further complicate this challenge. To bridge this gap, we introduce TaCo, the first comprehensive benchmark for Tactile data Codecs. TaCo evaluates 30 compression methods, including off-the-shelf compression algorithms and neural codecs, across five diverse datasets from various sensor types. We systematically assess both lossless and lossy compression schemes on four key tasks: lossless storage, human visualization, material and object classification, and dexterous robotic grasping. Notably, we pioneer the development of data-driven codecs explicitly trained on tactile data, TaCo-LL (lossless) and TaCo-L (lossy). Results have validated the superior performance of our TaCo-LL and TaCo-L. This benchmark provides a foundational framework for understanding the critical trade-offs between compression efficiency and task performance, paving the way for future advances in tactile perception.

Chang Liu, Tongyuan Yang, Yan Zhao

There is a hidden energy in tennis, which cannot be seen or touched. It is the force that controls the flow of the game and is present in all types of matches. This mysterious force is Momentum. This study introduces an evaluation model that synergizes the Entropy Weight Method (EWM) and Gray Relation Analysis (GRA) to quantify momentum's impact on match outcomes. Empirical validation was conducted through Mann-Whitney U and Kolmogorov-Smirnov tests, which yielded p values of 0.0043 and 0.00128,respectively. These results underscore the non-random association between momentum shifts and match outcomes, highlighting the critical role of momentum in tennis. Otherwise, our investigation foucus is the creation of a predictive model that combines the advanced machine learning algorithm XGBoost with the SHAP framework. This model enables precise predictions of match swings with exceptional accuracy (0.999013 for multiple matches and 0.992738 for finals). The model's ability to identify the influence of specific factors on match dynamics,such as bilateral distance run during points, demonstrates its prowess.The model's generalizability was thoroughly evaluated using datasets from the four Grand Slam tournaments. The results demonstrate its remarkable adaptability to different match scenarios,despite minor variations in predictive accuracy. It offers strategic insights that can help players effectively respond to opponents' shifts in momentum,enhancing their competitive edge.

Haohe Liu, Qiuqiang Kong, Qiao Tian et al.

Speech restoration aims to remove distortions in speech signals. Prior methods mainly focus on single-task speech restoration (SSR), such as speech denoising or speech declipping. However, SSR systems only focus on one task and do not address the general speech restoration problem. In addition, previous SSR systems show limited performance in some speech restoration tasks such as speech super-resolution. To overcome those limitations, we propose a general speech restoration (GSR) task that attempts to remove multiple distortions simultaneously. Furthermore, we propose VoiceFixer, a generative framework to address the GSR task. VoiceFixer consists of an analysis stage and a synthesis stage to mimic the speech analysis and comprehension of the human auditory system. We employ a ResUNet to model the analysis stage and a neural vocoder to model the synthesis stage. We evaluate VoiceFixer with additive noise, room reverberation, low-resolution, and clipping distortions. Our baseline GSR model achieves a 0.499 higher mean opinion score (MOS) than the speech enhancement SSR model. VoiceFixer further surpasses the GSR baseline model on the MOS score by 0.256. Moreover, we observe that VoiceFixer generalizes well to severely degraded real speech recordings, indicating its potential in restoring old movies and historical speeches. The source code is available at https://github.com/haoheliu/voicefixer_main.

Hao Miao, Yan Zhao, Chenjuan Guo et al.

The widespread deployment of wireless and mobile devices results in a proliferation of spatio-temporal data that is used in applications, e.g., traffic prediction, human mobility mining, and air quality prediction, where spatio-temporal prediction is often essential to enable safety, predictability, or reliability. Many recent proposals that target deep learning for spatio-temporal prediction suffer from so-called catastrophic forgetting, where previously learned knowledge is entirely forgotten when new data arrives. Such proposals may experience deteriorating prediction performance when applied in settings where data streams into the system. To enable spatio-temporal prediction on streaming data, we propose a unified replay-based continuous learning framework. The framework includes a replay buffer of previously learned samples that are fused with training data using a spatio-temporal mixup mechanism in order to preserve historical knowledge effectively, thus avoiding catastrophic forgetting. To enable holistic representation preservation, the framework also integrates a general spatio-temporal autoencoder with a carefully designed spatio-temporal simple siamese (STSimSiam) network that aims to ensure prediction accuracy and avoid holistic feature loss by means of mutual information maximization. The framework further encompasses five spatio-temporal data augmentation methods to enhance the performance of STSimSiam. Extensive experiments on real data offer insight into the effectiveness of the proposed framework.

Fan Xing, Xiaoyi Zhou, Xuefeng Fan et al.

Collected and annotated datasets, which are obtained through extensive efforts, are effective for training Deep Neural Network (DNN) models. However, these datasets are susceptible to be misused by unauthorized users, resulting in infringement of Intellectual Property (IP) rights owned by the dataset creators. Reversible Adversarial Exsamples (RAE) can help to solve the issues of IP protection for datasets. RAEs are adversarial perturbed images that can be restored to the original. As a cutting-edge approach, RAE scheme can serve the purposes of preventing unauthorized users from engaging in malicious model training, as well as ensuring the legitimate usage of authorized users. Nevertheless, in the existing work, RAEs still rely on the embedded auxiliary information for restoration, which may compromise their adversarial abilities. In this paper, a novel self-generation and self-recovery method, named as RAEDiff, is introduced for generating RAEs based on a Denoising Diffusion Probabilistic Models (DDPM). It diffuses datasets into a Biased Gaussian Distribution (BGD) and utilizes the prior knowledge of the DDPM for generating and recovering RAEs. The experimental results demonstrate that RAEDiff effectively self-generates adversarial perturbations for DNN models, including Artificial Intelligence Generated Content (AIGC) models, while also exhibiting significant self-recovery capabilities.

Yan Zhao, Amy Otteson

Not everyone who enrolls in college will leave with a certificate or degree, but the number of people who drop out or take a break is much higher than experts previously believed. In December 2013, there were 29 million people with some college education but no degree. That number jumped to 36 million by December of 2018, according to a new report from the National Student Clearinghouse Research Center[1]. It is imperative to understand the underlying factors contributing to student withdrawal and to assist decision-makers to identify effective strategies to prevent it. By analyzing the characteristics and educational pathways of the stopout student population, our aim is to provide actionable insights that can benefit institutions facing similar challenges. Eastern Michigan University (EMU) faces significant challenges in student retention, with approximately 55% of its undergraduate students not completing their degrees within six years. As an institution committed to student success, EMU conducted a comprehensive study of student withdrawals to understand the influencing factors. And the paper revealed a high correlation between certain factors and withdrawals, even in the early stages of university attendance. Based on these findings, we developed a predictive model that employs artificial intelligence techniques to assess the potential risk that students abandon their studies. These models enable universities to implement early intervention strategies, support at-risk students, and improve overall higher education success.

Lifan Jiang, Boxi Wu, Yuhang Pei et al.

Inversion-free image editing using flow-based generative models challenges the prevailing inversion-based pipelines. However, existing approaches rely on fixed Gaussian noise to construct the source trajectory, leading to biased trajectory dynamics and causing structural degradation or quality loss. To address this, we introduce SNR-Edit, a training-free framework achieving faithful Latent Trajectory Correction via adaptive noise control. Mechanistically, SNR-Edit uses structure-aware noise rectification to inject segmentation constraints into the initial noise, anchoring the stochastic component of the source trajectory to the real image's implicit inversion position and reducing trajectory drift during source--target transport. This lightweight modification yields smoother latent trajectories and ensures high-fidelity structural preservation without requiring model tuning or inversion. Across SD3 and FLUX, evaluations on PIE-Bench and SNR-Bench show that SNR-Edit delivers performance on pixel-level metrics and VLM-based scoring, while adding only about 1s overhead per image.

Chenxi Liu, Hao Miao, Qianxiong Xu et al.

Multivariate time series forecasting (MTSF) endeavors to predict future observations given historical data, playing a crucial role in time series data management systems. With advancements in large language models (LLMs), recent studies employ textual prompt tuning to infuse the knowledge of LLMs into MTSF. However, the deployment of LLMs often suffers from low efficiency during the inference phase. To address this problem, we introduce TimeKD, an efficient MTSF framework that leverages the calibrated language models and privileged knowledge distillation. TimeKD aims to generate high-quality future representations from the proposed cross-modality teacher model and cultivate an effective student model. The cross-modality teacher model adopts calibrated language models (CLMs) with ground truth prompts, motivated by the paradigm of Learning Under Privileged Information (LUPI). In addition, we design a subtractive cross attention (SCA) mechanism to refine these representations. To cultivate an effective student model, we propose an innovative privileged knowledge distillation (PKD) mechanism including correlation and feature distillation. PKD enables the student to replicate the teacher's behavior while minimizing their output discrepancy. Extensive experiments on real data offer insight into the effectiveness, efficiency, and scalability of the proposed TimeKD.

Lifan Jiang, Yuhang Pei, oxi Wu et al.

Recent advances in MLLMs are reframing segmentation from fixed-category prediction to instruction-grounded localization. While reasoning based segmentation has progressed rapidly in natural scenes, remote sensing lacks a generalizable solution due to the prohibitive cost of reasoning-oriented data and domain-specific challenges like overhead viewpoints. We present GeoSeg, a zero-shot, training-free framework that bypasses the supervision bottleneck for reasoning-driven remote sensing segmentation. GeoSeg couples MLLM reasoning with precise localization via: (i) bias-aware coordinate refinement to correct systematic grounding shifts and (ii) a dual-route prompting mechanism to fuse semantic intent with fine-grained spatial cues. We also introduce GeoSeg-Bench, a diagnostic benchmark of 810 image--query pairs with hierarchical difficulty levels. Experiments show that GeoSeg consistently outperforms all baselines, with extensive ablations confirming the effectiveness and necessity of each component.

Zhichen Lai, Huan Li, Dalin Zhang et al.

Cyber-physical system sensors emit multivariate time series (MTS) that monitor physical system processes. Such time series generally capture unknown numbers of states, each with a different duration, that correspond to specific conditions, e.g., "walking" or "running" in human-activity monitoring. Unsupervised identification of such states facilitates storage and processing in subsequent data analyses, as well as enhances result interpretability. Existing state-detection proposals face three challenges. First, they introduce substantial computational overhead, rendering them impractical in resourceconstrained or streaming settings. Second, although state-of-the-art (SOTA) proposals employ contrastive learning for representation, insufficient attention to false negatives hampers model convergence and accuracy. Third, SOTA proposals predominantly only emphasize offline non-streaming deployment, we highlight an urgent need to optimize online streaming scenarios. We propose E2Usd that enables efficient-yet-accurate unsupervised MTS state detection. E2Usd exploits a Fast Fourier Transform-based Time Series Compressor (fftCompress) and a Decomposed Dual-view Embedding Module (ddEM) that together encode input MTSs at low computational overhead. Additionally, we propose a False Negative Cancellation Contrastive Learning method (fnccLearning) to counteract the effects of false negatives and to achieve more cluster-friendly embedding spaces. To reduce computational overhead further in streaming settings, we introduce Adaptive Threshold Detection (adaTD). Comprehensive experiments with six baselines and six datasets offer evidence that E2Usd is capable of SOTA accuracy at significantly reduced computational overhead.

Jun Zhang, Huan Li, Dazhong Rong et al.

Privacy concerns have led to the rise of federated recommender systems (FRS), which can create personalized models across distributed clients. However, FRS is vulnerable to poisoning attacks, where malicious users manipulate gradients to promote their target items intentionally. Existing attacks against FRS have limitations, as they depend on specific models and prior knowledge, restricting their real-world applicability. In our exploration of practical FRS vulnerabilities, we devise a model-agnostic and prior-knowledge-free attack, named PIECK (Popular Item Embedding based Attack). The core module of PIECK is popular item mining, which leverages embedding changes during FRS training to effectively identify the popular items. Built upon the core module, PIECK branches into two diverse solutions: The PIECKIPE solution employs an item popularity enhancement module, which aligns the embeddings of targeted items with the mined popular items to increase item exposure. The PIECKUEA further enhances the robustness of the attack by using a user embedding approximation module, which approximates private user embeddings using mined popular items. Upon identifying PIECK, we evaluate existing federated defense methods and find them ineffective against PIECK, as poisonous gradients inevitably overwhelm the cold target items. We then propose a novel defense method by introducing two regularization terms during user training, which constrain item popularity enhancement and user embedding approximation while preserving FRS performance. We evaluate PIECK and its defense across two base models, three real datasets, four top-tier attacks, and six general defense methods, affirming the efficacy of both PIECK and its defense.

Liwei Deng, Tianfu Wang, Yan Zhao et al.

Portfolio management is an important yet challenging task in AI for FinTech, which aims to allocate investors' budgets among different assets to balance the risk and return of an investment. In this study, we propose a general Multi-objectIve framework with controLLable rIsk for pOrtfolio maNagement (MILLION), which consists of two main phases, i.e., return-related maximization and risk control. Specifically, in the return-related maximization phase, we introduce two auxiliary objectives, i.e., return rate prediction, and return rate ranking, combined with portfolio optimization to remit the overfitting problem and improve the generalization of the trained model to future markets. Subsequently, in the risk control phase, we propose two methods, i.e., portfolio interpolation and portfolio improvement, to achieve fine-grained risk control and fast risk adaption to a user-specified risk level. For the portfolio interpolation method, we theoretically prove that the risk can be perfectly controlled if the to-be-set risk level is in a proper interval. In addition, we also show that the return rate of the adjusted portfolio after portfolio interpolation is no less than that of the min-variance optimization, as long as the model in the reward maximization phase is effective. Furthermore, the portfolio improvement method can achieve greater return rates while keeping the same risk level compared to portfolio interpolation. Extensive experiments are conducted on three real-world datasets. The results demonstrate the effectiveness and efficiency of the proposed framework.

Yuchen Fang, Hao Miao, Yuxuan Liang et al.

Spatio-temporal deep learning models aims to utilize useful patterns in such data to support tasks like prediction. However, previous deep learning models designed for specific tasks typically require separate training for each use case, leading to increased computational and storage costs. To address this issue, spatio-temporal foundation models have emerged, offering a unified framework capable of solving multiple spatio-temporal tasks. These foundation models achieve remarkable success by learning general knowledge with spatio-temporal data or transferring the general capabilities of pre-trained language models. While previous surveys have explored spatio-temporal data and methodologies separately, they have ignored a comprehensive examination of how foundation models are designed, selected, pre-trained, and adapted. As a result, the overall pipeline for spatio-temporal foundation models remains unclear. To bridge this gap, we innovatively provide an up-to-date review of previous spatio-temporal foundation models from the pipeline perspective. The pipeline begins with an introduction to different types of spatio-temporal data, followed by details of data preprocessing and embedding techniques. The pipeline then presents a novel data property taxonomy to divide existing methods according to data sources and dependencies, providing efficient and effective model design and selection for researchers. On this basis, we further illustrate the training objectives of primitive models, as well as the adaptation techniques of transferred models. Overall, our survey provides a clear and structured pipeline to understand the connection between core elements of spatio-temporal foundation models while guiding researchers to get started quickly. Additionally, we introduce emerging opportunities such as multi-objective training in the field of spatio-temporal foundation models.

Yan Zhao, Zhongyun Li, Yushan Pan et al.

Generative Artificial Intelligence (AI), because of its emergent abilities, has empowered various fields, one typical of which is large language models (LLMs). One of the typical application fields of Generative AI is large language models (LLMs), and the natural language understanding capability of LLM is dramatically improved when compared with conventional AI-based methods. The natural language understanding capability has always been a barrier to the intent recognition performance of the Knowledge-Based-Question-and-Answer (KBQA) system, which arises from linguistic diversity and the newly appeared intent. Conventional AI-based methods for intent recognition can be divided into semantic parsing-based and model-based approaches. However, both of the methods suffer from limited resources in intent recognition. To address this issue, we propose a novel KBQA system based on a Large Language Model(LLM) and BERT (LB-KBQA). With the help of generative AI, our proposed method could detect newly appeared intent and acquire new knowledge. In experiments on financial domain question answering, our model has demonstrated superior effectiveness.

Yan Zhao, Amy Otteson

Enrollment projection is a critical aspect of university management, guiding decisions related to resource allocation and revenue forecasting. However, despite its importance, there remains a lack of transparency regarding the methodologies utilized by many institutions. This paper presents an innovative approach to enrollment projection using Markov Chain modeling, drawing upon a case study conducted at Eastern Michigan University (EMU). Markov Chain modeling emerges as a promising approach for enrollment projection, offering precise predictions based on historical trends. This paper outlines the implementation of Enhanced Markov Chain modeling at EMU, detailing the methodology used to compute transition probabilities and evaluate model performance. Despite challenges posed by external uncertainties such as the COVID-19 pandemic, Markov Chain modeling has demonstrated impressive accuracy, with an average difference of less than 1 percent between predicted and actual enrollments. The paper concludes with a discussion of future directions and opportunities for collaboration among institutions.

Jinwen Chen, Jiannan Guo, Dazhuo Qiu et al.

With the rapid advancement of mobile networks and the widespread use of mobile devices, spatial crowdsourcing, which involves assigning location-based tasks to mobile workers, has gained significant attention. However, most existing research focuses on task assignment at the current moment, overlooking the fluctuating demand and supply between tasks and workers over time. To address this issue, we introduce an adaptive task assignment problem, which aims to maximize the number of assigned tasks by dynamically adjusting task assignments in response to changing demand and supply. We develop a spatial crowdsourcing framework, namely demand-based adaptive task assignment with dynamic worker availability windows, which consists of two components including task demand prediction and task assignment. In the first component, we construct a graph adjacency matrix representing the demand dependency relationships in different regions and employ a multivariate time series learning approach to predict future task demands. In the task assignment component, we adjust tasks to workers based on these predictions, worker availability windows, and the current task assignments, where each worker has an availability window that indicates the time periods they are available for task assignments. To reduce the search space of task assignments and be efficient, we propose a worker dependency separation approach based on graph partition and a task value function with reinforcement learning. Experiments on real data demonstrate that our proposals are both effective and efficient.

Yuyang Xia, Zibo Liang, Liwei Deng et al.

Autonomous driving is an emerging technology that is expected to bring significant social, economic, and environmental benefits. However, these benefits come with rising energy consumption by computation engines, limiting the driving range of vehicles, especially electric ones. Perception computing is typically the most power-intensive component, as it relies on largescale deep learning models to extract environmental features. Recently, numerous studies have employed model compression techniques, such as sparsification, quantization, and distillation, to reduce computational consumption. However, these methods often result in either a substantial model size or a significant drop in perception accuracy compared to high-computation models. To address these challenges, we propose an energy-efficient autonomous driving framework, called EneAD. In the adaptive perception module, a perception optimization strategy is designed from the perspective of data management and tuning. Firstly, we manage multiple perception models with different computational consumption and adjust the execution framerate dynamically. Then, we define them as knobs and design a transferable tuning method based on Bayesian optimization to identify promising knob values that achieve low computation while maintaining desired accuracy. To adaptively switch the knob values in various traffic scenarios, a lightweight classification model is proposed to distinguish the perception difficulty in different scenarios. In the robust decision module, we propose a decision model based on reinforcement learning and design a regularization term to enhance driving stability in the face of perturbed perception results. Extensive experiments evidence the superiority of our framework in both energy consumption and driving performance. EneAD can reduce perception consumption by 1.9x to 3.5x and thus improve driving range by 3.9% to 8.5%

Kangjia Yan, Chenxi Liu, Hao Miao et al.

The proliferation of mobile devices generates a massive volume of time series across various domains, where effective time series forecasting enables a variety of real-world applications. This study focuses on a new problem of source-free domain adaptation for time series forecasting. It aims to adapt a pretrained model from sufficient source time series to the sparse target time series domain without access to the source data, embracing data protection regulations. To achieve this, we propose TimePD, the first source-free time series forecasting framework with proxy denoising, where large language models (LLMs) are employed to benefit from their generalization capabilities. Specifically, TimePD consists of three key components: (1) dual-branch invariant disentangled feature learning that enforces representation- and gradient-wise invariance by means of season-trend decomposition; (2) lightweight, parameter-free proxy denoising that dynamically calibrates systematic biases of LLMs; and (3) knowledge distillation that bidirectionally aligns the denoised prediction and the original target prediction. Extensive experiments on real-world datasets offer insight into the effectiveness of the proposed TimePD, outperforming SOTA baselines by 9.3% on average.

Chenxi Liu, Hao Miao, Cheng Long et al.

Large Language Models (LLMs) have emerged as a promising paradigm for time series analytics, leveraging their massive parameters and the shared sequential nature of textual and time series data. However, a cross-modality gap exists between time series and textual data, as LLMs are pre-trained on textual corpora and are not inherently optimized for time series. In this tutorial, we provide an up-to-date overview of LLM-based cross-modal time series analytics. We introduce a taxonomy that classifies existing approaches into three groups based on cross-modal modeling strategies, e.g., conversion, alignment, and fusion, and then discuss their applications across a range of downstream tasks. In addition, we summarize several open challenges. This tutorial aims to expand the practical application of LLMs in solving real-world problems in cross-modal time series analytics while balancing effectiveness and efficiency. Participants will gain a thorough understanding of current advancements, methodologies, and future research directions in cross-modal time series analytics.

Wenkang Zhang, Yan Zhao, Qiang Wang et al.

Free-viewpoint video (FVV) enables immersive 3D experiences, but efficient compression of dynamic 3D representations remains a major challenge. Recent advances in 3D Gaussian Splatting (3DGS) and its dynamic extensions have enabled high-fidelity scene modeling. However, existing methods often couple scene reconstruction with optimization-dependent coding, which limits generalizability. This paper presents Feedforward Compression of Dynamic Gaussian Splatting (D-FCGS), a novel feedforward framework for compressing temporally correlated Gaussian point cloud sequences. Our approach introduces a Group-of-Frames (GoF) structure with I-P frame coding, where inter-frame motions are extracted via sparse control points. The resulting motion tensors are compressed in a feedforward manner using a dual prior-aware entropy model that combines hyperprior and spatial-temporal priors for accurate rate estimation. For reconstruction, we perform control-point-guided motion compensation and employ a refinement network to enhance view-consistent fidelity. Trained on multi-view video-derived Gaussian frames, D-FCGS generalizes across scenes without per-scene optimization. Experiments show that it matches the rate-distortion performance of optimization-based methods, achieving over 40 times compression in under 2 seconds while preserving visual quality across viewpoints. This work advances feedforward compression for dynamic 3DGS, paving the way for scalable FVV transmission and storage in immersive applications.

Zhixun Chen, Ping Guo, Wenhan Han et al.

Data quality is a critical driver of large language model performance, yet existing model-based selection methods focus almost exclusively on English. We introduce MuRating, a scalable framework that transfers high-quality English data-quality signals into a single rater for 17 target languages. MuRating aggregates multiple English "raters" via pairwise comparisons to learn unified document-quality scores,then projects these judgments through translation to train a multilingual evaluator on monolingual, cross-lingual, and parallel text pairs. Applied to web data, MuRating selects balanced subsets of English and multilingual content to pretrain a 1.2 B-parameter LLaMA model. Compared to strong baselines, including QuRater, AskLLM, DCLM and so on, our approach boosts average accuracy on both English benchmarks and multilingual evaluations, with especially large gains on knowledge-intensive tasks. We further analyze translation fidelity, selection biases, and underrepresentation of narrative material, outlining directions for future work.

Yan Zhao, Zhengxue Cheng, Junxuan Zhang et al.

Most learning-based lossless compressors are designed for a single modality, requiring separate models for multi-modal data and lacking flexibility. However, different modalities vary significantly in format and statistical properties, making it ineffective to use compressors that lack modality-specific adaptations. While multi-modal large language models (MLLMs) offer a potential solution for modality-unified compression, their excessive complexity hinders practical deployment. To address these challenges, we focus on the two most common modalities, image and text, and propose DualComp, the first unified and lightweight learning-based dual-modality lossless compressor. Built on a lightweight backbone, DualComp incorporates three key structural enhancements to handle modality heterogeneity: modality-unified tokenization, modality-switching contextual learning, and modality-routing mixture-of-experts. A reparameterization training strategy is also used to boost compression performance. DualComp integrates both modality-specific and shared parameters for efficient parameter utilization, enabling near real-time inference (200KB/s) on desktop CPUs. With much fewer parameters, DualComp achieves compression performance on par with the SOTA LLM-based methods for both text and image datasets. Its simplified single-modality variant surpasses the previous best image compressor on the Kodak dataset by about 9% using just 1.2% of the model size.

Zunjie Zhu, Yan Zhao, Yihan Hu et al.

The motion capture system that supports full-body virtual representation is of key significance for virtual reality. Compared to vision-based systems, full-body pose estimation from sparse tracking signals is not limited by environmental conditions or recording range. However, previous works either face the challenge of wearing additional sensors on the pelvis and lower-body or rely on external visual sensors to obtain global positions of key joints. To improve the practicality of the technology for virtual reality applications, we estimate full-body poses using only inertial data obtained from three Inertial Measurement Unit (IMU) sensors worn on the head and wrists, thereby reducing the complexity of the hardware system. In this work, we propose a method called Progressive Inertial Poser (ProgIP) for human pose estimation, which combines neural network estimation with a human dynamics model, considers the hierarchical structure of the kinematic chain, and employs a multi-stage progressive network estimation with increased depth to reconstruct full-body motion in real time. The encoder combines Transformer Encoder and bidirectional LSTM (TE-biLSTM) to flexibly capture the temporal dependencies of the inertial sequence, while the decoder based on multi-layer perceptrons (MLPs) transforms high-dimensional features and accurately projects them onto Skinned Multi-Person Linear (SMPL) model parameters. Quantitative and qualitative experimental results on multiple public datasets show that our method outperforms state-of-the-art methods with the same inputs, and is comparable to recent works using six IMU sensors.

Bowen Zhang, Ying Chen, Long Bai et al.

Foundation models have become prominent in computer vision, achieving notable success in various tasks. However, their effectiveness largely depends on pre-training with extensive datasets. Applying foundation models directly to small datasets of capsule endoscopy images from scratch is challenging. Pre-training on broad, general vision datasets is crucial for successfully fine-tuning our model for specific tasks. In this work, we introduce a simplified approach called Adapt foundation models with a low-rank adaptation (LoRA) technique for easier customization. Our method, inspired by the DINOv2 foundation model, applies low-rank adaptation learning to tailor foundation models for capsule endoscopy diagnosis effectively. Unlike traditional fine-tuning methods, our strategy includes LoRA layers designed to absorb specific surgical domain knowledge. During the training process, we keep the main model (the backbone encoder) fixed and focus on optimizing the LoRA layers and the disease classification component. We tested our method on two publicly available datasets for capsule endoscopy disease classification. The results were impressive, with our model achieving 97.75% accuracy on the Kvasir-Capsule dataset and 98.81% on the Kvasirv2 dataset. Our solution demonstrates that foundation models can be adeptly adapted for capsule endoscopy diagnosis, highlighting that mere reliance on straightforward fine-tuning or pre-trained models from general computer vision tasks is inadequate for such specific applications.

Yan Zhao

Predicting student performance under varying data distributions is a challenging task. This study proposes a method to improve prediction accuracy by employing transfer learning techniques on the dataset with varying distributions. Using datasets from mathematics and Portuguese language courses, the model was trained and evaluated to enhance its generalization ability and prediction accuracy. The datasets used in this study were sourced from Kaggle, comprising a variety of attributes such as demographic details, social factors, and academic performance. The methodology involves using an Artificial Neural Network (ANN) combined with transfer learning, where some layer weights were progressively frozen, and the remaining layers were fine-tuned. Experimental results demonstrated that this approach excels in reducing Root Mean Square Error (RMSE) and Mean Absolute Error (MAE), while improving the coefficient of determination (R2). The model was initially trained on a subset with a larger sample size and subsequently fine-tuned on another subset. This method effectively facilitated knowledge transfer, enhancing model performance on tasks with limited data. The results demonstrate that freezing more layers improves performance for complex and noisy data, whereas freezing fewer layers is more effective for simpler and larger datasets. This study highlights the potential of transfer learning in predicting student performance and suggests future research to explore domain adaptation techniques for unlabeled datasets.

Ziqiao Liu, Hao Miao, Yan Zhao et al.

With the proliferation of GPS-equipped edge devices, huge trajectory data is generated and accumulated in various domains, motivating a variety of urban applications. Due to the limited acquisition capabilities of edge devices, a lot of trajectories are recorded at a low sampling rate, which may lead to the effectiveness drop of urban applications. We aim to recover a high-sampled trajectory based on the low-sampled trajectory in free space, i.e., without road network information, to enhance the usability of trajectory data and support urban applications more effectively. Recent proposals targeting trajectory recovery often assume that trajectories are available at a central location, which fail to handle the decentralized trajectories and hurt privacy. To bridge the gap between decentralized training and trajectory recovery, we propose a lightweight framework, LightTR, for federated trajectory recovery based on a client-server architecture, while keeping the data decentralized and private in each client/platform center (e.g., each data center of a company). Specifically, considering the limited processing capabilities of edge devices, LightTR encompasses a light local trajectory embedding module that offers improved computational efficiency without compromising its feature extraction capabilities. LightTR also features a meta-knowledge enhanced local-global training scheme to reduce communication costs between the server and clients and thus further offer efficiency improvement. Extensive experiments demonstrate the effectiveness and efficiency of the proposed framework.

Yong Wang, Cheng Lu, Hailun Lian et al.

Swin-Transformer has demonstrated remarkable success in computer vision by leveraging its hierarchical feature representation based on Transformer. In speech signals, emotional information is distributed across different scales of speech features, e.\,g., word, phrase, and utterance. Drawing above inspiration, this paper presents a hierarchical speech Transformer with shifted windows to aggregate multi-scale emotion features for speech emotion recognition (SER), called Speech Swin-Transformer. Specifically, we first divide the speech spectrogram into segment-level patches in the time domain, composed of multiple frame patches. These segment-level patches are then encoded using a stack of Swin blocks, in which a local window Transformer is utilized to explore local inter-frame emotional information across frame patches of each segment patch. After that, we also design a shifted window Transformer to compensate for patch correlations near the boundaries of segment patches. Finally, we employ a patch merging operation to aggregate segment-level emotional features for hierarchical speech representation by expanding the receptive field of Transformer from frame-level to segment-level. Experimental results demonstrate that our proposed Speech Swin-Transformer outperforms the state-of-the-art methods.

Cheng Lu, Yuan Zong, Hailun Lian et al.

In speaker-independent speech emotion recognition, the training and testing samples are collected from diverse speakers, leading to a multi-domain shift challenge across the feature distributions of data from different speakers. Consequently, when the trained model is confronted with data from new speakers, its performance tends to degrade. To address the issue, we propose a Dynamic Joint Distribution Adaptation (DJDA) method under the framework of multi-source domain adaptation. DJDA firstly utilizes joint distribution adaptation (JDA), involving marginal distribution adaptation (MDA) and conditional distribution adaptation (CDA), to more precisely measure the multi-domain distribution shifts caused by different speakers. This helps eliminate speaker bias in emotion features, allowing for learning discriminative and speaker-invariant speech emotion features from coarse-level to fine-level. Furthermore, we quantify the adaptation contributions of MDA and CDA within JDA by using a dynamic balance factor based on $\mathcal{A}$-Distance, promoting to effectively handle the unknown distributions encountered in data from new speakers. Experimental results demonstrate the superior performance of our DJDA as compared to other state-of-the-art (SOTA) methods.

Yan Zhao, Lingjun Zhao, Zhong Liu et al.

Aircraft detection in Synthetic Aperture Radar (SAR) imagery is a challenging task in SAR Automatic Target Recognition (SAR ATR) areas due to aircraft's extremely discrete appearance, obvious intraclass variation, small size and serious background's interference. In this paper, a single-shot detector namely Attentional Feature Refinement and Alignment Network (AFRAN) is proposed for detecting aircraft in SAR images with competitive accuracy and speed. Specifically, three significant components including Attention Feature Fusion Module (AFFM), Deformable Lateral Connection Module (DLCM) and Anchor-guided Detection Module (ADM), are carefully designed in our method for refining and aligning informative characteristics of aircraft. To represent characteristics of aircraft with less interference, low-level textural and high-level semantic features of aircraft are fused and refined in AFFM throughly. The alignment between aircraft's discrete back-scatting points and convolutional sampling spots is promoted in DLCM. Eventually, the locations of aircraft are predicted precisely in ADM based on aligned features revised by refined anchors. To evaluate the performance of our method, a self-built SAR aircraft sliced dataset and a large scene SAR image are collected. Extensive quantitative and qualitative experiments with detailed analysis illustrate the effectiveness of the three proposed components. Furthermore, the topmost detection accuracy and competitive speed are achieved by our method compared with other domain-specific,e.g., DAPN, PADN, and general CNN-based methods,e.g., FPN, Cascade R-CNN, SSD, RefineDet and RPDet.

Chunzhi Gu, Yan Zhao, Chao Zhang

Human motion prediction, which plays a key role in computer vision, generally requires a past motion sequence as input. However, in real applications, a complete and correct past motion sequence can be too expensive to achieve. In this paper, we propose a novel approach to predicting future human motions from a much weaker condition, i.e., a single image, with mixture density networks (MDN) modeling. Contrary to most existing deep human motion prediction approaches, the multimodal nature of MDN enables the generation of diverse future motion hypotheses, which well compensates for the strong stochastic ambiguity aggregated by the single input and human motion uncertainty. In designing the loss function, we further introduce the energy-based formulation to flexibly impose prior losses over the learnable parameters of MDN to maintain motion coherence as well as improve the prediction accuracy by customizing the energy functions. Our trained model directly takes an image as input and generates multiple plausible motions that satisfy the given condition. Extensive experiments on two standard benchmark datasets demonstrate the effectiveness of our method in terms of prediction diversity and accuracy.

Ruihai Wu, Yan Zhao, Kaichun Mo et al.

Perceiving and manipulating 3D articulated objects (e.g., cabinets, doors) in human environments is an important yet challenging task for future home-assistant robots. The space of 3D articulated objects is exceptionally rich in their myriad semantic categories, diverse shape geometry, and complicated part functionality. Previous works mostly abstract kinematic structure with estimated joint parameters and part poses as the visual representations for manipulating 3D articulated objects. In this paper, we propose object-centric actionable visual priors as a novel perception-interaction handshaking point that the perception system outputs more actionable guidance than kinematic structure estimation, by predicting dense geometry-aware, interaction-aware, and task-aware visual action affordance and trajectory proposals. We design an interaction-for-perception framework VAT-Mart to learn such actionable visual representations by simultaneously training a curiosity-driven reinforcement learning policy exploring diverse interaction trajectories and a perception module summarizing and generalizing the explored knowledge for pointwise predictions among diverse shapes. Experiments prove the effectiveness of the proposed approach using the large-scale PartNet-Mobility dataset in SAPIEN environment and show promising generalization capabilities to novel test shapes, unseen object categories, and real-world data. Project page: https://hyperplane-lab.github.io/vat-mart

Liwei Deng, Xuanhao Chen, Yan Zhao et al.

Monitoring complex systems results in massive multivariate time series data, and anomaly detection of these data is very important to maintain the normal operation of the systems. Despite the recent emergence of a large number of anomaly detection algorithms for multivariate time series, most of them ignore the correlation modeling among multivariate, which can often lead to poor anomaly detection results. In this work, we propose a novel anomaly detection model for multivariate time series with \underline{HI}gh-order \underline{F}eature \underline{I}nteractions (HIFI). More specifically, HIFI builds multivariate feature interaction graph automatically and uses the graph convolutional neural network to achieve high-order feature interactions, in which the long-term temporal dependencies are modeled by attention mechanisms and a variational encoding technique is utilized to improve the model performance and robustness. Extensive experiments on three publicly available datasets demonstrate the superiority of our framework compared with state-of-the-art approaches.