Li Lu

Xinyu Zhang, Qingyu Liu, Zhongjie Ba et al.

Federated Learning (FL) is a promising distributed learning approach that enables multiple clients to collaboratively train a shared global model. However, recent studies show that FL is vulnerable to various poisoning attacks, which can degrade the performance of global models or introduce backdoors into them. In this paper, we first conduct a comprehensive study on prior FL attacks and detection methods. The results show that all existing detection methods are only effective against limited and specific attacks. Most detection methods suffer from high false positives, which lead to significant performance degradation, especially in not independent and identically distributed (non-IID) settings. To address these issues, we propose FLTracer, the first FL attack provenance framework to accurately detect various attacks and trace the attack time, objective, type, and poisoned location of updates. Different from existing methodologies that rely solely on cross-client anomaly detection, we propose a Kalman filter-based cross-round detection to identify adversaries by seeking the behavior changes before and after the attack. Thus, this makes it resilient to data heterogeneity and is effective even in non-IID settings. To further improve the accuracy of our detection method, we employ four novel features and capture their anomalies with the joint decisions. Extensive evaluations show that FLTracer achieves an average true positive rate of over $96.88\%$ at an average false positive rate of less than $2.67\%$, significantly outperforming SOTA detection methods. \footnote{Code is available at \url{https://github.com/Eyr3/FLTracer}.}

Xuejun Yan, Hongyu Yan, Jingjing Wang et al.

The rapid development of point cloud learning has driven point cloud completion into a new era. However, the information flows of most existing completion methods are solely feedforward, and high-level information is rarely reused to improve low-level feature learning. To this end, we propose a novel Feedback Network (FBNet) for point cloud completion, in which present features are efficiently refined by rerouting subsequent fine-grained ones. Firstly, partial inputs are fed to a Hierarchical Graph-based Network (HGNet) to generate coarse shapes. Then, we cascade several Feedback-Aware Completion (FBAC) Blocks and unfold them across time recurrently. Feedback connections between two adjacent time steps exploit fine-grained features to improve present shape generations. The main challenge of building feedback connections is the dimension mismatching between present and subsequent features. To address this, the elaborately designed point Cross Transformer exploits efficient information from feedback features via cross attention strategy and then refines present features with the enhanced feedback features. Quantitative and qualitative experiments on several datasets demonstrate the superiority of proposed FBNet compared to state-of-the-art methods on point completion task.

Peng Cheng, Yuwei Wang, Peng Huang et al.

Extensive research has revealed that adversarial examples (AE) pose a significant threat to voice-controllable smart devices. Recent studies have proposed black-box adversarial attacks that require only the final transcription from an automatic speech recognition (ASR) system. However, these attacks typically involve many queries to the ASR, resulting in substantial costs. Moreover, AE-based adversarial audio samples are susceptible to ASR updates. In this paper, we identify the root cause of these limitations, namely the inability to construct AE attack samples directly around the decision boundary of deep learning (DL) models. Building on this observation, we propose ALIF, the first black-box adversarial linguistic feature-based attack pipeline. We leverage the reciprocal process of text-to-speech (TTS) and ASR models to generate perturbations in the linguistic embedding space where the decision boundary resides. Based on the ALIF pipeline, we present the ALIF-OTL and ALIF-OTA schemes for launching attacks in both the digital domain and the physical playback environment on four commercial ASRs and voice assistants. Extensive evaluations demonstrate that ALIF-OTL and -OTA significantly improve query efficiency by 97.7% and 73.3%, respectively, while achieving competitive performance compared to existing methods. Notably, ALIF-OTL can generate an attack sample with only one query. Furthermore, our test-of-time experiment validates the robustness of our approach against ASR updates.

Meng Chen, Li Lu, Jiadi Yu et al.

Faced with the threat of identity leakage during voice data publishing, users are engaged in a privacy-utility dilemma when enjoying convenient voice services. Existing studies employ direct modification or text-based re-synthesis to de-identify users' voices, but resulting in inconsistent audibility in the presence of human participants. In this paper, we propose a voice de-identification system, which uses adversarial examples to balance the privacy and utility of voice services. Instead of typical additive examples inducing perceivable distortions, we design a novel convolutional adversarial example that modulates perturbations into real-world room impulse responses. Benefit from this, our system could preserve user identity from exposure by Automatic Speaker Identification (ASI) while remaining the voice perceptual quality for non-intrusive de-identification. Moreover, our system learns a compact speaker distribution through a conditional variational auto-encoder to sample diverse target embeddings on demand. Combining diverse target generation and input-specific perturbation construction, our system enables any-to-any identify transformation for adaptive de-identification. Experimental results show that our system could achieve 98% and 79% successful de-identification on mainstream ASIs and commercial systems with an objective Mel cepstral distortion of 4.31dB and a subjective mean opinion score of 4.48.

Zewang Zhang, Yibin Zheng, Xinhui Li et al.

In this paper, we develop a new multi-singer Chinese neural singing voice synthesis (SVS) system named WeSinger. To improve the accuracy and naturalness of synthesized singing voice, we design several specifical modules and techniques: 1) A deep bi-directional LSTM-based duration model with multi-scale rhythm loss and post-processing step; 2) A Transformer-alike acoustic model with progressive pitch-weighted decoder loss; 3) a 24 kHz pitch-aware LPCNet neural vocoder to produce high-quality singing waveforms; 4) A novel data augmentation method with multi-singer pre-training for stronger robustness and naturalness. To our knowledge, WeSinger is the first SVS system to adopt 24 kHz LPCNet and multi-singer pre-training simultaneously. Both quantitative and qualitative evaluation results demonstrate the effectiveness of WeSinger in terms of accuracy and naturalness, and WeSinger achieves state-of-the-art performance on the recent public Chinese singing corpus Opencpop\footnote{https://wenet.org.cn/opencpop/}. Some synthesized singing samples are available online\footnote{https://zzw922cn.github.io/wesinger/}.

Zhongjie Ba, Qingyu Liu, Zhenguang Liu et al.

Deepfake technology has given rise to a spectrum of novel and compelling applications. Unfortunately, the widespread proliferation of high-fidelity fake videos has led to pervasive confusion and deception, shattering our faith that seeing is believing. One aspect that has been overlooked so far is that current deepfake detection approaches may easily fall into the trap of overfitting, focusing only on forgery clues within one or a few local regions. Moreover, existing works heavily rely on neural networks to extract forgery features, lacking theoretical constraints guaranteeing that sufficient forgery clues are extracted and superfluous features are eliminated. These deficiencies culminate in unsatisfactory accuracy and limited generalizability in real-life scenarios. In this paper, we try to tackle these challenges through three designs: (1) We present a novel framework to capture broader forgery clues by extracting multiple non-overlapping local representations and fusing them into a global semantic-rich feature. (2) Based on the information bottleneck theory, we derive Local Information Loss to guarantee the orthogonality of local representations while preserving comprehensive task-relevant information. (3) Further, to fuse the local representations and remove task-irrelevant information, we arrive at a Global Information Loss through the theoretical analysis of mutual information. Empirically, our method achieves state-of-the-art performance on five benchmark datasets.Our code is available at \url{https://github.com/QingyuLiu/Exposing-the-Deception}, hoping to inspire researchers.

Qing Wen, Haohao Li, Zhongjie Ba et al.

Advances in AIGC technologies have enabled the synthesis of highly realistic audio deepfakes capable of deceiving human auditory perception. Although numerous audio deepfake detection (ADD) methods have been developed, most rely on local temporal/spectral features or pairwise relations, overlooking high-order interactions (HOIs). HOIs capture discriminative patterns that emerge from multiple feature components beyond their individual contributions. We propose HyperPotter, a hypergraph-based framework that explicitly models these synergistic HOIs through clustering-based hyperedges with class-aware prototype initialization. Extensive experiments demonstrate that HyperPotter surpasses its baseline by an average relative gain of 22.15% across 11 datasets and outperforms state-of-the-art methods by 13.96% on 4 challenging cross-domain datasets, demonstrating superior generalization to diverse attacks and speakers.

Xavier Hu, Jinxiang Xia, Shengze Xu et al.

Long-horizon planning is widely recognized as a core capability of autonomous LLM-based agents; however, current evaluation frameworks suffer from being largely episodic, domain-specific, or insufficiently grounded in persistent economic dynamics. We introduce EcoGym, a generalizable benchmark for continuous plan-and-execute decision making in interactive economies. EcoGym comprises three diverse environments: Vending, Freelance, and Operation, implemented in a unified decision-making process with standardized interfaces, and budgeted actions over an effectively unbounded horizon (1000+ steps if 365 day-loops for evaluation). The evaluation of EcoGym is based on business-relevant outcomes (e.g., net worth, income, and DAU), targeting long-term strategic coherence and robustness under partial observability and stochasticity. Experiments across eleven leading LLMs expose a systematic tension: no single model dominates across all three scenarios. Critically, we find that models exhibit significant suboptimality in either high-level strategies or efficient actions executions. EcoGym is released as an open, extensible testbed for transparent long-horizon agent evaluation and for studying controllability-utility trade-offs in realistic economic settings.

Meng Chen, Kun Wang, Li Lu et al.

Modern Large audio-language models (LALMs) power intelligent voice interactions by tightly integrating audio and text. This integration, however, expands the attack surface beyond text and introduces vulnerabilities in the continuous, high-dimensional audio channel. While prior work studied audio jailbreaks, the security risks of malicious audio injection and downstream behavior manipulation remain underexamined. In this work, we reveal a previously overlooked threat, auditory prompt injection, under realistic constraints of audio data-only access and strong perceptual stealth. To systematically analyze this threat, we propose \textit{AudioHijack}, a general framework that generates context-agnostic and imperceptible adversarial audio to hijack LALMs. \textit{AudioHijack} employs sampling-based gradient estimation for end-to-end optimization across diverse models, bypassing non-differentiable audio tokenization. Through attention supervision and multi-context training, it steers model attention toward adversarial audio and generalizes to unseen user contexts. We also design a convolutional blending method that modulates perturbations into natural reverberation, making them highly imperceptible to users. Extensive experiments on 13 state-of-the-art LALMs show consistent hijacking across 6 misbehavior categories, achieving average success rates of 79\%-96\% on unseen user contexts with high acoustic fidelity. Real-world studies demonstrate that commercial voice agents from Mistral AI and Microsoft Azure can be induced to execute unauthorized actions on behalf of users. These findings expose critical vulnerabilities in LALMs and highlight the urgent need for dedicated defense.

Zhongjie Ba, Liang Yi, Peng Cheng et al.

Toxic speech detection has become a crucial challenge in maintaining safe online communication environments. However, existing approaches to toxic speech detection often neglect the contribution of paralinguistic cues, such as emotion, intonation, and speech rate, which are key to detecting speech toxicity. Moreover, current toxic speech datasets are predominantly text-based, limiting the development of models that can capture paralinguistic cues.To address these challenges, we present ToxiAlert-Bench, a large-scale audio dataset comprising over 30,000 audio clips annotated with seven major toxic categories and twenty fine-grained toxic labels. Uniquely, our dataset annotates toxicity sources -- distinguishing between textual content and paralinguistic origins -- for comprehensive toxic speech analysis.Furthermore, we propose a dual-head neural network with a multi-stage training strategy tailored for toxic speech detection. This architecture features two task-specific classification headers: one for identifying the source of sensitivity (textual or paralinguistic), and the other for categorizing the specific toxic type. The training process involves independent head training followed by joint fine-tuning to reduce task interference. To mitigate data class imbalance, we incorporate class-balanced sampling and weighted loss functions.Our experimental results show that leveraging paralinguistic features significantly improves detection performance. Our method consistently outperforms existing baselines across multiple evaluation metrics, with a 21.1% relative improvement in Macro-F1 score and a 13.0% relative gain in accuracy over the strongest baseline, highlighting its enhanced effectiveness and practical applicability.

Kun Wang, Meng Chen, Junhao Wang et al.

With the widespread deployment of deep-learning-based speech models in security-critical applications, backdoor attacks have emerged as a serious threat: an adversary who poisons a small fraction of training data can implant a hidden trigger that controls the model's output while preserving normal behavior on clean inputs. Existing inference-time defenses are not well suited to the audio domain, as they either rely on trigger over-robustness assumptions that fail on transformation-based and semantic triggers, or depend on properties specific to image or text modalities. In this paper, we propose STEP (Stability-based Trigger Exposure Profiling), a black-box, retraining-free backdoor detector that operates under hard-label-only access. Its core idea is to exploit a characteristic dual anomaly of backdoor triggers: anomalous label stability under semantic-breaking perturbations, and anomalous label fragility under semantic-preserving perturbations. STEP profiles each test sample with two complementary perturbation branches that target these two properties respectively, scores the resulting stability features with one-class anomaly detectors trained on benign references, and fuses the two scores via unsupervised weighting. Extensive experiments across seven backdoor attacks show that STEP achieves an average AUROC of 97.92% and EER of 4.54%, substantially outperforming state-of-the-art baselines, and generalizes across model architectures, speech tasks, an open-set verification scenario, and over-the-air physical-world settings.

Yunzhe Li, Jiajun Yan, Yuzhou Wei et al.

Failing to be aware of speeding vehicles approaching from behind poses a huge threat to the road safety of pedestrians and cyclists. In this paper, we propose BlinkBud, which utilizes a single earbud and a paired phone to online detect hazardous objects approaching from behind of a user. The core idea is to accurately track visually identified objects utilizing a small number of sampled camera images taken from the earbud. To minimize the power consumption of the earbud and the phone while guaranteeing the best tracking accuracy, a novel 3D object tracking algorithm is devised, integrating both a Kalman filter based trajectory estimation scheme and an optimal image sampling strategy based on reinforcement learning. Moreover, the impact of constant user head movements on the tracking accuracy is significantly eliminated by leveraging the estimated pitch and yaw angles to correct the object depth estimation and align the camera coordinate system to the user's body coordinate system, respectively. We implement a prototype BlinkBud system and conduct extensive real-world experiments. Results show that BlinkBud is lightweight with ultra-low mean power consumptions of 29.8 mW and 702.6 mW on the earbud and smartphone, respectively, and can accurately detect hazards with a low average false positive ratio (FPR) and false negative ratio (FNR) of 4.90% and 1.47%, respectively.

Zhanpeng Luo, Linna Wang, Guangwu Qian et al.

Point cloud completion aims to recover the completed 3D shape of an object from its partial observation caused by occlusion, sensor's limitation, noise, etc. When some key semantic information is lost in the incomplete point cloud, the neural network needs to infer the missing part based on the input information. Intuitively we would apply an autoencoder architecture to solve this kind of problem, which take the incomplete point cloud as input and is supervised by the ground truth. This process that develops model's imagination from incomplete shape to complete shape is done automatically in the latent space. But the knowledge for mapping from incomplete to complete still remains dark and could be further explored. Motivated by the knowledge distillation's teacher-student learning strategy, we design a knowledge transfer way for completing 3d shape. In this work, we propose a novel View Distillation Point Completion Network (VD-PCN), which solve the completion problem by a multi-view distillation way. The design methodology fully leverages the orderliness of 2d pixels, flexibleness of 2d processing and powerfulness of 2d network. Extensive evaluations on PCN, ShapeNet55/34, and MVP datasets confirm the effectiveness of our design and knowledge transfer strategy, both quantitatively and qualitatively. Committed to facilitate ongoing research, we will make our code publicly available.

Xiao Chen, Zhongjing Du, Jiazhen Huang et al.

Test-Time Adaptation (TTA) enhances model robustness to out-of-distribution (OOD) data by updating the model online during inference, yet existing methods lack theoretical insights into the fundamental causes of performance degradation under domain shifts. Recently, Neural Collapse (NC) has been proposed as an emergent geometric property of deep neural networks (DNNs), providing valuable insights for TTA. In this work, we extend NC to the sample-wise level and discover a novel phenomenon termed Sample-wise Alignment Collapse (NC3+), demonstrating that a sample's feature embedding, obtained by a trained model, aligns closely with the corresponding classifier weight. Building on NC3+, we identify that the performance degradation stems from sample-wise misalignment in adaptation which exacerbates under larger distribution shifts. This indicates the necessity of realigning the feature embeddings with their corresponding classifier weights. However, the misalignment makes pseudo-labels unreliable under domain shifts. To address this challenge, we propose NCTTA, a novel feature-classifier alignment method with hybrid targets to mitigate the impact of unreliable pseudo-labels, which blends geometric proximity with predictive confidence. Extensive experiments demonstrate the effectiveness of NCTTA in enhancing robustness to domain shifts. For example, NCTTA outperforms Tent by 14.52% on ImageNet-C.

Linna Wang, Zhixuan You, Qihui Zhang et al.

Large Language Models (LLMs) and causal learning each hold strong potential for clinical decision making (CDM). However, their synergy remains poorly understood, largely due to the lack of systematic benchmarks evaluating their integration in clinical risk prediction. In real-world healthcare, identifying features with causal influence on outcomes is crucial for actionable and trustworthy predictions. While recent work highlights LLMs' emerging causal reasoning abilities, there lacks comprehensive benchmarks to assess their causal learning and performance informed by causal features in clinical risk prediction. To address this, we introduce REACT-LLM, a benchmark designed to evaluate whether combining LLMs with causal features can enhance clinical prognostic performance and potentially outperform traditional machine learning (ML) methods. Unlike existing LLM-clinical benchmarks that often focus on a limited set of outcomes, REACT-LLM evaluates 7 clinical outcomes across 2 real-world datasets, comparing 15 prominent LLMs, 6 traditional ML models, and 3 causal discovery (CD) algorithms. Our findings indicate that while LLMs perform reasonably in clinical prognostics, they have not yet outperformed traditional ML models. Integrating causal features derived from CD algorithms into LLMs offers limited performance gains, primarily due to the strict assumptions of many CD methods, which are often violated in complex clinical data. While the direct integration yields limited improvement, our benchmark reveals a more promising synergy.

Hongyu Yan, Zijun Li, Kunming Luo et al.

Point cloud completion aims to recover a complete point shape from a partial point cloud. Although existing methods can form satisfactory point clouds in global completeness, they often lose the original geometry details and face the problem of geometric inconsistency between existing point clouds and reconstructed missing parts. To tackle this problem, we introduce SymmCompletion, a highly effective completion method based on symmetry guidance. Our method comprises two primary components: a Local Symmetry Transformation Network (LSTNet) and a Symmetry-Guidance Transformer (SGFormer). First, LSTNet efficiently estimates point-wise local symmetry transformation to transform key geometries of partial inputs into missing regions, thereby generating geometry-align partial-missing pairs and initial point clouds. Second, SGFormer leverages the geometric features of partial-missing pairs as the explicit symmetric guidance that can constrain the refinement process for initial point clouds. As a result, SGFormer can exploit provided priors to form high-fidelity and geometry-consistency final point clouds. Qualitative and quantitative evaluations on several benchmark datasets demonstrate that our method outperforms state-of-the-art completion networks.

Zhanpeng Luo, Haoxi Ran, Li Lu

Dynamic view synthesis has seen significant advances, yet reconstructing scenes from uncalibrated, casual video remains challenging due to slow optimization and complex parameter estimation. In this work, we present Instant4D, a monocular reconstruction system that leverages native 4D representation to efficiently process casual video sequences within minutes, without calibrated cameras or depth sensors. Our method begins with geometric recovery through deep visual SLAM, followed by grid pruning to optimize scene representation. Our design significantly reduces redundancy while maintaining geometric integrity, cutting model size to under 10% of its original footprint. To handle temporal dynamics efficiently, we introduce a streamlined 4D Gaussian representation, achieving a 30x speed-up and reducing training time to within two minutes, while maintaining competitive performance across several benchmarks. Our method reconstruct a single video within 10 minutes on the Dycheck dataset or for a typical 200-frame video. We further apply our model to in-the-wild videos, showcasing its generalizability. Our project website is published at https://instant4d.github.io/.

Zijun Li, Hongyu Yan, Shijie Li et al.

Latent diffusion models (LDMs) have demonstrated remarkable generative capabilities across various low-level vision tasks. However, their potential for point cloud completion remains underexplored due to the unstructured and irregular nature of point clouds. In this work, we propose DiffPCN, a novel diffusion-based coarse-to-fine framework for point cloud completion. Our approach comprises two stages: an initial stage for generating coarse point clouds, and a refinement stage that improves their quality through point denoising and upsampling. Specifically, we first project the unordered and irregular partial point cloud into structured depth images, which serve as conditions for a well-designed DepthLDM to synthesize completed multi-view depth images that are used to form coarse point clouds. In this way, our DiffPCN can yield high-quality and high-completeness coarse point clouds by leveraging LDM' s powerful generation and comprehension capabilities. Then, since LDMs inevitably introduce outliers into the generated depth maps, we design a Point Denoising Network to remove artifacts from the coarse point cloud by predicting a per-point distance score. Finally, we devise an Association-Aware Point Upsampler, which guides the upsampling process by leveraging local association features between the input point cloud and the corresponding coarse points, further yielding a dense and high-fidelity output. Experimental results demonstrate that our DiffPCN achieves state-of-the-art performance in geometric accuracy and shape completeness, significantly improving the robustness and consistency of point cloud completion.

Qianniu Chen, Xiaoyang Hao, Bowen Li et al.

Zero-shot Text-To-Speech (TTS) synthesis shows great promise for personalized voice customization through voice cloning. However, current methods for achieving zero-shot TTS heavily rely on large model scales and extensive training datasets to ensure satisfactory performance and generalizability across various speakers. This raises concerns regarding both deployment costs and data security. In this paper, we present a lightweight and stable zero-shot TTS system. We introduce a novel TTS architecture designed to effectively model linguistic content and various speaker attributes from source speech and prompt speech, respectively. Furthermore, we present a two-stage self-distillation framework that constructs parallel data pairs for effectively disentangling linguistic content and speakers from the perspective of training data. Extensive experiments show that our system exhibits excellent performance and superior stability on the zero-shot TTS tasks. Moreover, it shows markedly superior computational efficiency, with RTFs of 0.13 and 0.012 on the CPU and GPU, respectively.

Shilun Lin, Wenchao Su, Li Meng et al.

This paper presents Nana-HDR, a new non-attentive non-autoregressive model with hybrid Transformer-based Dense-fuse encoder and RNN-based decoder for TTS. It mainly consists of three parts: Firstly, a novel Dense-fuse encoder with dense connections between basic Transformer blocks for coarse feature fusion and a multi-head attention layer for fine feature fusion. Secondly, a single-layer non-autoregressive RNN-based decoder. Thirdly, a duration predictor instead of an attention model that connects the above hybrid encoder and decoder. Experiments indicate that Nana-HDR gives full play to the advantages of each component, such as strong text encoding ability of Transformer-based encoder, stateful decoding without being bothered by exposure bias and local information preference, and stable alignment provided by duration predictor. Due to these advantages, Nana-HDR achieves competitive performance in naturalness and robustness on two Mandarin corpora.

Haoxi Ran, Wei Zhuo, Jun Liu et al.

The prevalence of relation networks in computer vision is in stark contrast to underexplored point-based methods. In this paper, we explore the possibilities of local relation operators and survey their feasibility. We propose a scalable and efficient module, called group relation aggregator. The module computes a feature of a group based on the aggregation of the features of the inner-group points weighted by geometric relations and semantic relations. We adopt this module to design our RPNet. We further verify the expandability of RPNet, in terms of both depth and width, on the tasks of classification and segmentation. Surprisingly, empirical results show that wider RPNet fits for classification, while deeper RPNet works better on segmentation. RPNet achieves state-of-the-art for classification and segmentation on challenging benchmarks. We also compare our local aggregator with PointNet++, with around 30% parameters and 50% computation saving. Finally, we conduct experiments to reveal the robustness of RPNet with regard to rigid transformation and noises.

Mingbo Hong, Shuiwang Li, Yuchao Yang et al.

With the increasing demand for search and rescue, it is highly demanded to detect objects of interest in large-scale images captured by Unmanned Aerial Vehicles (UAVs), which is quite challenging due to extremely small scales of objects. Most existing methods employed Feature Pyramid Network (FPN) to enrich shallow layers' features by combing deep layers' contextual features. However, under the limitation of the inconsistency in gradient computation across different layers, the shallow layers in FPN are not fully exploited to detect tiny objects. In this paper, we propose a Scale Selection Pyramid network (SSPNet) for tiny person detection, which consists of three components: Context Attention Module (CAM), Scale Enhancement Module (SEM), and Scale Selection Module (SSM). CAM takes account of context information to produce hierarchical attention heatmaps. SEM highlights features of specific scales at different layers, leading the detector to focus on objects of specific scales instead of vast backgrounds. SSM exploits adjacent layers' relationships to fulfill suitable feature sharing between deep layers and shallow layers, thereby avoiding the inconsistency in gradient computation across different layers. Besides, we propose a Weighted Negative Sampling (WNS) strategy to guide the detector to select more representative samples. Experiments on the TinyPerson benchmark show that our method outperforms other state-of-the-art (SOTA) detectors.

Shuiwang Li, Qijun Zhao, Ziliang Feng et al.

(Discriminative) Correlation Filter has been successfully applied to visual tracking and has advanced the field significantly in recent years. Correlation filter-based trackers consider visual tracking as a problem of matching the feature template of the object and candidate regions in the detection sample, in which correlation filter provides the means to calculate the similarities. In contrast, convolution filter is usually used for blurring, sharpening, embossing, edge detection, etc in image processing. On the surface, correlation filter and convolution filter are usually used for different purposes. In this paper, however, we proves, for the first time, that correlation filter and convolution filter are equivalent in the sense that their minimum mean-square errors (MMSEs) in visual tracking are equal, under the condition that the optimal solutions exist and the ideal filter response is Gaussian and centrosymmetric. This result gives researchers the freedom to choose correlation or convolution in formulating their trackers. It also suggests that the explanation of the ideal response in terms of similarities is not essential.

Cheng Luo, Dayiheng Liu, Chanjuan Li et al.

In open-domain conversational systems, it is important but challenging to leverage background knowledge. We can use the incorporation of knowledge to make the generation of dialogue controllable, and can generate more diverse sentences that contain real knowledge. In this paper, we combine the knowledge bases and pre-training model to propose a knowledge-driven conversation system. The system includes modules such as dialogue topic prediction, knowledge matching and dialogue generation. Based on this system, we study the performance factors that maybe affect the generation of knowledge-driven dialogue: topic coarse recall algorithm, number of knowledge choices, generation model choices, etc., and finally made the system reach state-of-the-art. These experimental results will provide some guiding significance for the future research of this task. As far as we know, this is the first work to study and analyze the effects of the related factors.

Shilun Lin, Fenglong Xie, Li Meng et al.

In this work, a robust and efficient text-to-speech (TTS) synthesis system named Triple M is proposed for large-scale online application. The key components of Triple M are: 1) A sequence-to-sequence model adopts a novel multi-guidance attention to transfer complementary advantages from guiding attention mechanisms to the basic attention mechanism without in-domain performance loss and online service modification. Compared with single attention mechanism, multi-guidance attention not only brings better naturalness to long sentence synthesis, but also reduces the word error rate by 26.8%. 2) A new efficient multi-band multi-time vocoder framework, which reduces the computational complexity from 2.8 to 1.0 GFLOP and speeds up LPCNet by 2.75x on a single CPU.

Haoxi Ran, Li Lu

Prevalence of deeper networks driven by self-attention is in stark contrast to underexplored point-based methods. In this paper, we propose groupwise self-attention as the basic block to construct our network: SepNet. Our proposed module can effectively capture both local and global dependencies. This module computes the features of a group based on the summation of the weighted features of any point within the group. For convenience, we generalize groupwise operations to assemble this module. To further facilitate our networks, we deepen and widen SepNet on the tasks of segmentation and classification respectively, and verify its practicality. Specifically, SepNet achieves state-of-the-art for the tasks of classification and segmentation on most of the datasets. We show empirical evidence that SepNet can obtain extra accuracy in classification or segmentation from increased width or depth, respectively.

Haoxi Ran, Guangfu Wang, Li Lu

Human imitation has become topical recently, driven by GAN's ability to disentangle human pose and body content. However, the latest methods hardly focus on 3D information, and to avoid self-occlusion, a massive amount of input images are needed. In this paper, we propose RIN, a novel volume-based framework for reconstructing a textured 3D model from a single picture and imitating a subject with the generated model. Specifically, to estimate most of the human texture, we propose a U-Net-like front-to-back translation network. With both front and back images input, the textured volume recovery module allows us to color a volumetric human. A sequence of 3D poses then guides the colored volume via Flowable Disentangle Networks as a volume-to-volume translation task. To project volumes to a 2D plane during training, we design a differentiable depth-aware renderer. Our experiments demonstrate that our volume-based model is adequate for human imitation, and the back view can be estimated reliably using our network. While prior works based on either 2D pose or semantic map often fail for the unstable appearance of a human, our framework can still produce concrete results, which are competitive to those imagined from multi-view input.