Kun Liu

Guangtao Lyu, Kun Liu, Anna Zhu et al.

The scene text removal (STR) task aims to remove text regions and recover the background smoothly in images for private information protection. Most existing STR methods adopt encoder-decoder-based CNNs, with direct copies of the features in the skip connections. However, the encoded features contain both text texture and structure information. The insufficient utilization of text features hampers the performance of background reconstruction in text removal regions. To tackle these problems, we propose a novel Feature Erasing and Transferring (FET) mechanism to reconfigure the encoded features for STR in this paper. In FET, a Feature Erasing Module (FEM) is designed to erase text features. An attention module is responsible for generating the feature similarity guidance. The Feature Transferring Module (FTM) is introduced to transfer the corresponding features in different layers based on the attention guidance. With this mechanism, a one-stage, end-to-end trainable network called FETNet is constructed for scene text removal. In addition, to facilitate research on both scene text removal and segmentation tasks, we introduce a novel dataset, Flickr-ST, with multi-category annotations. A sufficient number of experiments and ablation studies are conducted on the public datasets and Flickr-ST. Our proposed method achieves state-of-the-art performance using most metrics, with remarkably higher quality scene text removal results. The source code of our work is available at: \href{https://github.com/GuangtaoLyu/FETNet}{https://github.com/GuangtaoLyu/FETNet.

Xin Li, Jiachao Gong, Xijun Wang et al.

This paper presents an overview of the NTIRE 2026 Challenge on Short-form UGC Video Restoration in the Wild with Generative Models. This challenge utilizes a new short-form UGC (S-UGC) video restoration benchmark, termed KwaiVIR, which is contributed by USTC and Kuaishou Technology. It contains both synthetically distorted videos and real-world short-form UGC videos in the wild. For this edition, the released data include 200 synthetic training videos, 48 wild training videos, 11 validation videos, and 20 testing videos. The primary goal of this challenge is to establish a strong and practical benchmark for restoring short-form UGC videos under complex real-world degradations, especially in the emerging paradigm of generative-model-based S-UGC video restoration. This challenge has two tracks: (i) the primary track is a subjective track, where the evaluation is based on a user study; (ii) the second track is an objective track. These two tracks enable a comprehensive assessment of restoration quality. In total, 95 teams have registered for this competition. And 12 teams submitted valid final solutions and fact sheets for the testing phase. The submitted methods achieved strong performance on the KwaiVIR benchmark, demonstrating encouraging progress in short-form UGC video restoration in the wild.

Kun Liu, Huiyuan Fu, Zheng Zhang et al.

This paper provides a brief overview of our submission to the no interaction track of SAPIEN ManiSkill Challenge 2021. Our approach follows an end-to-end pipeline which mainly consists of two steps: we first extract the point cloud features of multiple objects; then we adopt these features to predict the action score of the robot simulators through a deep and wide transformer-based network. More specially, %to give guidance for future work, to open up avenues for exploitation of learning manipulation skill, we present an empirical study that includes a bag of tricks and abortive attempts. Finally, our method achieves a promising ranking on the leaderboard. All code of our solution is available at https://github.com/liu666666/bigfish\_codes.

Kaituo Xu, Yan Jia, Kai Huang et al.

We present FireRedASR2S, a state-of-the-art industrial-grade all-in-one automatic speech recognition (ASR) system. It integrates four modules in a unified pipeline: ASR, Voice Activity Detection (VAD), Spoken Language Identification (LID), and Punctuation Prediction (Punc). All modules achieve SOTA performance on the evaluated benchmarks: FireRedASR2: An ASR module with two variants, FireRedASR2-LLM (8B+ parameters) and FireRedASR2-AED (1B+ parameters), supporting speech and singing transcription for Mandarin, Chinese dialects and accents, English, and code-switching. Compared to FireRedASR, FireRedASR2 delivers improved recognition accuracy and broader dialect and accent coverage. FireRedASR2-LLM achieves 2.89% average CER on 4 public Mandarin benchmarks and 11.55% on 19 public Chinese dialects and accents benchmarks, outperforming competitive baselines including Doubao-ASR, Qwen3-ASR, and Fun-ASR. FireRedVAD: An ultra-lightweight module (0.6M parameters) based on the Deep Feedforward Sequential Memory Network (DFSMN), supporting streaming VAD, non-streaming VAD, and multi-label VAD (mVAD). On the FLEURS-VAD-102 benchmark, it achieves 97.57% frame-level F1 and 99.60% AUC-ROC, outperforming Silero-VAD, TEN-VAD, FunASR-VAD, and WebRTC-VAD. FireRedLID: An Encoder-Decoder LID module supporting 100+ languages and 20+ Chinese dialects and accents. On FLEURS (82 languages), it achieves 97.18% utterance-level accuracy, outperforming Whisper and SpeechBrain. FireRedPunc: A BERT-style punctuation prediction module for Chinese and English. On multi-domain benchmarks, it achieves 78.90% average F1, outperforming FunASR-Punc (62.77%). To advance research in speech processing, we release model weights and code at https://github.com/FireRedTeam/FireRedASR2S.

Xiaodong Chen, Xinchen Liu, Wu Liu et al.

Action recognition from videos, i.e., classifying a video into one of the pre-defined action types, has been a popular topic in the communities of artificial intelligence, multimedia, and signal processing. However, existing methods usually consider an input video as a whole and learn models, e.g., Convolutional Neural Networks (CNNs), with coarse video-level class labels. These methods can only output an action class for the video, but cannot provide fine-grained and explainable cues to answer why the video shows a specific action. Therefore, researchers start to focus on a new task, Part-level Action Parsing (PAP), which aims to not only predict the video-level action but also recognize the frame-level fine-grained actions or interactions of body parts for each person in the video. To this end, we propose a coarse-to-fine framework for this challenging task. In particular, our framework first predicts the video-level class of the input video, then localizes the body parts and predicts the part-level action. Moreover, to balance the accuracy and computation in part-level action parsing, we propose to recognize the part-level actions by segment-level features. Furthermore, to overcome the ambiguity of body parts, we propose a pose-guided positional embedding method to accurately localize body parts. Through comprehensive experiments on a large-scale dataset, i.e., Kinetics-TPS, our framework achieves state-of-the-art performance and outperforms existing methods over a 31.10% ROC score.

Qi Liu, Xinchen Liu, Kun Liu et al.

Multi-modal human action segmentation is a critical and challenging task with a wide range of applications. Nowadays, the majority of approaches concentrate on the fusion of dense signals (i.e., RGB, optical flow, and depth maps). However, the potential contributions of sparse IoT sensor signals, which can be crucial for achieving accurate recognition, have not been fully explored. To make up for this, we introduce a Sparse signalguided Transformer (SigFormer) to combine both dense and sparse signals. We employ mask attention to fuse localized features by constraining cross-attention within the regions where sparse signals are valid. However, since sparse signals are discrete, they lack sufficient information about the temporal action boundaries. Therefore, in SigFormer, we propose to emphasize the boundary information at two stages to alleviate this problem. In the first feature extraction stage, we introduce an intermediate bottleneck module to jointly learn both category and boundary features of each dense modality through the inner loss functions. After the fusion of dense modalities and sparse signals, we then devise a two-branch architecture that explicitly models the interrelationship between action category and temporal boundary. Experimental results demonstrate that SigFormer outperforms the state-of-the-art approaches on a multi-modal action segmentation dataset from real industrial environments, reaching an outstanding F1 score of 0.958. The codes and pre-trained models have been available at https://github.com/LIUQI-creat/SigFormer.

Tongtong Yuan, Xuange Zhang, Kun Liu et al.

Surveillance videos are an essential component of daily life with various critical applications, particularly in public security. However, current surveillance video tasks mainly focus on classifying and localizing anomalous events. Existing methods are limited to detecting and classifying the predefined events with unsatisfactory semantic understanding, although they have obtained considerable performance. To address this issue, we propose a new research direction of surveillance video-and-language understanding, and construct the first multimodal surveillance video dataset. We manually annotate the real-world surveillance dataset UCF-Crime with fine-grained event content and timing. Our newly annotated dataset, UCA (UCF-Crime Annotation), contains 23,542 sentences, with an average length of 20 words, and its annotated videos are as long as 110.7 hours. Furthermore, we benchmark SOTA models for four multimodal tasks on this newly created dataset, which serve as new baselines for surveillance video-and-language understanding. Through our experiments, we find that mainstream models used in previously publicly available datasets perform poorly on surveillance video, which demonstrates the new challenges in surveillance video-and-language understanding. To validate the effectiveness of our UCA, we conducted experiments on multimodal anomaly detection. The results demonstrate that our multimodal surveillance learning can improve the performance of conventional anomaly detection tasks. All the experiments highlight the necessity of constructing this dataset to advance surveillance AI. The link to our dataset is provided at: https://xuange923.github.io/Surveillance-Video-Understanding.

Kun Liu, Liqun Chen

The alignment of Multi-Agent Systems (MAS) for autonomous software engineering is constrained by evaluator epistemic uncertainty. Current paradigms, such as Reinforcement Learning from Human Feedback (RLHF) and AI Feedback (RLAIF), frequently induce model sycophancy, while execution-based environments suffer from adversarial "Test Evasion" by unconstrained agents. In this paper, we introduce an objective alignment paradigm: \textbf{Out-of-Money Reinforcement Learning (OOM-RL)}. By deploying agents into the non-stationary, high-friction reality of live financial markets, we utilize critical capital depletion as an un-hackable negative gradient. Our longitudinal 20-month empirical study (July 2024 -- February 2026) chronicles the system's evolution from a high-turnover, sycophantic baseline to a robust, liquidity-aware architecture. We demonstrate that the undeniable ontological consequences of financial loss forced the MAS to abandon overfitted hallucinations in favor of the \textbf{Strict Test-Driven Agentic Workflow (STDAW)}, which enforces a Byzantine-inspired uni-directional state lock (RO-Lock) anchored to a deterministically verified $\geq 95\%$ code coverage constraint matrix. Our results show that while early iterations suffered severe execution decay, the final OOM-RL-aligned system achieved a stable equilibrium with an annualized Sharpe ratio of 2.06 in its mature phase. We conclude that substituting subjective human preference with rigorous economic penalties provides a robust methodology for aligning autonomous agents in high-stakes, real-world environments, laying the groundwork for generalized paradigms where computational billing acts as an objective physical constraint

Shuaitao Zhao, Kun Liu, Yuhang Huang et al.

Human pose estimation aims to figure out the keypoints of all people in different scenes. Current approaches still face some challenges despite promising results. Existing top-down methods deal with a single person individually, without the interaction between different people and the scene they are situated in. Consequently, the performance of human detection degrades when serious occlusion happens. On the other hand, existing bottom-up methods consider all people at the same time and capture the global knowledge of the entire image. However, they are less accurate than the top-down methods due to the scale variation. To address these problems, we propose a novel Dual-Pipeline Integrated Transformer (DPIT) by integrating top-down and bottom-up pipelines to explore the visual clues of different receptive fields and achieve their complementarity. Specifically, DPIT consists of two branches, the bottom-up branch deals with the whole image to capture the global visual information, while the top-down branch extracts the feature representation of local vision from the single-human bounding box. Then, the extracted feature representations from bottom-up and top-down branches are fed into the transformer encoder to fuse the global and local knowledge interactively. Moreover, we define the keypoint queries to explore both full-scene and single-human posture visual clues to realize the mutual complementarity of the two pipelines. To the best of our knowledge, this is one of the first works to integrate the bottom-up and top-down pipelines with transformers for human pose estimation. Extensive experiments on COCO and MPII datasets demonstrate that our DPIT achieves comparable performance to the state-of-the-art methods.

Yunheng Wang, Yuetong Fang, Taowen Wang et al.

Vision-and-Language Navigation (VLN) is a cornerstone of embodied intelligence. However, current agents often suffer from significant performance degradation when transitioning from simulation to real-world deployment, primarily due to perceptual instability (e.g., lighting variations and motion blur) and under-specified instructions. While existing methods attempt to bridge this gap by scaling up model size and training data, we argue that the bottleneck lies in the lack of robust spatial grounding and cross-domain priors. In this paper, we propose StereoNav, a robust Vision-Language-Action framework designed to enhance real-world navigation consistency. To address the inherent gap between synthetic training and physical execution, we introduce Target-Location Priors as a persistent bridge. These priors provide stable visual guidance that remains invariant across domains, effectively grounding the agent even when instructions are vague. Furthermore, to mitigate visual disturbances like motion blur and illumination shifts, StereoNav leverages stereo vision to construct a unified representation of semantics and geometry, enabling precise action prediction through enhanced depth awareness. Extensive experiments on R2R-CE and RxR-CE demonstrate that StereoNav achieves state-of-the-art egocentric RGB performance, with SR and SPL scores of 81.1% and 68.3%, and 67.5% and 52.0%, respectively, while using significantly fewer parameters and less training data than prior scaling-based approaches. More importantly, real-world robotic deployments confirm that StereoNav substantially improves navigation reliability in complex, unstructured environments. Project page: https://yunheng-wang.github.io/stereonav-public.github.io.

Haoyu Li, Xuhong Li, Yiming Dong et al.

Dataset diversity plays a pivotal role for the successful training of many machine learning models, particularly in the supervised fine-tuning (SFT) stage of large language model (LLM) development. Despite increasing recognition of its importance, systematic analyses of dataset diversity still remain underexplored. To address this gap, this work presents a systematic taxonomy of existing diversity-control strategies, which primarily focus on the instruction component, operating at either macroscopic (entire instruction semantics) or mesoscopic levels (instruction units), and furthermore introduces a novel analysis of microscopic diversity within the response component, specifically analyzing the statistical distribution of tokens in SFT training samples. In the experimental evaluation, we construct fixed-size datasets (e.g., 10,000 samples each) from a corpus of 117,000 open-source SFT samples, incorporating six distinct diversity-control strategies spanning macro-, meso-, and microscopic levels applied to both instructions and responses. We then fine-tune LLMs on these datasets to assess the six diversity-control strategies. Results reveal that while macroscopic and mesoscopic strategies lead to higher performance with increasing diversity, the microscopic strategy in responses exhibits both a stronger correlation between model performance and the degree of diversity and superior performance with maximum diversity across all strategies. These findings offer actionable insights for constructing high-performance SFT datasets.

Kun Liu, Yao Fu, Chuanqi Tan et al.

Recent studies in deep learning have shown significant progress in named entity recognition (NER). Most existing works assume clean data annotation, yet a fundamental challenge in real-world scenarios is the large amount of noise from a variety of sources (e.g., pseudo, weak, or distant annotations). This work studies NER under a noisy labeled setting with calibrated confidence estimation. Based on empirical observations of different training dynamics of noisy and clean labels, we propose strategies for estimating confidence scores based on local and global independence assumptions. We partially marginalize out labels of low confidence with a CRF model. We further propose a calibration method for confidence scores based on the structure of entity labels. We integrate our approach into a self-training framework for boosting performance. Experiments in general noisy settings with four languages and distantly labeled settings demonstrate the effectiveness of our method. Our code can be found at https://github.com/liukun95/Noisy-NER-Confidence-Estimation

Xinkun Ai, Kun Liu, Wei Zheng et al.

Ball mills play a critical role in modern mining operations, making their bearing failures a significant concern due to the potential loss of production efficiency and economic consequences. This paper presents an anomaly detection method based on Deep Convolutional Auto-encoding Neural Networks (DCAN) for addressing the issue of ball mill bearing fault detection. The proposed approach leverages vibration data collected during normal operation for training, overcoming challenges such as labeling issues and data imbalance often encountered in supervised learning methods. DCAN includes the modules of convolutional feature extraction and transposed convolutional feature reconstruction, demonstrating exceptional capabilities in signal processing and feature extraction. Additionally, the paper describes the practical deployment of the DCAN-based anomaly detection model for bearing fault detection, utilizing data from the ball mill bearings of Wuhan Iron & Steel Resources Group and fault data from NASA's bearing vibration dataset. Experimental results validate the DCAN model's reliability in recognizing fault vibration patterns. This method holds promise for enhancing bearing fault detection efficiency, reducing production interruptions, and lowering maintenance costs.

Rong Fu, Jia Yee Tan, Youjin Wang et al.

Zero-knowledge circuits enable privacy-preserving and scalable systems but are difficult to implement correctly due to the tight coupling between witness computation and circuit constraints. We present zkCraft, a practical framework that combines deterministic, R1CS-aware localization with proof-bearing search to detect semantic inconsistencies. zkCraft encodes candidate constraint edits into a single Row-Vortex polynomial and replaces repeated solver queries with a Violation IOP that certifies the existence of edits together with a succinct proof. Deterministic LLM-driven mutation templates bias exploration toward edge cases while preserving auditable algebraic verification. Evaluation on real Circom code shows that proof-bearing localization detects diverse under- and over-constrained faults with low false positives and reduces costly solver interaction. Our approach bridges formal verification and automated debugging, offering a scalable path for robust ZK circuit development.

Candi Zheng, Kun Liu, Yang Wang et al.

Background: Invasive coronary arteriography (ICA) is recognized as the gold standard for diagnosing cardiovascular diseases, including unstable angina (UA). The challenge lies in determining the optimal timing for ICA in UA patients, balancing the need for revascularization in high-risk patients against the potential complications in low-risk ones. Unlike myocardial infarction, UA does not have specific indicators like ST-segment deviation or cardiac enzymes, making risk assessment complex. Objectives: Our study aims to enhance the early risk assessment for UA patients by utilizing machine learning algorithms. These algorithms can potentially identify patients who would benefit most from ICA by analyzing less specific yet related indicators that are challenging for human physicians to interpret. Methods: We collected data from 640 UA patients at Shanghai General Hospital, including medical history and electrocardiograms (ECG). Machine learning algorithms were trained using multi-modal demographic characteristics including clinical risk factors, symptoms, biomarker levels, and ECG features extracted by pre-trained neural networks. The goal was to stratify patients based on their revascularization risk. Additionally, we translated our models into applicable and explainable look-up tables through discretization for practical clinical use. Results: The study achieved an Area Under the Curve (AUC) of $0.719 \pm 0.065$ in risk stratification, significantly surpassing the widely adopted GRACE score's AUC of $0.579 \pm 0.044$. Conclusions: The results suggest that machine learning can provide superior risk stratification for UA patients. This improved stratification could help in balancing the risks, costs, and complications associated with ICA, indicating a potential shift in clinical assessment practices for unstable angina.

Rong Fu, Xiaowen Ma, Kun Liu et al.

Deploying expressive learning models directly on programmable dataplanes promises line-rate, low-latency traffic analysis but remains hindered by strict hardware constraints and the need for predictable, auditable behavior. Chimera introduces a principled framework that maps attention-oriented neural computations and symbolic constraints onto dataplane primitives, enabling trustworthy inference within the match-action pipeline. Chimera combines a kernelized, linearized attention approximation with a two-layer key-selection hierarchy and a cascade fusion mechanism that enforces hard symbolic guarantees while preserving neural expressivity. The design includes a hardware-aware mapping protocol and a two-timescale update scheme that together permit stable, line-rate operation under realistic dataplane budgets. The paper presents the Chimera architecture, a hardware mapping strategy, and empirical evidence showing that neuro-symbolic attention primitives can achieve high-fidelity inference within the resource envelope of commodity programmable switches.

Xin Zhao, Shiyu Hu, Yipei Wang et al.

Single object tracking (SOT) is a fundamental problem in computer vision, with a wide range of applications, including autonomous driving, augmented reality, and robot navigation. The robustness of SOT faces two main challenges: tiny target and fast motion. These challenges are especially manifested in videos captured by unmanned aerial vehicles (UAV), where the target is usually far away from the camera and often with significant motion relative to the camera. To evaluate the robustness of SOT methods, we propose BioDrone -- the first bionic drone-based visual benchmark for SOT. Unlike existing UAV datasets, BioDrone features videos captured from a flapping-wing UAV system with a major camera shake due to its aerodynamics. BioDrone hence highlights the tracking of tiny targets with drastic changes between consecutive frames, providing a new robust vision benchmark for SOT. To date, BioDrone offers the largest UAV-based SOT benchmark with high-quality fine-grained manual annotations and automatically generates frame-level labels, designed for robust vision analyses. Leveraging our proposed BioDrone, we conduct a systematic evaluation of existing SOT methods, comparing the performance of 20 representative models and studying novel means of optimizing a SOTA method (KeepTrack KeepTrack) for robust SOT. Our evaluation leads to new baselines and insights for robust SOT. Moving forward, we hope that BioDrone will not only serve as a high-quality benchmark for robust SOT, but also invite future research into robust computer vision. The database, toolkits, evaluation server, and baseline results are available at http://biodrone.aitestunion.com.

Allen He, Qi Liu, Kun Liu et al.

Temporal sentence grounding in videos (TSGV) aims to localize a temporal segment that semantically corresponds to a sentence query from an untrimmed video. Most current methods adopt pre-trained query-agnostic visual encoders for offline feature extraction, and the video backbones are frozen and not optimized for TSGV. This leads to a task discrepancy issue for the video backbone trained for visual classification, but utilized for TSGV. To bridge this gap, we propose a fully end-to-end paradigm that jointly optimizes the video backbone and localization head. We first conduct an empirical study validating the effectiveness of end-to-end learning over frozen baselines across different model scales. Furthermore, we introduce a Sentence Conditioned Adapter (SCADA), which leverages sentence features to train a small portion of video backbone parameters adaptively. SCADA facilitates the deployment of deeper network backbones with reduced memory and significantly enhances visual representation by modulating feature maps through precise integration of linguistic embeddings. Experiments on two benchmarks show that our method outperforms state-of-the-art approaches. The code and models will be released.

Kun Liu, Qi Liu, Xinchen Liu et al.

Text-to-video (T2V) generation has made tremendous progress in generating complicated scenes based on texts. However, human-object interaction (HOI) often cannot be precisely generated by current T2V models due to the lack of large-scale videos with accurate captions for HOI. To address this issue, we introduce HOIGen-1M, the first largescale dataset for HOI Generation, consisting of over one million high-quality videos collected from diverse sources. In particular, to guarantee the high quality of videos, we first design an efficient framework to automatically curate HOI videos using the powerful multimodal large language models (MLLMs), and then the videos are further cleaned by human annotators. Moreover, to obtain accurate textual captions for HOI videos, we design a novel video description method based on a Mixture-of-Multimodal-Experts (MoME) strategy that not only generates expressive captions but also eliminates the hallucination by individual MLLM. Furthermore, due to the lack of an evaluation framework for generated HOI videos, we propose two new metrics to assess the quality of generated videos in a coarse-to-fine manner. Extensive experiments reveal that current T2V models struggle to generate high-quality HOI videos and confirm that our HOIGen-1M dataset is instrumental for improving HOI video generation. Project webpage is available at https://liuqi-creat.github.io/HOIGen.github.io.

Rong Fu, Zijian Zhang, Wenxin Zhang et al.

Comparative analysis of adaptive immune repertoires at population scale is hampered by two practical bottlenecks: the near-quadratic cost of pairwise affinity evaluations and dataset imbalances that obscure clinically important minority clonotypes. We introduce SubQuad, an end-to-end pipeline that addresses these challenges by combining antigen-aware, near-subquadratic retrieval with GPU-accelerated affinity kernels, learned multimodal fusion, and fairness-constrained clustering. The system employs compact MinHash prefiltering to sharply reduce candidate comparisons, a differentiable gating module that adaptively weights complementary alignment and embedding channels on a per-pair basis, and an automated calibration routine that enforces proportional representation of rare antigen-specific subgroups. On large viral and tumor repertoires SubQuad achieves measured gains in throughput and peak memory usage while preserving or improving recall@k, cluster purity, and subgroup equity. By co-designing indexing, similarity fusion, and equity-aware objectives, SubQuad offers a scalable, bias-aware platform for repertoire mining and downstream translational tasks such as vaccine target prioritization and biomarker discovery.

Rong Fu, Muge Qi, Chunlei Meng et al.

Graph neural networks frequently encounter significant performance degradation when confronted with structural noise or non-homophilous topologies. To address these systemic vulnerabilities, we present AdvSynGNN, a comprehensive architecture designed for resilient node-level representation learning. The proposed framework orchestrates multi-resolution structural synthesis alongside contrastive objectives to establish geometry-sensitive initializations. We develop a transformer backbone that adaptively accommodates heterophily by modulating attention mechanisms through learned topological signals. Central to our contribution is an integrated adversarial propagation engine, where a generative component identifies potential connectivity alterations while a discriminator enforces global coherence. Furthermore, label refinement is achieved through a residual correction scheme guided by per-node confidence metrics, which facilitates precise control over iterative stability. Empirical evaluations demonstrate that this synergistic approach effectively optimizes predictive accuracy across diverse graph distributions while maintaining computational efficiency. The study concludes with practical implementation protocols to ensure the robust deployment of the AdvSynGNN system in large-scale environments.

Rong Fu, Ziming Wang, Shuo Yin et al.

Emotional expression underpins natural communication and effective human-computer interaction. We present Emotion Collider (EC-Net), a hyperbolic hypergraph framework for multimodal emotion and sentiment modeling. EC-Net represents modality hierarchies using Poincare-ball embeddings and performs fusion through a hypergraph mechanism that passes messages bidirectionally between nodes and hyperedges. To sharpen class separation, contrastive learning is formulated in hyperbolic space with decoupled radial and angular objectives. High-order semantic relations across time steps and modalities are preserved via adaptive hyperedge construction. Empirical results on standard multimodal emotion benchmarks show that EC-Net produces robust, semantically coherent representations and consistently improves accuracy, particularly when modalities are partially available or contaminated by noise. These findings indicate that explicit hierarchical geometry combined with hypergraph fusion is effective for resilient multimodal affect understanding.

Rong Fu, Zijian Zhang, Haiyun Wei et al.

The continuous expansion of digital learning environments has catalyzed the demand for intelligent systems capable of providing personalized educational content. While current exercise recommendation frameworks have made significant strides, they frequently encounter obstacles regarding the long-tailed distribution of student engagement and the failure to adapt to idiosyncratic learning trajectories. We present LiveGraph, a novel active-structure neural re-ranking framework designed to overcome these limitations. Our approach utilizes a graph-based representation enhancement strategy to bridge the information gap between active and inactive students while integrating a dynamic re-ranking mechanism to foster content diversity. By prioritizing the structural relationships within learning histories, the proposed model effectively balances recommendation precision with pedagogical variety. Comprehensive experimental evaluations conducted on multiple real-world datasets demonstrate that LiveGraph surpasses contemporary baselines in both predictive accuracy and the breadth of exercise diversity.

Ke Wang, Lei He, Kun Liu et al.

Large Multimodal Models (LMMs) have demonstrated exceptional performance across a wide range of domains. This paper explores their potential in pronunciation assessment tasks, with a particular focus on evaluating the capabilities of the Generative Pre-trained Transformer (GPT) model, specifically GPT-4o. Our study investigates its ability to process speech and audio for pronunciation assessment across multiple levels of granularity and dimensions, with an emphasis on feedback generation and scoring. For our experiments, we use the publicly available Speechocean762 dataset. The evaluation focuses on two key aspects: multi-level scoring and the practicality of the generated feedback. Scoring results are compared against the manual scores provided in the Speechocean762 dataset, while feedback quality is assessed using Large Language Models (LLMs). The findings highlight the effectiveness of integrating LMMs with traditional methods for pronunciation assessment, offering insights into the model's strengths and identifying areas for further improvement.

Bo Liu, Pengfei Qiao, Minhan Ma et al.

Understanding surveillance video content remains a critical yet underexplored challenge in vision-language research, particularly due to its real-world complexity, irregular event dynamics, and safety-critical implications. In this work, we introduce SurveillanceVQA-589K, the largest open-ended video question answering benchmark tailored to the surveillance domain. The dataset comprises 589,380 QA pairs spanning 12 cognitively diverse question types, including temporal reasoning, causal inference, spatial understanding, and anomaly interpretation, across both normal and abnormal video scenarios. To construct the benchmark at scale, we design a hybrid annotation pipeline that combines temporally aligned human-written captions with Large Vision-Language Model-assisted QA generation using prompt-based techniques. We also propose a multi-dimensional evaluation protocol to assess contextual, temporal, and causal comprehension. We evaluate eight LVLMs under this framework, revealing significant performance gaps, especially in causal and anomaly-related tasks, underscoring the limitations of current models in real-world surveillance contexts. Our benchmark provides a practical and comprehensive resource for advancing video-language understanding in safety-critical applications such as intelligent monitoring, incident analysis, and autonomous decision-making.

Kun Liu, Jin Zhao

In the field of finance, the prediction of individual credit default is of vital importance. However, existing methods face problems such as insufficient interpretability and transparency as well as limited performance when dealing with high-dimensional and nonlinear data. To address these issues, this paper introduces a method based on Kolmogorov-Arnold Networks (KANs). KANs is a new type of neural network architecture with learnable activation functions and no linear weights, which has potential advantages in handling complex multi-dimensional data. Specifically, this paper applies KANs to the field of individual credit risk prediction for the first time and constructs the Kolmogorov-Arnold Credit Default Predict (KACDP) model. Experiments show that the KACDP model outperforms mainstream credit default prediction models in performance metrics (ROC_AUC and F1 values). Meanwhile, through methods such as feature attribution scores and visualization of the model structure, the model's decision-making process and the importance of different features are clearly demonstrated, providing transparent and interpretable decision-making basis for financial institutions and meeting the industry's strict requirements for model interpretability. In conclusion, the KACDP model constructed in this paper exhibits excellent predictive performance and satisfactory interpretability in individual credit risk prediction, providing an effective way to address the limitations of existing methods and offering a new and practical credit risk prediction tool for financial institutions.

Rong Fu, Wenxin Zhang, Chunlei Meng et al.

The pursuit of optimal trade-offs in high-dimensional search spaces under stringent computational constraints poses a fundamental challenge for contemporary multi-objective optimization. We develop NeuroPareto, a cohesive architecture that integrates rank-centric filtering, uncertainty disentanglement, and history-conditioned acquisition strategies to navigate complex objective landscapes. A calibrated Bayesian classifier estimates epistemic uncertainty across non-domination tiers, enabling rapid generation of high-quality candidates with minimal evaluation cost. Deep Gaussian Process surrogates further separate predictive uncertainty into reducible and irreducible components, providing refined predictive means and risk-aware signals for downstream selection. A lightweight acquisition network, trained online from historical hypervolume improvements, guides expensive evaluations toward regions balancing convergence and diversity. With hierarchical screening and amortized surrogate updates, the method maintains accuracy while keeping computational overhead low. Experiments on DTLZ and ZDT suites and a subsurface energy extraction task show that NeuroPareto consistently outperforms classifier-enhanced and surrogate-assisted baselines in Pareto proximity and hypervolume.

Kun Liu, Tuozhen Liu, Feifei Wang et al.

Existing e-commerce platforms heavily rely on manual annotation for product categorization, which is inefficient and inconsistent. These platforms often employ a hierarchical structure for categorizing products; however, few studies have leveraged this hierarchical information for classification. Furthermore, studies that consider hierarchical information fail to account for similarities and differences across various hierarchical categories. Herein, we introduce a large-scale hierarchical dataset collected from the JD e-commerce platform (www.JD.com), comprising 1,011,450 products with titles and a three-level category structure. By making this dataset openly accessible, we provide a valuable resource for researchers and practitioners to advance research and applications associated with product categorization. Moreover, we propose a novel hierarchical text classification approach based on the widely used Bidirectional Encoder Representations from Transformers (BERT), called Hierarchical Fine-tuning BERT (HFT-BERT). HFT-BERT leverages the remarkable text feature extraction capabilities of BERT, achieving prediction performance comparable to those of existing methods on short texts. Notably, our HFT-BERT model demonstrates exceptional performance in categorizing longer short texts, such as books.

Xiaodong Chen, Xinchen Liu, Kun Liu et al.

This technical report introduces our 2nd place solution to Kinetics-TPS Track on Part-level Action Parsing in ICCV DeeperAction Workshop 2021. Our entry is mainly based on YOLOF for instance and part detection, HRNet for human pose estimation, and CSN for video-level action recognition and frame-level part state parsing. We describe technical details for the Kinetics-TPS dataset, together with some experimental results. In the competition, we achieved 61.37% mAP on the test set of Kinetics-TPS.

Xiaopeng Li, Jiang Wu, Zhanbo Xu et al.

Aggregated stochastic characteristics of geographically distributed wind generation will provide valuable information for secured and economical system operation in electricity markets. This paper focuses on the uncertainty set prediction of the aggregated generation of geographically distributed wind farms. A Spatio-temporal model is proposed to learn the dynamic features from partial observation in near-surface wind fields of neighboring wind farms. We use Bayesian LSTM, a probabilistic prediction model, to obtain the uncertainty set of the generation in individual wind farms. Then, spatial correlation between different wind farms is presented to correct the output results. Numerical testing results based on the actual data with 6 wind farms in northwest China show that the uncertainty set of aggregated wind generation of distributed wind farms is less volatile than that of a single wind farm.

Kun Liu, Huadong Ma, Chuang Gan

We address the challenging task of cross-modal moment retrieval, which aims to localize a temporal segment from an untrimmed video described by a natural language query. It poses great challenges over the proper semantic alignment between vision and linguistic domains. Existing methods independently extract the features of videos and sentences and purely utilize the sentence embedding in the multi-modal fusion stage, which do not make full use of the potential of language. In this paper, we present Language Guided Networks (LGN), a new framework that leverages the sentence embedding to guide the whole process of moment retrieval. In the first feature extraction stage, we propose to jointly learn visual and language features to capture the powerful visual information which can cover the complex semantics in the sentence query. Specifically, the early modulation unit is designed to modulate the visual feature extractor's feature maps by a linguistic embedding. Then we adopt a multi-modal fusion module in the second fusion stage. Finally, to get a precise localizer, the sentence information is utilized to guide the process of predicting temporal positions. Specifically, the late guidance module is developed to linearly transform the output of localization networks via the channel attention mechanism. The experimental results on two popular datasets demonstrate the superior performance of our proposed method on moment retrieval (improving by 5.8\% in terms of Rank1@IoU0.5 on Charades-STA and 5.2\% on TACoS). The source code for the complete system will be publicly available.

Kun Liu, Wu Liu, Huadong Ma et al.

Deep neural networks have achieved remarkable success for video-based action recognition. However, most of existing approaches cannot be deployed in practice due to the high computational cost. To address this challenge, we propose a new real-time convolutional architecture, called Temporal Convolutional 3D Network (T-C3D), for action representation. T-C3D learns video action representations in a hierarchical multi-granularity manner while obtaining a high process speed. Specifically, we propose a residual 3D Convolutional Neural Network (CNN) to capture complementary information on the appearance of a single frame and the motion between consecutive frames. Based on this CNN, we develop a new temporal encoding method to explore the temporal dynamics of the whole video. Furthermore, we integrate deep compression techniques with T-C3D to further accelerate the deployment of models via reducing the size of the model. By these means, heavy calculations can be avoided when doing the inference, which enables the method to deal with videos beyond real-time speed while keeping promising performance. Our method achieves clear improvements on UCF101 action recognition benchmark against state-of-the-art real-time methods by 5.4% in terms of accuracy and 2 times faster in terms of inference speed with a less than 5MB storage model. We validate our approach by studying its action representation performance on four different benchmarks over three different tasks. Extensive experiments demonstrate comparable recognition performance to the state-of-the-art methods. The source code and the pre-trained models are publicly available at https://github.com/tc3d.

Tingting Zhang, Yushi Lan, Aiguo Song et al.

The network information system is a military information network system with evolution characteristics. Evolution is a process of replacement between disorder and order, chaos and equilibrium. Given that the concept of evolution originates from biological systems, in this article, the evolution of network information architecture is analyzed by genetic algorithms, and the network information architecture is represented by chromosomes. Besides, the genetic algorithm is also applied to find the optimal chromosome in the architecture space. The evolutionary simulation is used to predict the optimal scheme of the network information architecture and provide a reference for system construction.

Peng Xu, Kun Liu, Tao Xiang et al.

Existing sketch-analysis work studies sketches depicting static objects or scenes. In this work, we propose a novel cross-modal retrieval problem of fine-grained instance-level sketch-based video retrieval (FG-SBVR), where a sketch sequence is used as a query to retrieve a specific target video instance. Compared with sketch-based still image retrieval, and coarse-grained category-level video retrieval, this is more challenging as both visual appearance and motion need to be simultaneously matched at a fine-grained level. We contribute the first FG-SBVR dataset with rich annotations. We then introduce a novel multi-stream multi-modality deep network to perform FG-SBVR under both strong and weakly supervised settings. The key component of the network is a relation module, designed to prevent model over-fitting given scarce training data. We show that this model significantly outperforms a number of existing state-of-the-art models designed for video analysis.

Fenggen Yu, Kun Liu, Yan Zhang et al.

Deep learning approaches to 3D shape segmentation are typically formulated as a multi-class labeling problem. Existing models are trained for a fixed set of labels, which greatly limits their flexibility and adaptivity. We opt for top-down recursive decomposition and develop the first deep learning model for hierarchical segmentation of 3D shapes, based on recursive neural networks. Starting from a full shape represented as a point cloud, our model performs recursive binary decomposition, where the decomposition network at all nodes in the hierarchy share weights. At each node, a node classifier is trained to determine the type (adjacency or symmetry) and stopping criteria of its decomposition. The features extracted in higher level nodes are recursively propagated to lower level ones. Thus, the meaningful decompositions in higher levels provide strong contextual cues constraining the segmentations in lower levels. Meanwhile, to increase the segmentation accuracy at each node, we enhance the recursive contextual feature with the shape feature extracted for the corresponding part. Our method segments a 3D shape in point cloud into an unfixed number of parts, depending on the shape complexity, showing strong generality and flexibility. It achieves the state-of-the-art performance, both for fine-grained and semantic segmentation, on the public benchmark and a new benchmark of fine-grained segmentation proposed in this work. We also demonstrate its application for fine-grained part refinements in image-to-shape reconstruction.

Haiyong Chen, Yue Pang, Qidi Hu et al.

Similar and indeterminate defect detection of solar cell surface with heterogeneous texture and complex background is a challenge of solar cell manufacturing. The traditional manufacturing process relies on human eye detection which requires a large number of workers without a stable and good detection effect. In order to solve the problem, a visual defect detection method based on multi-spectral deep convolutional neural network (CNN) is designed in this paper. Firstly, a selected CNN model is established. By adjusting the depth and width of the model, the influence of model depth and kernel size on the recognition result is evaluated. The optimal CNN model structure is selected. Secondly, the light spectrum features of solar cell color image are analyzed. It is found that a variety of defects exhibited different distinguishable characteristics in different spectral bands. Thus, a multi-spectral CNN model is constructed to enhance the discrimination ability of the model to distinguish between complex texture background features and defect features. Finally, some experimental results and K-fold cross validation show that the multi-spectral deep CNN model can effectively detect the solar cell surface defects with higher accuracy and greater adaptability. The accuracy of defect recognition reaches 94.30%. Applying such an algorithm can increase the efficiency of solar cell manufacturing and make the manufacturing process smarter.

Yuling Li, Kun Liu, Wei He et al.

In this paper, bilateral teleoperation of multiple slaves coupled to a single master under scheduling communication is investigated. The sampled-data transmission between the master and the multiple slaves is fulfilled over a delayed communication network, and at each sampling instant, only one slave is allowed to transmit its current information to the master side according to some scheduling protocols. To achieve the master-slave synchronization, Round-Robin scheduling protocol and Try-Once-Discard scheduling protocol are employed, respectively. By designing a scheduling-communication-based controller, some sufficient stability criteria related to the controller gain matrices, sampling intervals, and communication delays are obtained for the closed-loop teleoperation system under Round-Robin and Try-Once-Discard scheduling protocols, respectively. Finally, simulation studies are given to validate the effectiveness of the proposed results.

Kun Liu, Wu Liu, Huadong Ma et al.

Action recognition in surveillance video makes our life safer by detecting the criminal events or predicting violent emergencies. However, efficient action recognition is not free of difficulty. First, there are so many action classes in daily life that we cannot pre-define all possible action classes beforehand. Moreover, it is very hard to collect real-word videos for certain particular actions such as steal and street fight due to legal restrictions and privacy protection. These challenges make existing data-driven recognition methods insufficient to attain desired performance. Zero-shot learning is potential to be applied to solve these issues since it can perform classification without positive example. Nevertheless, current zero-shot learning algorithms have been studied under the unreasonable setting where seen classes are absent during the testing phase. Motivated by this, we study the task of action recognition in surveillance video under a more realistic \emph{generalized zero-shot setting}, where testing data contains both seen and unseen classes. To our best knowledge, this is the first work to study video action recognition under the generalized zero-shot setting. We firstly perform extensive empirical studies on several existing zero-shot leaning approaches under this new setting on a web-scale video data. Our experimental results demonstrate that, under the generalize setting, typical zero-shot learning methods are no longer effective for the dataset we applied. Then, we propose a method for action recognition by deploying generalized zero-shot learning, which transfers the knowledge of web video to detect the anomalous actions in surveillance videos. To verify the effectiveness of our proposed method, we further construct a new surveillance video dataset consisting of nine action classes related to the public safety situation.

Li Yi, Lin Shao, Manolis Savva et al.

We introduce a large-scale 3D shape understanding benchmark using data and annotation from ShapeNet 3D object database. The benchmark consists of two tasks: part-level segmentation of 3D shapes and 3D reconstruction from single view images. Ten teams have participated in the challenge and the best performing teams have outperformed state-of-the-art approaches on both tasks. A few novel deep learning architectures have been proposed on various 3D representations on both tasks. We report the techniques used by each team and the corresponding performances. In addition, we summarize the major discoveries from the reported results and possible trends for the future work in the field.

Abraham Bagherjeiran, Nemanja Djuric, Mihajlo Grbovic et al.

Proceedings of the 2017 AdKDD and TargetAd Workshop held in conjunction with the 23rd ACM SIGKDD Conference on Knowledge Discovery and Data Mining Halifax, Nova Scotia, Canada.