arXivSub Start free trial

AAAI 2023 Papers with Code β€” Page 7

AAAI Conference on Artificial Intelligence Β· 696 papers

Socially Optimal Non-discriminatory Restrictions for Continuous-Action Games

Michael Oesterle (University of Mannheim), Guni Sharon (Texas A&M University)

CodeOptimizationReinforcement LearningTabular

🎯 What it does: This paper proposes to enhance the social utility of the minimum Nash equilibrium in continuous action multi-player games through a unified action space constraint (non-discriminatory constraint) and presents the SOAR algorithm to achieve this goal.

Solving Explainability Queries with Quantification: The Case of Feature Relevancy

Xuanxiang Huang (University of Toulouse), Joao Marques-Silva (National University of Singapore)

CodeExplainability and InterpretabilityComputational EfficiencyTabularBenchmark

🎯 What it does: This study investigates the quantification problem of Feature Relevance Queries (FRP) and proposes an algorithm applicable to any machine learning classifier, with experimental validation conducted on random forests.

Sparse Coding in a Dual Memory System for Lifelong Learning

Fahad Sarfraz (NavInfo Europe), Bahram Zonooz (Eindhoven University of Technology)

CodeClassificationConvolutional Neural NetworkReinforcement LearningImage

🎯 What it does: The SCoMMER method is proposed, which combines sparse activation and multiple memory replay in continual learning, mimicking the brain's sparse coding and multi-memory system to alleviate catastrophic forgetting.

Sparse Maximum Margin Learning from Multimodal Human Behavioral Patterns

Ervine Zheng (Rochester Institute of Technology), Zhi Zheng (Rochester Institute of Technology)

CodeClassificationExplainability and InterpretabilityRecurrent Neural NetworkMultimodalityBiomedical Data

🎯 What it does: A dynamic multimodal data fusion framework based on a two-layer probabilistic mixture model (SM2-MRS) is proposed, which simultaneously conducts pattern mining and maximum margin learning, utilizing group sparse priors to filter patterns that contribute to classification.

Spatial-Spectral Transformer for Hyperspectral Image Denoising

Miaoyu Li (Beijing Institute of Technology), Yulun Zhang (ETH Zurich)

CodeRestorationTransformerImage

🎯 What it does: A spatial-spectral Transformer (SST) is proposed for hyperspectral image (HSI) denoising.

Spatio-Temporal Neural Structural Causal Models for Bike Flow Prediction

Pan Deng (Beihang University), Mulan Wang (Beihang University)

CodeGraph Neural NetworkTime Series

🎯 What it does: This paper proposes a spatiotemporal neural structural causal model (STNSCM) based on structural causal models, which eliminates confounding interference through the frontdoor criterion and combines dynamic causal graphs with a counterfactual representation reasoning module to predict the flow of bike-sharing systems.

Spatio-Temporal Self-Supervised Learning for Traffic Flow Prediction

Jiahao Ji (Beihang University), Yu Zheng (JD Technology)

CodeGraph Neural NetworkContrastive LearningTime Series

🎯 What it does: A spatial-temporal model ST-SSL based on self-supervised learning is proposed for urban traffic flow prediction.

Spatiotemporal Deformation Perception for Fisheye Video Rectification

Shangrong Yang (Beijing Jiaotong University), Yao Zhao (Beijing Jiaotong University)

CodeImage TranslationRestorationConvolutional Neural NetworkGenerative Adversarial NetworkOptical FlowVideo

🎯 What it does: A fisheye video correction framework based on spatiotemporal deformation perception is proposed, achieving stable and accurate correction through optical flow estimation and enhancement.

Spectral Feature Augmentation for Graph Contrastive Learning and Beyond

Yifei Zhang (Chinese University of Hong Kong), Irwin King (Chinese University of Hong Kong)

CodeClassificationRepresentation LearningGraph Neural NetworkContrastive LearningImageGraph

🎯 What it does: This paper proposes a Spectral Feature Augmentation (SFA) method based on incomplete power iteration, aimed at rebalancing the singular values of the feature matrix and injecting noise in graph contrastive learning (GCL) and image contrastive learning, thereby enhancing the alignment and generalization capabilities of representations.

SSDA3D: Semi-supervised Domain Adaptation for 3D Object Detection from Point Cloud

Yan Wang (Beijing Institute of Technology), Jianbing Shen (University of Macau)

CodeObject DetectionDomain AdaptationAutonomous DrivingPoint Cloud

🎯 What it does: This paper proposes a framework for semi-supervised domain adaptation (SSDA) in 3D object detection, named SSDA3D, which addresses the significant domain gap between the source and target domains and enhances performance using a small amount of target annotations.

STAGE: Span Tagging and Greedy Inference Scheme for Aspect Sentiment Triplet Extraction

Shuo Liang (Huazhong University of Science and Technology), Dangyang Chen (Ping An Property and Casualty Insurance Company of China)

CodeTransformerSupervised Fine-TuningText

🎯 What it does: This paper proposes the STAGE framework, which employs span-level labeling and greedy inference for the Aspect Sentiment Triplet Extraction (ASTE) task, constructing an end-to-end BERT-based model capable of simultaneously identifying aspect terms, opinion terms, and their sentiment polarity.

Stroke Extraction of Chinese Character Based on Deep Structure Deformable Image Registration

Meng Li (Institute of Automation, Chinese Academy of Sciences), Jian Wang (Institute of Automation, Chinese Academy of Sciences)

CodeSegmentationConvolutional Neural NetworkImage

🎯 What it does: A method for extracting Chinese character strokes based on deep learning is proposed, utilizing structure-variable image registration, semantic segmentation, and single-stroke extraction networks to achieve precise separation and matching of strokes.

Structure Flow-Guided Network for Real Depth Super-resolution

Jiayi Yuan (Nanjing University of Science and Technology), Jian Yang (Nanjing University of Science and Technology)

CodeRestorationDepth EstimationSuper ResolutionOptical FlowImageMultimodality

🎯 What it does: A structure flow-guided deep depth map super-resolution framework (SFG) is proposed to recover structural distortions and edge noise in real scenes.

Structured BFGS Method for Optimal Doubly Stochastic Matrix Approximation

Dejun Chu (Hefei University of Technology), Qing Tao (Tsinghua University)

CodeOptimizationTabular

🎯 What it does: A structured BFGS algorithm is proposed to find the optimal approximation of a given matrix on the Birkhoff polytope (i.e., the set of doubly stochastic matrices), transforming the problem into unconstrained smooth optimization using the dual-dual form;

Structured Case-Based Reasoning for Inference-Time Adaptation of Text-to-SQL Parsers

Abhijeet Awasthi (Indian Institute of Technology Bombay), Sunita Sarawagi (Indian Institute of Technology Bombay)

CodeDomain AdaptationOptimizationTransformerLarge Language ModelSupervised Fine-TuningText

🎯 What it does: This paper proposes a structured case-based reasoning (StructCBR) method that does not require retraining parameters during inference, aimed at quickly adapting Text-to-SQL models to new database schemas.

Style-Content Metric Learning for Multidomain Remote Sensing Object Recognition

Wenda Zhao (Dalian University of Technology), You He (Tsinghua University)

CodeRecognitionObject DetectionContrastive LearningImage

🎯 What it does: A style-content metric learning framework is proposed to address the generalization problem in multi-domain remote sensing object recognition.

StyleTalk: One-Shot Talking Head Generation with Controllable Speaking Styles

Yifeng Ma (Tsinghua University), Xin Yu (University of Technology Sydney)

CodeGenerationTransformerGenerative Adversarial NetworkImageVideoAudio

🎯 What it does: A controllable talking head generation framework called StyleTalk is proposed, which can synthesize realistic talking videos with any reference video speaking style from a single target image and a segment of audio.

SumREN: Summarizing Reported Speech about Events in News

Revanth Gangi Reddy (University of Illinois Urbana-Champaign), Heng Ji (University of Macau)

CodeTransformerLarge Language ModelPrompt EngineeringTextBenchmark

🎯 What it does: This paper proposes the task of summarizing reporting statements from different speakers about events in news texts and constructs the SUMREN benchmark dataset.

Super-efficient Echocardiography Video Segmentation via Proxy- and Kernel-Based Semi-supervised Learning

Huisi Wu (Shenzhen University), Jing Qin (Hong Kong Polytechnic University)

CodeSegmentationConvolutional Neural NetworkVideoUltrasound

🎯 What it does: A semi-supervised cardiac ultrasound video segmentation network based on agents and convolutional kernels, PKEcho-Net, is proposed to achieve real-time segmentation of the left ventricular endocardium.

Superpoint Transformer for 3D Scene Instance Segmentation

Jiahao Sun (South China University of Technology), Xiangmin Xu (South China University of Technology)

CodeObject DetectionSegmentationTransformerPoint Cloud

🎯 What it does: Proposes an end-to-end 3D instance segmentation method SPFormer based on Superpoint Transformer.

Supervised Contrastive Few-Shot Learning for High-Frequency Time Series

Xi Chen (Alibaba Group), Jin Wang (Alibaba Group)

CodeClassificationAnomaly DetectionRepresentation LearningConvolutional Neural NetworkContrastive LearningTime Series

🎯 What it does: A supervised contrastive learning framework SCFSL has been developed for few-shot representation learning and classification of high-frequency vibration time series.

Sustaining Fairness via Incremental Learning

Somnath Basu Roy Chowdhury (University of North Carolina at Chapel Hill), Snigdha Chaturvedi (University of North Carolina at Chapel Hill)

CodeAdversarial AttackTabular

🎯 What it does: Proposes the FaIRL framework, which simultaneously learns fair representations and maintains performance on new tasks in an incremental learning environment.

SVFI: Spiking-Based Video Frame Interpolation for High-Speed Motion

Lujie Xia (Peking University), Tiejun Huang (Peking University)

CodeRestorationData SynthesisSpiking Neural NetworkOptical FlowVideo

🎯 What it does: A dual-modal video frame interpolation framework SVFI is proposed, which generates intermediate frames using the high temporal resolution binary pulse stream produced by a pulsed camera in conjunction with traditional RGB frames.

SwiftAvatar: Efficient Auto-Creation of Parameterized Stylized Character on Arbitrary Avatar Engines

Shizun Wang (Beijing University of Posts and Telecommunications), Jing Liu (Douyin Vision)

CodeGenerationData SynthesisConvolutional Neural NetworkGenerative Adversarial NetworkImage

🎯 What it does: This paper proposes an unsupervised SwiftAvatar framework that can automatically generate avatar parameters that meet user needs based on user selfies in any stylized avatar engine.

SWL-Adapt: An Unsupervised Domain Adaptation Model with Sample Weight Learning for Cross-User Wearable Human Activity Recognition

Rong Hu (Zhejiang University), Xing Tang (Zhejiang University)

CodeRecognitionDomain AdaptationMeta LearningTime Series

🎯 What it does: This paper proposes an unsupervised domain adaptation model SWL-Adapt, which achieves adaptive cross-user wearable human activity recognition through sample weight learning.

T2G-FORMER: Organizing Tabular Features into Relation Graphs Promotes Heterogeneous Feature Interaction

Jiahuan Yan (Zhejiang University), Jian Wu (Zhejiang University)

CodeClassificationOptimizationGraph Neural NetworkTransformerTabular

🎯 What it does: A feature relationship graph (FR-Graph) based on a Graph Estimator is proposed and embedded into the Transformer structure, forming T2G-FORMER, to enhance the heterogeneous feature interaction and prediction performance of tabular data.

Target-Aware Tracking with Long-Term Context Attention

Kaijie He (Guangxi Normal University), Zhiwen Wang (Guangxi University of Science and Technology)

CodeObject TrackingTransformerVideo

🎯 What it does: A Long Context Attention (LCA) module based on the fusion of multi-frame target and background information is proposed, which is embedded in a Transformer to construct the TATrack target-aware tracker, along with a dynamic template update strategy based on classification confidence.

Task-Specific Scene Structure Representations

Jisu Shin (Gwangju Institute of Science and Technology), Hae-Gon Jeon (Gwangju Institute of Science and Technology)

CodeSuper ResolutionConvolutional Neural NetworkImage

🎯 What it does: A lightweight neural network SSGNet is proposed, which can unsupervisedly generate task-specific scene structure-guided features and can be integrated as a plug-and-play module into low-level vision tasks.

TC-DWA:Text Clustering with Dual Word-Level Augmentation

Bo Cheng (Jilin University), Yi Chang (Jilin University)

CodeClassificationTransformerLarge Language ModelText

🎯 What it does: Using BERT for self-training and introducing dual word-level enhancement (anchor words and expected enhancement) to achieve unsupervised text clustering.

Temporal Knowledge Graph Reasoning with Historical Contrastive Learning

Yi Xu (Shanghai Jiao Tong University), Luoyi Fu (Shanghai Jiao Tong University)

CodeGraph Neural NetworkContrastive LearningGraphTime Series

🎯 What it does: This paper proposes a new model for event prediction in temporal knowledge graphs, CENET, which can simultaneously utilize the dependencies of historical and non-historical events, and identify the most relevant entities through contrastive learning of queries, ultimately achieving precise inference through a masking strategy.

Temporal-Frequency Co-training for Time Series Semi-supervised Learning

Zhen Liu (South China University of Technology), Linghao Wang (South China University of Technology)

CodeClassificationAnomaly DetectionContrastive LearningTime Series

🎯 What it does: This paper proposes a temporal semi-supervised learning framework TS-TFC based on dual views in the time domain and frequency domain, which enhances the utilization of unlabeled data through pseudo-label propagation and collaborative training.

Tensor Compressive Sensing Fused Low-Rankness and Local-Smoothness

Xinling Liu (Southwest University), Jianjun Wang (Southwest University)

CodeRestorationOptimizationImageVideo

🎯 What it does: A novel regularization method based on tensor compressed sensing is proposedβ€”Tensor Correlated Total Variation (TCTV), which utilizes low-rankness and local smoothness to recover high-dimensional tensor data.

Tensorized Incomplete Multi-View Clustering with Intrinsic Graph Completion

Shuping Zhao (Shenzhen Key Laboratory of Visual Object Detection and Recognition, Harbin Institute of Technology), Bob Zhang (University of Macau)

CodeRepresentation LearningMultimodality

🎯 What it does: A missing multi-view clustering method TIMVC IGC based on low-rank tensors and cross-view consistency constraints is proposed, which can simultaneously complete missing view inference, construct a complete graph, and learn co-representations.

Text to Point Cloud Localization with Relation-Enhanced Transformer

Guangzhi Wang (National University of Singapore), Mohan Kankanhalli (National University of Singapore)

CodePose EstimationRetrievalAutonomous DrivingTransformerTextPoint Cloud

🎯 What it does: This study investigates the problem of locating target positions in urban-scale point clouds based on natural language instructions, proposing a two-stage framework that first retrieves matching cells and then refines the instance matching and regresses the position.

Text-DIAE: A Self-Supervised Degradation Invariant Autoencoder for Text Recognition and Document Enhancement

Mohamed Ali Souibgui (Universitat AutΓ²noma de Barcelona), Dimosthenis Karatzas (Digital Research Center of Sfax)

CodeRecognitionRestorationTransformerAuto EncoderContrastive LearningImageText

🎯 What it does: This paper proposes a self-supervised degradation-invariant autoencoder (Text-DIAE) that is pre-trained by applying three degradation tasksβ€”masking, blurring, and noiseβ€”to text images, and then fine-tuned for handwritten/scenario text recognition and document image enhancement.

The Effect of Diversity in Meta-Learning

Ramnath Kumar (Google Research), Yoshua Bengio (Mila)

CodeMeta LearningImage

🎯 What it does: This study investigates the impact of task diversity on model performance in meta-learning and explores the relationship between task diversity and model generalization through experimental and theoretical analysis.

The Multi-Agent Transportation Problem

Pascal Bachor (Albert-Ludwigs-Universitat Freiburg), Bernhard Nebel (Albert-Ludwigs-Universitat Freiburg)

CodeOptimizationAgentic AIGraph

🎯 What it does: A multi-agent transportation problem (MAT) is proposed, along with a complete algorithm based on SAT solving;

The Sufficiency of Off-Policyness and Soft Clipping: PPO Is Still Insufficient according to an Off-Policy Measure

Xing Chen (Jilin University), Yi Chang (Jilin University)

CodeReinforcement LearningSequential

🎯 What it does: An improved PPO algorithm called P3O is proposed, which utilizes the importance sampling ratio with sigmoid preprocessing to achieve broader policy space exploration.

The Unreasonable Effectiveness of Deep Evidential Regression

Nis Meinert (Pasteur Labs), Alexander Lavin (Pasteur Labs)

CodeDepth EstimationImage

🎯 What it does: This paper analyzes and evaluates the effectiveness of Deep Evidential Regression (DER) in uncertainty estimation, revealing its theoretical flaws and providing suggestions for improvement.

The Value of AI Guidance in Human Examination of Synthetically-Generated Faces

Aidan Boyd (University of Notre Dame), Adam Czajka (University of Notre Dame)

CodeRecognitionGenerationExplainability and InterpretabilityConvolutional Neural NetworkGenerative Adversarial NetworkImage

🎯 What it does: This paper evaluates the effectiveness of AI-assisted human recognition of synthetic faces through large-scale experiments and compares the impact of different AI prompting methods and model training approaches on non-expert human detection of synthetic faces.

Time-Aware Random Walk Diffusion to Improve Dynamic Graph Learning

Jong-whi Lee (Jeonbuk National University), Jinhong Jung (Jeonbuk National University)

CodeOptimizationComputational EfficiencyGraph Neural NetworkGraph

🎯 What it does: A time-aware random walk diffusion method named TIARA is proposed to enhance the spatial and temporal locality of dynamic graphs, thereby improving the learning effectiveness of dynamic graph neural networks.

TinyNeRF: Towards 100 x Compression of Voxel Radiance Fields

Tianli Zhao (University of Chinese Academy of Sciences), Jian Cheng (Institute of Automation Chinese Academy of Sciences)

CodeCompressionNeural Radiance FieldPoint Cloud

🎯 What it does: This paper proposes TinyNeRF, which achieves a high compression rate for NeRF voxel models through three steps: frequency domain transformation, pruning, and quantization.

Token Mixing: Parameter-Efficient Transfer Learning from Image-Language to Video-Language

Yuqi Liu (Renmin University of China), Qin Jin (Renmin University of China)

CodeGenerationRetrievalTransformerVision Language ModelVideoTextMultimodality

🎯 What it does: A Token Mixing strategy is proposed to achieve parameter-efficient transfer of image-language models to video-language tasks without adding extra modules.

Toward Robust Diagnosis: A Contour Attention Preserving Adversarial Defense for COVID-19 Detection

Kun Xiang (Sun Yat-sen University), Shancheng Jiang (Sun Yat-sen University)

CodeClassificationDomain AdaptationAdversarial AttackTransformerContrastive LearningImageComputed Tomography

🎯 What it does: This paper proposes a novel adversarial defense method called CAP, based on maintaining attention to lung contours, aimed at enhancing the robustness of COVID-19 CT image classification.

Towards a Holistic Understanding of Mathematical Questions with Contrastive Pre-training

Yuting Ning (University of Science and Technology of China), Shijin Wang (iFLYTEK Co., Ltd.)

CodeTransformerContrastive LearningText

🎯 What it does: QuesCo is proposed, a comparative pre-training model for mathematical problems that enhances the generation of surface-diverse but semantically similar samples through a dual-layer content and structure approach, and learns overall semantic representations through knowledge hierarchy-based ranking and ranking contrastive loss.

Towards Automated Modeling Assistance: An Efficient Approach for Repairing Flawed Planning Domains

Songtuan Lin (Australian National University), Pascal Bercher (Australian National University)

CodeOptimizationComputational EfficiencyTabularBenchmark

🎯 What it does: An automatic domain repair method based on conflict detection and minimal hitting set is proposed, which can quickly locate and minimally repair the planning domain under the premise of a given erroneous plan, making the plan executable.

Towards Complex Scenarios: Building End-to-End Task-Oriented Dialogue System across Multiple Knowledge Bases

Libo Qin (Central South University), Wanxiang Che (Harbin Institute of Technology)

CodeRecurrent Neural NetworkGraph Neural NetworkText

🎯 What it does: This paper proposes a knowledge graph attention network named KoK-HAN to address the end-to-end task-oriented dialogue system problem in the context of multiple knowledge bases.

Towards Efficient and Domain-Agnostic Evasion Attack with High-Dimensional Categorical Inputs

Hongyan Bao (King Abdullah University of Science and Technology), Xiangliang Zhang (University of Notre Dame)

CodeComputational EfficiencyAdversarial AttackTextTabularBiomedical DataElectronic Health Records

🎯 What it does: This paper proposes a domain-agnostic attack method called FEAT for high-dimensional categorical inputs, aimed at efficiently finding feasible adversarial perturbations.

Towards Fine-Grained Explainability for Heterogeneous Graph Neural Network

Tong Li (Shanghai Jiao Tong University), Caleb Chen Cao (Huawei Research Hong Kong)

CodeExplainability and InterpretabilityGraph Neural NetworkGraph

🎯 What it does: This paper proposes the xPath framework to provide fine-grained interpretability for the node classification task of black-box heterogeneous graph neural networks (HGN), specifically by giving explanations of causal nodes and their influence paths.

Towards Global Video Scene Segmentation with Context-Aware Transformer

Yang Yang (Nanjing University of Science and Technology), Dingyin Xia (HUAWEI CBG Edu AI Lab)

CodeSegmentationTransformerVideo

🎯 What it does: The Context-Aware Transformer (CAT) model is proposed, which learns high-quality shot representations through self-supervised pre-training tasks, ultimately used for video scene segmentation.

Towards More Robust Interpretation via Local Gradient Alignment

Sunghwan Joo (Sungkyunkwan University), Taesup Moon (Seoul National University)

CodeOptimizationExplainability and InterpretabilityConvolutional Neural NetworkImage

🎯 What it does: This paper proposes a gradient alignment regularization method that combines β„“2 and cosine distance to enhance the robustness of deep network feature attribution.

Towards Optimal Randomized Strategies in Adversarial Example Game

Jiahao Xie (Zhejiang University), Hui Qian (Zhejiang University)

CodeOptimizationAdversarial AttackImageStochastic Differential Equation

🎯 What it does: This paper proposes the FRAT algorithm, which can solve the mixed Nash equilibrium of adversarial example games in continuous parameter spaces, thereby achieving fully randomized robust training.

Towards Real-Time Panoptic Narrative Grounding by an End-to-End Grounding Network

Haowei Wang (Xiamen University), Xiaoshuai Sun (Tencent)

CodeObject DetectionSegmentationConvolutional Neural NetworkContrastive LearningImageTextMultimodalityBenchmark

🎯 What it does: An end-to-end single-stage panoptic narrative grounding network (EPNG) is proposed, which can generate pixel masks corresponding to text descriptions in real-time, eliminating the candidate mask generation process of traditional two-stage methods.

Towards Reliable Neural Machine Translation with Consistency-Aware Meta-Learning

Rongxiang Weng (Soochow University), Min Zhang (Soochow University)

CodeMeta LearningTransformerText

🎯 What it does: A Consistency-Aware Meta-Learning (CAML) framework is proposed, which utilizes a combination of Transformer and MAML to learn semantically consistent representations in the outer loop and the mapping from these representations to target sentences in the inner loop, thereby enhancing the robustness and reliability of NMT to source diversity.

Towards Voice Reconstruction from EEG during Imagined Speech

Young-Eun Lee (Korea University), Seong-Whan Lee (Korea University)

CodeGenerationDomain AdaptationRecurrent Neural NetworkGenerative Adversarial NetworkTime SeriesAudio

🎯 What it does: This study proposes a generative framework named NeuroTalk, which utilizes non-invasive EEG (imagined speech) to reconstruct the user's own voice.

Tracking and Reconstructing Hand Object Interactions from Point Cloud Sequences in the Wild

Jiayi Chen (Peking University), He Wang (Stanford University)

CodeObject TrackingPose EstimationVideoPoint Cloud

🎯 What it does: Using deep point cloud sequences in a wild environment to track and reconstruct the pose and shape of hands and objects in real-time.

Training Meta-Surrogate Model for Transferable Adversarial Attack

Yunxiao Qin (Communication University of China), Cho-Jui Hsieh (University of California)

CodeOptimizationAdversarial AttackConvolutional Neural NetworkImage

🎯 What it does: This paper proposes a Meta-Transfer Attack (MTA) framework, which trains a Meta-Surrogate Model (MSM) so that attacks on the MSM can better transfer to the target model;

Transformation-Equivariant 3D Object Detection for Autonomous Driving

Hai Wu (Xiamen University), Cheng Wang (Xiamen University)

CodeObject DetectionAutonomous DrivingConvolutional Neural NetworkPoint Cloud

🎯 What it does: An efficient Transformation-Equivariant 3D object detection framework TED is proposed, which utilizes sparse convolution to extract multi-transform equivariant features, and compresses these features into lightweight representations through TeBEV pooling and TiVoxel pooling, achieving real-time and high-precision object detection.

TransLO: A Window-Based Masked Point Transformer Framework for Large-Scale LiDAR Odometry

Jiuming Liu (Shanghai Jiao Tong University), Hesheng Wang (China University of Mining and Technology)

CodePose EstimationAutonomous DrivingTransformerSimultaneous Localization and MappingPoint Cloud

🎯 What it does: A window attention-based point cloud Transformer network (TransLO) is proposed, which projects LiDAR point clouds into 2D pseudo-images and uses window mask self-attention and cross-frame attention to achieve end-to-end LiDAR odometry estimation.

TransVCL: Attention-Enhanced Video Copy Localization Network with Flexible Supervision

Sifeng He (Ant Group), Jiandong Zhang (Ant Group)

CodeRecognitionObject DetectionTransformerVideo

🎯 What it does: An end-to-end TransVCL network is proposed, which enhances frame features using Transformers to generate a differentiable similarity matrix, and achieves video segment localization through object detection.

Tree Learning: Optimal Sample Complexity and Algorithms

Dmitrii Avdiukhin (Indiana University), Faraz Mirza (Thomas Jefferson High School for Science and Technology)

CodeTabular

🎯 What it does: The study learns hierarchical tree representations from labeled tuples (such as triplets) and provides upper bounds on the optimal sample complexity in PAC learning and online learning scenarios; it also proposes a near-linear time tree construction algorithm.

TrEP: Transformer-Based Evidential Prediction for Pedestrian Intention with Uncertainty

Zhengming Zhang (Purdue University), Zhengming Ding (Tulane University)

CodeAutonomous DrivingTransformerTime Series

🎯 What it does: A Transformer-based evidence learning model, TrEP, has been designed and implemented for predicting pedestrian crossing intentions from the perspective of an autonomous vehicle, along with providing uncertainty estimates.

Two Heads Are Better than One: Image-Point Cloud Network for Depth-Based 3D Hand Pose Estimation

Pengfei Ren (Beijing University of Posts and Telecommunications), Jianxin Liao (Beijing University of Posts and Telecommunications)

CodePose EstimationDepth EstimationConvolutional Neural NetworkGraph Neural NetworkImagePoint Cloud

🎯 What it does: This paper proposes an IPNet network that simultaneously utilizes depth images and point clouds to achieve 3D hand pose estimation.

Ultra-High-Definition Low-Light Image Enhancement: A Benchmark and Transformer-Based Method

Tao Wang (Nanjing University), Tong Lu (Rakuten Institute of Technology)

CodeRestorationTransformerImageBenchmark

🎯 What it does: A novel dataset called UHD-LOL for ultra-high resolution (4K/8K) low-light image enhancement is proposed, and based on this dataset, the LLFormer Transformer model is introduced to achieve UHD-LLIE.

Uncertainty-Aware Self-Training for Low-Resource Neural Sequence Labeling

Jianing Wang (East China Normal University), Aoying Zhou (East China Normal University)

CodeClassificationRecognitionTransformerSupervised Fine-TuningTextSequential

🎯 What it does: This paper proposes SeqUST, a framework that utilizes uncertainty-aware self-training to address the low-resource neural sequence labeling problem.

Understanding Representation Learnability of Nonlinear Self-Supervised Learning

Ruofeng Yang (Shanghai Jiao Tong University), Shuai Li (Shanghai Jiao Tong University)

CodeRepresentation LearningContrastive LearningTabular

🎯 What it does: This study investigates the learning outcomes of a single-layer nonlinear self-supervised learning (SSL) model, demonstrating that it can converge to a local optimum after gradient descent training and accurately describes the feature representation corresponding to that optimum solution.

Uniform Sequence Better: Time Interval Aware Data Augmentation for Sequential Recommendation

Yizhou Dang (Northeastern University), Hong Liu (Alibaba Group)

CodeRecommendation SystemTransformerContrastive LearningSequential

🎯 What it does: This paper proposes a time interval-based data augmentation method for sequential data, converting non-uniform time interval sequences into uniform sequences to enhance sequence recommendation performance.

Unlabeled Imperfect Demonstrations in Adversarial Imitation Learning

Yunke Wang (Wuhan University), Chang Xu (University of Sydney)

CodeRobotic IntelligenceReinforcement LearningGenerative Adversarial NetworkSequential

🎯 What it does: A positive-negative unlabeled adversarial imitation learning framework UID is proposed to learn policies in situations where the demonstration data contains an unknown proportion of imperfect samples.

Unsupervised Cross-Domain Rumor Detection with Contrastive Learning and Cross-Attention

Hongyan Ran (Beijing Jiaotong University), Caiyan Jia (Beijing Jiaotong University)

CodeDomain AdaptationAnomaly DetectionTransformerContrastive LearningText

🎯 What it does: This paper proposes an unsupervised cross-domain rumor detection model UCD-RD, which combines instance-level and prototype-level contrastive learning along with a cross-attention mechanism to achieve feature alignment and robustness enhancement from the source domain to the target domain.

Unsupervised Deep Video Denoising with Untrained Network

Huan Zheng (National University of Singapore), Hui Ji (National University of Singapore)

CodeRestorationConvolutional Neural NetworkOptical FlowVideo

🎯 What it does: A completely unsupervised deep video denoising method that does not rely on clean video samples is proposed.

Unsupervised Explanation Generation via Correct Instantiations

Sijie Cheng (Fudan University), Lingpeng Kong (Shanghai Artificial Intelligence Laboratory)

CodeGenerationExplainability and InterpretabilityTransformerLarge Language ModelPrompt EngineeringText

🎯 What it does: A two-stage unsupervised explanation generation framework called NEON is designed and implemented, which first automatically generates correct instances that are similar to the commonality of erroneous statements, and then uses these instances to induce large pre-trained language models to implicitly infer conflict points and generate natural language explanations.

Unsupervised Legal Evidence Retrieval via Contrastive Learning with Approximate Aggregated Positive

Feng Yao (Tsinghua University), Weixing Shen (Tsinghua University)

CodeRetrievalTransformerContrastive LearningText

🎯 What it does: By constructing a dense retrieval model, this paper automatically retrieves oral evidence related to facts in criminal cases, helping judges quickly verify facts.

Unsupervised Multi-Exposure Image Fusion Breaking Exposure Limits via Contrastive Learning

Han Xu (Wuhan University), Jiayi Ma (Wuhan University)

CodeRestorationContrastive LearningImage

🎯 What it does: A novel unsupervised multi-exposure image fusion method MEF-CL is proposed, which utilizes contrastive learning to achieve exposure limitation breakthrough;

Untargeted Attack against Federated Recommendation Systems via Poisonous Item Embeddings and the Defense

Yang Yu (University of Science and Technology of China), Zaixi Zhang (University of Science and Technology of China)

CodeRecommendation SystemFederated LearningAdversarial AttackContrastive LearningTabular

🎯 What it does: For federated recommendation systems, we propose ClusterAttack, which uploads toxic gradient aggregates of item embeddings, leading to the failure of recommendation ranking. At the same time, we design the UNION defense mechanism, which uses contrastive learning to make item embeddings tend towards a uniform distribution, thereby detecting and filtering malicious gradients.

User-Controllable Arbitrary Style Transfer via Entropy Regularization

Jiaxin Cheng (University of Southern California), Prem Natarajan (Amazon)

CodeImage TranslationDomain AdaptationConvolutional Neural NetworkAuto EncoderImage

🎯 What it does: A user-controllable arbitrary style transfer (Ρ-Assign-and-Mix) framework based on entropy regularization is proposed, which can produce diverse style transfer results while maintaining speed and quality.

USER: Unsupervised Structural Entropy-Based Robust Graph Neural Network

Yifei Wang (University of Auckland), Jiamou Liu (University of Auckland)

CodeAnomaly DetectionRepresentation LearningGraph Neural NetworkGraph

🎯 What it does: This paper proposes an unsupervised robust graph neural network framework called USER, which constructs a harmless graph using a learnable adjacency matrix and unlabeled data, thereby offsetting random perturbations in the graph and learning more robust node representations.

Value-Consistent Representation Learning for Data-Efficient Reinforcement Learning

Yang Yue (Tsinghua University), Shuicheng Yan (Sea AI Lab)

CodeRepresentation LearningReinforcement LearningContrastive LearningVideo

🎯 What it does: This paper proposes a Value Consistent Representation Learning (VCR) method that enhances the sample efficiency of RL by predicting the value of imagined future states and aligning them with real states.

Variable-Based Calibration for Machine Learning Classifiers

Markelle Kelly (University of California, Irvine), Padhraic Smyth (University of California, Irvine)

CodeClassificationImageTextTabular

🎯 What it does: This paper proposes variable-based calibration (VCE, VECE) metrics and visualization methods, and calibrates specific variables to reveal systematic errors hidden by traditional ECE.

Variational Wasserstein Barycenters with C-cyclical Monotonicity Regularization

Jinjin Chi (Jilin University), Renchu Guan (Jilin University)

CodeOptimizationTabular

🎯 What it does: A variational Wasserstein barycenter method based on c-cyclic monotonicity regularization is proposed, which directly estimates the barycenter of continuous distributions using samples.

VBLC: Visibility Boosting and Logit-Constraint Learning for Domain Adaptive Semantic Segmentation under Adverse Conditions

Mingjia Li (Beijing Institute of Technology), Xinjing Cheng (Tsinghua University)

CodeObject DetectionSegmentationDomain AdaptationConvolutional Neural NetworkTransformerImage

🎯 What it does: This paper proposes an unsupervised domain adaptation framework VBLC that does not rely on normal image pairs, utilizing a visibility enhancement module and logarithmic it constraint learning to improve the robustness of semantic segmentation models under adverse weather conditions.

Video Compression Artifact Reduction by Fusing Motion Compensation and Global Context in a Swin-CNN Based Parallel Architecture

Xinjian Zhang (Fudan University), Weishan Zhang (China University of Petroleum)

CodeRestorationCompressionConvolutional Neural NetworkTransformerVideo

🎯 What it does: A novel spatiotemporal compensation fusion framework (STCF) is proposed, which removes video compression artifacts by integrating motion compensation and global context through parallel Ada-CNN and Swin self-attention.

Video Event Extraction via Tracking Visual States of Arguments

Guang Yang (Tsinghua University), Shih-Fu Chang (Columbia University)

CodeRecognitionObject DetectionObject TrackingConvolutional Neural NetworkRecurrent Neural NetworkTransformerVideo

🎯 What it does: A framework for event extraction based on the visual state changes of argumentative entities in videos is proposed, which identifies video events and their semantic roles by tracking pixel changes, positional displacements, and multi-object interactions.

Wasserstein Graph Distance Based on L1–Approximated Tree Edit Distance between Weisfeiler–Lehman Subtrees

Zhongxi Fang (Waseda University), Hiroyuki Kasai (Waseda University)

CodeGraph Neural NetworkGraphBiomedical Data

🎯 What it does: Proposes the Wasserstein distance based on WL subtree (WWLS) for L1-approximate tree edit distance, capturing fine-grained differences in graph structures and providing a new graph similarity measure.

WaveForM: Graph Enhanced Wavelet Learning for Long Sequence Forecasting of Multivariate Time Series

Fuhao Yang (Beijing Institute of Technology), Mingzhong Wang (The University of the Sunshine Coast)

CodeRecurrent Neural NetworkGraph Neural NetworkTime Series

🎯 What it does: This paper proposes WaveForM, an end-to-end multivariate time series forecasting framework based on discrete wavelet transform and graph convolution.

Weakly-Supervised Semantic Segmentation for Histopathology Images Based on Dataset Synthesis and Feature Consistency Constraint

Zijie Fang (Tsinghua University), Yongbing Zhang (Harbin Institute of Technology)

CodeSegmentationData SynthesisConvolutional Neural NetworkImageBiomedical Data

🎯 What it does: This paper proposes a weakly supervised semantic segmentation framework called PistoSeg, which generates a pixel-level annotated dataset by performing Mosaic synthesis on images of a single tissue category. It first trains a preliminary segmentation network on this synthetic dataset, and then refines the CAM and the pseudo-mask obtained from the preliminary segmentation using attention feature consistency, ultimately producing high-quality pseudo-masks for training a fine segmentation model.

Weight Predictor Network with Feature Selection for Small Sample Tabular Biomedical Data

Andrei Margeloiu (University of Cambridge), Mateja Jamnik (University of Cambridge)

CodeClassificationOptimizationComputational EfficiencyTabularBiomedical Data

🎯 What it does: A framework called WPFS, based on weight prediction networks and feature selection, has been designed and implemented for classification on high-dimensional, extremely small sample biomedical tabular data, significantly reducing learnable parameters and achieving global feature selection.

Weighted Policy Constraints for Offline Reinforcement Learning

Zhiyong Peng (National University of Defense Technology), Zongtan Zhou (National University of Defense Technology)

CodeReinforcement LearningTabular

🎯 What it does: A Weighted Policy Constraints (wPC) offline reinforcement learning algorithm is proposed and implemented, which applies constraints only to the desirable state-action pairs in the dataset during training, thereby alleviating distribution shift and improving policy performance.

What Does Your Face Sound Like? 3D Face Shape towards Voice

Zhihan Yang (Tsinghua University), Jia Jia (Tsinghua University)

CodeGenerationData SynthesisTransformerAudio

🎯 What it does: A speech generation framework based on 3D facial shapes is proposed, which maps the 3D facial model, texture, facial attributes, and demographic information to speaker embeddings to synthesize speech.

When Congestion Games Meet Mobile Crowdsourcing: Selective Information Disclosure

Hongbo Li (Singapore University of Technology and Design), Lingjie Duan (Singapore University of Technology and Design)

CodeOptimizationReinforcement LearningGraph

🎯 What it does: This paper studies how to incentivize self-interested users to achieve the optimal exploration-exploitation trade-off in a dynamic congestion game through information mechanisms in a mobile crowdsourcing environment, proposing a Selective Information Disclosure (SID) mechanism.

When Online Learning Meets ODE: Learning without Forgetting on Variable Feature Space

Diyang Li (Nanjing University of Information Science and Technology), Bin Gu (MBZUAI)

CodeTabularOrdinary Differential Equation

🎯 What it does: This paper proposes a dynamic feature learning system (DFLS) based on ordinary differential equations (ODEs), which can online update model parameters as the feature space changes over time and ensure convergence to the same optimal solution as a completely new training;

Where Will Players Move Next? Dynamic Graphs and Hierarchical Fusion for Movement Forecasting in Badminton

Kai-Shiang Chang (National Yang Ming Chiao Tung University), Wen-Chih Peng (National Yang Ming Chiao Tung University)

CodeGraph Neural NetworkGraphTime SeriesSequential

🎯 What it does: Proposes a motion prediction task that predicts the type and location of a player's next shot based on badminton rally records.

WLD-Reg: A Data-Dependent Within-Layer Diversity Regularizer

Firas Laakom (Tampere University), Moncef Gabbouj (Tampere University)

CodeOptimizationImage

🎯 What it does: A data-driven intra-layer diversity regularization method is proposed, encouraging the activation diversity of neurons within the same layer.

WSiP: Wave Superposition Inspired Pooling for Dynamic Interactions-Aware Trajectory Prediction

Renzhi Wang (Central South University), Xiang Wang (National University of Defense Technology)

CodeAutonomous DrivingExplainability and InterpretabilityRecurrent Neural NetworkGenerative Adversarial NetworkTime SeriesSequential

🎯 What it does: A wave-pooling method based on wave superposition is proposed and embedded into an encoding-decoding framework WSiP for predicting vehicle trajectories on highways.

Yet Another Traffic Classifier: A Masked Autoencoder Based Traffic Transformer with Multi-Level Flow Representation

Ruijie Zhao (Shanghai Jiao Tong University), Zhi Xue (Shanghai Jiao Tong University)

CodeClassificationRepresentation LearningTransformerAuto EncoderTabular

🎯 What it does: Developed a traffic Transformer based on MAE (YaTC) that classifies network traffic using multi-layer flow representation.

YOLOV: Making Still Image Object Detectors Great at Video Object Detection

Yuheng Shi (Tianjin University), Xiaojie Guo (TuSimple)

CodeObject DetectionConvolutional Neural NetworkImageVideo

🎯 What it does: In the video object detection task, a one-stage detector based on YOLOX selects high-confidence boxes through post-processing and aggregates the features of these boxes to improve detection accuracy.

Zero-Cost Operation Scoring in Differentiable Architecture Search

Lichuan Xiang (University of Warwick), Hongkai Wen (University of Warwick)

CodeNeural Architecture SearchImageBenchmark

🎯 What it does: This paper proposes a zero-cost perturbation-based operation scoring method called Zero-Cost-PT, aimed at improving local operation selection in differentiable neural architecture search.