{"list":"other","total":58,"rows":[{"id":"2102.04306","title":"TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation","created":"2021-02-08","cited_by_count":1558},{"id":"2112.10003","title":"Image Segmentation Using Text and Image Prompts","created":"2021-12-18","cited_by_count":512},{"id":"2403.06135","title":"MACE: Mass Concept Erasure in Diffusion Models","created":"2024-03-10","cited_by_count":307},{"id":"2108.04024","title":"Image Retrieval on Real-life Images with Pre-trained Vision-and-Language Models","created":"2021-08-09","cited_by_count":251},{"id":"2403.20150","title":"TFB: Towards Comprehensive and Fair Benchmarking of Time Series Forecasting Methods","created":"2024-03-29","cited_by_count":249},{"id":"1906.00817","title":"Zero-Shot Semantic Segmentation","created":"2019-06-03","cited_by_count":245},{"id":"1812.07119","title":"Composing Text and Image for Image Retrieval - An Empirical Odyssey","created":"2018-12-18","cited_by_count":236},{"id":"2307.12493","title":"TF-ICON: Diffusion-Based Training-Free Cross-Domain Image Composition","created":"2023-07-24","cited_by_count":182},{"id":"2505.17685","title":"FutureSightDrive: Thinking Visually with Spatio-Temporal CoT for Autonomous Driving","created":"2025-05-23","cited_by_count":166},{"id":"2410.18775","title":"Robust Watermarking Using Generative Priors Against Image Editing: From Benchmarking to Advances","created":"2024-10-24","cited_by_count":110},{"id":"2412.20413","title":"EraseAnything: Enabling Concept Erasure in Rectified Flow Transformers","created":"2024-12-29","cited_by_count":95},{"id":"2410.12261","title":"CATCH: Channel-Aware multivariate Time Series Anomaly Detection via Frequency Patching","created":"2024-10-16","cited_by_count":94},{"id":"1805.00145","title":"Dialog-based Interactive Image Retrieval","created":"2018-05-01","cited_by_count":84},{"id":"2203.08101","title":"ARTEMIS: Attention-based Retrieval with Text-Explicit Matching and Implicit Similarity","created":"2022-03-15","cited_by_count":83},{"id":"2504.12782","title":"Set You Straight: Auto-Steering Denoising Trajectories to Sidestep Unwanted Concepts","created":"2025-04-17","cited_by_count":62},{"id":"2506.18046","title":"TAB: Unified Benchmarking of Time Series Anomaly Detection Methods","created":"2025-06-22","cited_by_count":60},{"id":"2310.05473","title":"Sentence-level Prompts Benefit Composed Image Retrieval","created":"2023-10-09","cited_by_count":59},{"id":"2111.02036","title":"GRCN: Graph-Refined Convolutional Network for Multimedia Recommendation with Implicit Feedback","created":"2021-11-03","cited_by_count":58},{"id":"2410.11802","title":"TSFM-Bench: A Comprehensive and Unified Benchmark of Foundation Models for Time Series Forecasting","created":"2024-10-15","cited_by_count":58},{"id":"2505.11250","title":"Rethinking Irregular Time Series Forecasting: A Simple yet Effective Baseline","created":"2025-05-16","cited_by_count":55},{"id":"2308.14746","title":"CoVR-2: Automatic Data Construction for Composed Video Retrieval","created":"2023-08-28","cited_by_count":52},{"id":"2505.13408","title":"CoT-Kinetics: A Theoretical Modeling Assessing LRM Reasoning Process","created":"2025-05-19","cited_by_count":51},{"id":"2211.07394","title":"Composed Image Retrieval with Text Feedback via Multi-grained Uncertainty Regularization","created":"2022-11-14","cited_by_count":45},{"id":"2503.21309","title":"FineCIR: Explicit Parsing of Fine-Grained Modification Semantics for Composed Image Retrieval","created":"2025-03-27","cited_by_count":42},{"id":"2102.10044","title":"Interest-aware Message-Passing GCN for Recommendation","created":"2021-02-19","cited_by_count":39},{"id":"2303.02483","title":"FAME-ViL: Multi-Tasking Vision-Language Model for Heterogeneous Fashion Tasks","created":"2023-03-04","cited_by_count":38},{"id":"2309.01366","title":"Target-Guided Composed Image Retrieval","created":"2023-09-04","cited_by_count":36},{"id":"2305.16304","title":"Candidate Set Re-ranking for Composed Image Retrieval with Dual Multi-modal Encoder","created":"2023-05-25","cited_by_count":35},{"id":"2403.15992","title":"BIMCV-R: A Landmark Dataset for 3D CT Text-Image Retrieval","created":"2024-03-24","cited_by_count":30},{"id":"2412.17603","title":"EasyTime: Time Series Forecasting Made Easy","created":"2024-12-23","cited_by_count":30},{"id":"2204.11212","title":"Progressive Learning for Image Retrieval with Hybrid-Modality Queries","created":"2022-04-24","cited_by_count":26},{"id":"2404.15875","title":"Simple but Effective Raw-Data Level Multimodal Fusion for Composed Image Retrieval","created":"2024-04-24","cited_by_count":24},{"id":"2305.09979","title":"Self-Training Boosted Multi-Factor Matching Network for Composed Image Retrieval","created":"2023-05-17","cited_by_count":22},{"id":"2405.19149","title":"CaLa: Complementary Association Learning for Augmenting Composed Image Retrieval","created":"2024-05-29","cited_by_count":21},{"id":"2505.22521","title":"Evaluating Supervised Learning Models for Fraud Detection: A Comparative Study of Classical and Deep Architectures on Imbalanced Transaction Data","created":"2025-05-28","cited_by_count":20},{"id":"2401.06385","title":"SD-MVS: Segmentation-Driven Deformation Multi-View Stereo with Spherical Refinement and EM optimization","created":"2024-01-12","cited_by_count":19},{"id":"2407.11335","title":"LaMI-DETR: Open-Vocabulary Detection with Language Model Instruction","created":"2024-07-16","cited_by_count":19},{"id":"2410.15997","title":"MultiRC: Joint Learning for Time Series Anomaly Prediction and Detection with Multi-scale Reconstructive Contrast","created":"2024-10-21","cited_by_count":19},{"id":"2503.19296","title":"Fine-grained Textual Inversion Network for Zero-Shot Composed Image Retrieval","created":"2025-03-25","cited_by_count":18},{"id":"2506.02544","title":"CoRe-MMRAG: Cross-Source Knowledge Reconciliation for Multimodal RAG","created":"2025-06-03","cited_by_count":18},{"id":"2305.14579","title":"Real-Time Idling Vehicles Detection using Combined Audio-Visual Deep Learning","created":"2023-05-23","cited_by_count":17},{"id":"2410.04810","title":"FedBiP: Heterogeneous One-Shot Federated Learning with Personalized Latent Diffusion Models","created":"2024-10-07","cited_by_count":16},{"id":"2506.00107","title":"Gated Multimodal Graph Learning for Personalized Recommendation","created":"2025-05-30","cited_by_count":15},{"id":"2304.05051","title":"FashionSAP: Symbols and Attributes Prompt for Fine-grained Fashion Vision-Language Pre-training","created":"2023-04-11","cited_by_count":14},{"id":"2410.21170","title":"Joint Audio-Visual Idling Vehicle Detection with Streamlined Input Dependencies","created":"2024-10-28","cited_by_count":14},{"id":"2403.10720","title":"Development and Application of a Monte Carlo Tree Search Algorithm for Simulating Da Vinci Code Game Strategies","created":"2024-03-15","cited_by_count":12},{"id":"2502.09971","title":"Conditional Latent Coding with Learnable Synthesized Reference for Deep Image Compression","created":"2025-02-14","cited_by_count":11},{"id":"2407.12887","title":"Self-Adaptive Robust Motion Planning for High DoF Robot Manipulator using Deep MPC","created":"2024-07-17","cited_by_count":8},{"id":"2502.05147","title":"LP-DETR: Layer-wise Progressive Relations for Object Detection","created":"2025-02-07","cited_by_count":8},{"id":"2405.17485","title":"Comet: A Communication-efficient and Performant Approximation for Private Transformer Inference","created":"2024-05-24","cited_by_count":7},{"id":"2406.06558","title":"Enhancing Text Authenticity: A Novel Hybrid Approach for AI-Generated Text Detection","created":"2024-06-01","cited_by_count":7},{"id":"2411.02608","title":"SSFold: Learning to Fold Arbitrary Crumpled Cloth Using Graph Dynamics from Human Demonstration","created":"2024-10-24","cited_by_count":7},{"id":"2505.11335","title":"Understanding and Mitigating Under-Confidence in GNNs from the Final Layer","created":"2025-05-16","cited_by_count":6},{"id":"2408.04914","title":"GuidedNet: Semi-Supervised Multi-Organ Segmentation via Labeled Data Guide Unlabeled Data","created":"2024-08-09","cited_by_count":5},{"id":"2506.22769","title":"Learning Efficient Robotic Garment Manipulation with Standardization","created":"2025-06-28","cited_by_count":5},{"id":"2409.02444","title":"USV-AUV Collaboration Framework for Underwater Tasks under Extreme Sea Conditions","created":"2024-09-04","cited_by_count":4},{"id":"2503.00527","title":"Never too Prim to Swim: An LLM-Enhanced RL-based Adaptive S-Surface Controller for AUVs under Extreme Sea Conditions","created":"2025-03-01","cited_by_count":4},{"id":"2412.03959","title":"Is FISHER All You Need in The Multi-AUV Underwater Target Tracking Task?","created":"2024-12-05","cited_by_count":3}],"next_cursor":null}