{"total":53,"rows":[{"id":"2410.04803","title":"Timer-XL: Long-Context Transformers for Unified Time Series Forecasting","created":"2024-10-07","cited_by_count":87,"area":null},{"id":"2502.20087","title":"OverLoCK: An Overview-first-Look-Closely-next ConvNet with Context-Mixing Dynamic Kernels","created":"2025-02-27","cited_by_count":25,"area":null},{"id":"2503.18783","title":"Frequency Dynamic Convolution for Dense Image Prediction","created":"2025-03-24","cited_by_count":19,"area":null},{"id":"2503.23135","title":"LSNet: See Large, Focus Small","created":"2025-03-29","cited_by_count":15,"area":null},{"id":"2501.03775","title":"Strip R-CNN: Large Strip Convolution for Remote Sensing Object Detection","created":"2025-01-07","cited_by_count":14,"area":null},{"id":"2406.02395","title":"GrootVL: Tree Topology is All You Need in State Space Model","created":"2024-06-04","cited_by_count":13,"area":null},{"id":"2407.21631","title":"RoadFormer+: Delivering RGB-X Scene Parsing through Scale-Aware Information Decoupling and Advanced Heterogeneous Feature Fusion","created":"2024-07-31","cited_by_count":10,"area":null},{"id":"2502.12627","title":"DAMamba: Vision State Space Model with Dynamic Adaptive Scan","created":"2025-02-18","cited_by_count":9,"area":null},{"id":"2407.08972","title":"Revealing the Dark Secrets of Extremely Large Kernel ConvNets on Robustness","created":"2024-07-12","cited_by_count":8,"area":null},{"id":"2410.08049","title":"Scaling Up Your Kernels: Large Kernel Design in ConvNets towards Universal Representations","created":"2024-10-10","cited_by_count":8,"area":null},{"id":"2401.14405","title":"Multimodal Pathway: Improve Transformers with Irrelevant Data from Other Modalities","created":"2024-01-25","cited_by_count":7,"area":null},{"id":"2404.11848","title":"Partial Large Kernel CNNs for Efficient Super-Resolution","created":"2024-04-18","cited_by_count":7,"area":null},{"id":"2506.18034","title":"Pre-Trained LLM is a Semantic-Aware and Generalizable Segmentation Booster","created":"2025-06-22","cited_by_count":7,"area":null},{"id":"2405.12721","title":"StarLKNet: Star Mixup with Large Kernel Networks for Palm Vein Identification","created":"2024-05-21","cited_by_count":5,"area":null},{"id":"2406.09412","title":"Explore the Limits of Omni-modal Pretraining at Scale","created":"2024-06-13","cited_by_count":5,"area":null},{"id":"2401.12736","title":"$ShiftwiseConv:$ Small Convolutional Kernel with Large Kernel Effect","created":"2024-01-23","cited_by_count":4,"area":null},{"id":"2406.16004","title":"RepNeXt: A Fast Multi-Scale CNN using Structural Reparameterization","created":"2024-06-23","cited_by_count":4,"area":null},{"id":"2410.08582","title":"DeBiFormer: Vision Transformer with Deformable Agent Bi-level Routing Attention","created":"2024-10-11","cited_by_count":4,"area":null},{"id":"2402.03040","title":"InteractiveVideo: User-Centric Controllable Video Generation with Synergistic Multimodal Instructions","created":"2024-02-05","cited_by_count":3,"area":null},{"id":"2405.09933","title":"MiniMaxAD: A Lightweight Autoencoder for Feature-Rich Anomaly Detection","created":"2024-05-16","cited_by_count":3,"area":null},{"id":"2407.18054","title":"LKCell: Efficient Cell Nuclei Instance Segmentation with Large Convolution Kernels","created":"2024-07-25","cited_by_count":3,"area":null},{"id":"2410.06373","title":"Unveiling the Backbone-Optimizer Coupling Bias in Visual Representation Learning","created":"2024-10-08","cited_by_count":3,"area":null},{"id":"2508.09000","title":"UniConvNet: Expanding Effective Receptive Field while Maintaining Asymptotically Gaussian Distribution for ConvNets of Any Scale","created":"2025-08-12","cited_by_count":3,"area":null},{"id":"2508.16881","title":"AWM-Fuse: Multi-Modality Image Fusion for Adverse Weather via Global and Local Text Perception","created":"2025-08-23","cited_by_count":3,"area":null},{"id":"2312.13735","title":"DECO: Unleashing the Potential of ConvNets for Query-based Detection and Segmentation","created":"2023-12-21","cited_by_count":2,"area":null},{"id":"2408.09453","title":"Reparameterized Multi-Resolution Convolutions for Long Sequence Modelling","created":"2024-08-18","cited_by_count":2,"area":null},{"id":"2410.15279","title":"ContextDet: Temporal Action Detection with Adaptive Context Aggregation","created":"2024-10-20","cited_by_count":2,"area":null},{"id":"2506.13552","title":"A Comprehensive Survey on Video Scene Parsing:Advances, Challenges, and Prospects","created":"2025-06-16","cited_by_count":2,"area":null},{"id":"2406.02021","title":"FFNet: MetaMixer-based Efficient Convolutional Mixer Design","created":"2024-06-04","cited_by_count":1,"area":null},{"id":"2407.13155","title":"Real-Time 3D Occupancy Prediction via Geometric-Semantic Disentanglement","created":"2024-07-18","cited_by_count":1,"area":null},{"id":"2409.07752","title":"GatedUniPose: A Novel Approach for Pose Estimation Combining UniRepLKNet and Gated Convolution","created":"2024-09-12","cited_by_count":1,"area":null},{"id":"2601.03163","title":"LSP-DETR: Efficient and Scalable Nuclei Segmentation in Whole-Slide Images","created":"2026-01-06","cited_by_count":1,"area":null},{"id":"2605.13049","title":"Uncertainty-aware Spatial-Frequency Registration and Fusion for Infrared and Visible Images","created":"2026-05-13","cited_by_count":1,"area":null},{"id":"2605.17470","title":"EchoSR: Efficient Context Harnessing for Lightweight Image Super-Resolution","created":"2026-05-17","cited_by_count":1,"area":null},{"id":"2408.09230","title":"Siamese Multiple Attention Temporal Convolution Networks for Human Mobility Signature Identification","created":"2024-08-17","cited_by_count":0,"area":null},{"id":"2411.09023","title":"CoMiX: Cross-Modal Fusion with Deformable Convolutions for HSI-X Semantic Segmentation","created":"2024-11-13","cited_by_count":0,"area":null},{"id":"2412.05842","title":"DREAM: Domain-agnostic Reverse Engineering Attributes of Black-box Model","created":"2024-12-08","cited_by_count":0,"area":null},{"id":"2412.17401","title":"Learning Dynamic Local Context Representations for Infrared Small Target Detection","created":"2024-12-23","cited_by_count":0,"area":null},{"id":"2412.19628","title":"RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations","created":"2024-12-27","cited_by_count":0,"area":null},{"id":"2503.12093","title":"SFMNet: Sparse Focal Modulation for 3D Object Detection","created":"2025-03-15","cited_by_count":0,"area":null},{"id":"2503.22841","title":"GmNet: Revisiting Gating Mechanisms From A Frequency View","created":"2025-03-28","cited_by_count":0,"area":null},{"id":"2504.14481","title":"LSP-ST: Ladder Shape-Biased Side-Tuning for Robust Infrared Small Target Detection","created":"2025-04-20","cited_by_count":0,"area":null},{"id":"2506.14170","title":"Progressive Multimodal Interaction Network for Reliable Quantification of Fish Feeding Intensity in Aquaculture","created":"2025-06-17","cited_by_count":0,"area":null},{"id":"2509.15436","title":"Region-Aware Deformable Convolutions","created":"2025-09-18","cited_by_count":0,"area":null},{"id":"2512.10051","title":"DB2-TransF: All You Need Is Learnable Daubechies Wavelets for Time Series Forecasting","created":"2025-12-10","cited_by_count":0,"area":null},{"id":"2602.20537","title":"PFGNet: A Fully Convolutional Frequency-Guided Peripheral Gating Network for Efficient Spatiotemporal Predictive Learning","created":"2026-02-24","cited_by_count":0,"area":null},{"id":"2603.19899","title":"Deep Time-Series Forecasting in 10 Years: A Survey","created":"2026-03-20","cited_by_count":0,"area":null},{"id":"2604.17439","title":"Attention Is not Everything: Efficient Alternatives for Vision","created":"2026-04-19","cited_by_count":0,"area":null},{"id":"2605.18298","title":"DARE-EEG: A Foundation Model for Mining Dual-Aligned Representation of EEG","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2606.21956","title":"Denoising-Enhanced Coarse-to-Fine Infrared Small Target Detection with Attention Prior-Guided Knowledge Distillation","created":"2026-06-20","cited_by_count":0,"area":null},{"id":"2607.22704","title":"Visible-Light Imaging Diagnosis of Neutral Particle Emission Tomography in the Tokamak Divertor: An Efficient Transformer-based Surrogate Model","created":"2026-07-19","cited_by_count":0,"area":null},{"id":"2608.26859","title":"A Geometry-Driven, Framework-Agnostic Optimization for Object Pose Estimation","created":"2026-08-27","cited_by_count":0,"area":null},{"id":"2609.33325","title":"VisionHOPE: Visual Backbones as Self-Modifying Learning Systems","created":"2026-09-27","cited_by_count":0,"area":null}],"next_cursor":null}