{"total":132,"rows":[{"id":"2410.02073","title":"Depth Pro: Sharp Monocular Metric Depth in Less Than a Second","created":"2024-10-02","cited_by_count":404,"area":null},{"id":"2405.07992","title":"MambaOut: Do We Really Need Mamba for Vision?","created":"2024-05-13","cited_by_count":143,"area":"ssm"},{"id":"2307.09283","title":"RepViT: Revisiting Mobile CNN From ViT Perspective","created":"2023-07-18","cited_by_count":123,"area":null},{"id":"2404.03663","title":"Spike-driven Transformer V2: Meta Spiking Neural Network Architecture Inspiring the Design of Next-generation Neuromorphic Chips","created":"2024-02-15","cited_by_count":103,"area":null},{"id":"2405.14325","title":"Dinomaly: The Less Is More Philosophy in Multi-Class Unsupervised Anomaly Detection","created":"2024-05-23","cited_by_count":93,"area":null},{"id":"2303.16900","title":"InceptionNeXt: When Inception Meets ConvNeXt","created":"2023-03-29","cited_by_count":86,"area":null},{"id":"2305.17997","title":"DiffRate : Differentiable Compression Rate for Efficient Vision Transformers","created":"2023-05-29","cited_by_count":77,"area":"inference"},{"id":"2412.13303","title":"FastVLM: Efficient Vision Encoding for Vision Language Models","created":"2024-12-17","cited_by_count":77,"area":"mllm"},{"id":"2304.02419","title":"TM2D: Bimodality Driven 3D Dance Generation via Music-Text Integration","created":"2023-04-05","cited_by_count":76,"area":null},{"id":"2308.14480","title":"Priority-Centric Human Motion Generation in Discrete Latent Space","created":"2023-08-28","cited_by_count":67,"area":"diffusion"},{"id":"2411.16061","title":"Scaling Spike-driven Transformer with Efficient Spike Firing Approximation Training","created":"2024-11-25","cited_by_count":59,"area":null},{"id":"2409.10594","title":"Kolmogorov-Arnold Transformer","created":"2024-09-16","cited_by_count":56,"area":null},{"id":"2410.11842","title":"MoH: Multi-Head Attention as Mixture-of-Head Attention","created":"2024-10-15","cited_by_count":44,"area":"moe"},{"id":"2301.04644","title":"Does progress on ImageNet transfer to real-world datasets?","created":"2023-01-11","cited_by_count":35,"area":null},{"id":"2308.12216","title":"SG-Former: Self-guided Transformer with Evolving Token Reallocation","created":"2023-08-23","cited_by_count":32,"area":null},{"id":"2403.09577","title":"The NeRFect Match: Exploring NeRF Features for Visual Localization","created":"2024-03-14","cited_by_count":32,"area":null},{"id":"2504.00496","title":"Learned Image Compression with Dictionary-based Entropy Model","created":"2025-04-01","cited_by_count":30,"area":null},{"id":"2501.09436","title":"Scaling up self-supervised learning for improved surgical foundation models","created":"2025-01-16","cited_by_count":25,"area":null},{"id":"2303.03932","title":"FFT-based Dynamic Token Mixer for Vision","created":"2023-03-07","cited_by_count":22,"area":null},{"id":"2310.18605","title":"TorchDEQ: A Library for Deep Equilibrium Models","created":"2023-10-28","cited_by_count":21,"area":null},{"id":"2411.10741","title":"MetaLA: Unified Optimal Linear Approximation to Softmax Attention Map","created":"2024-11-16","cited_by_count":21,"area":null},{"id":"2502.12677","title":"Spiking Vision Transformer with Saccadic Attention","created":"2025-02-18","cited_by_count":21,"area":null},{"id":"2412.00965","title":"Token Cropr: Faster ViTs for Quite a Few Tasks","created":"2024-12-01","cited_by_count":19,"area":"inference"},{"id":"2405.08768","title":"EfficientTrain++: Generalized Curriculum Learning for Efficient Visual Backbone Training","created":"2024-05-14","cited_by_count":18,"area":null},{"id":"2404.12699","title":"SOPHON: Non-Fine-Tunable Learning to Restrain Task Transferability For Pre-trained Models","created":"2024-04-19","cited_by_count":17,"area":null},{"id":"2507.02915","title":"Audio-JEPA: Joint-Embedding Predictive Architecture for Audio Representation Learning","created":"2025-06-25","cited_by_count":17,"area":null},{"id":"2403.19963","title":"Efficient Modulation for Vision Networks","created":"2024-03-29","cited_by_count":16,"area":null},{"id":"2406.04138","title":"The 3D-PC: a benchmark for visual perspective taking in humans and machines","created":"2024-06-06","cited_by_count":16,"area":null},{"id":"2410.04960","title":"On Efficient Variants of Segment Anything Model: A Survey","created":"2024-10-07","cited_by_count":16,"area":null},{"id":"2303.17696","title":"Dual Cross-Attention for Medical Image Segmentation","created":"2023-03-30","cited_by_count":15,"area":null},{"id":"2304.05659","title":"RIFormer: Keep Your Vision Backbone Effective While Removing Token Mixer","created":"2023-04-12","cited_by_count":13,"area":null},{"id":"2501.13492","title":"Quantized Spike-driven Transformer","created":"2025-01-23","cited_by_count":13,"area":null},{"id":"2408.03703","title":"CAS-ViT: Convolutional Additive Self-attention Vision Transformers for Efficient Mobile Applications","created":"2024-08-07","cited_by_count":12,"area":null},{"id":"2503.08703","title":"SDTrack: A Baseline for Event-based Tracking via Spiking Neural Networks","created":"2025-03-09","cited_by_count":12,"area":null},{"id":"2406.14912","title":"FC3DNet: A Fully Connected Encoder-Decoder for Efficient Demoir'eing","created":"2024-06-21","cited_by_count":11,"area":null},{"id":"2405.13985","title":"LookHere: Vision Transformers with Directed Attention Generalize and Extrapolate","created":"2024-05-22","cited_by_count":10,"area":null},{"id":"2502.05091","title":"DCFormer: Efficient 3D Vision-Language Modeling with Decomposed Convolutions","created":"2025-02-07","cited_by_count":10,"area":"mllm"},{"id":"2507.12006","title":"Frequency-Dynamic Attention Modulation for Dense Prediction","created":"2025-07-16","cited_by_count":10,"area":null},{"id":"2309.15755","title":"CAIT: Triple-Win Compression towards High Accuracy, Fast Inference, and Favorable Transferability For ViTs","created":"2023-09-27","cited_by_count":9,"area":"inference"},{"id":"2310.10563","title":"RefConv: Re-parameterized Refocusing Convolution for Powerful ConvNets","created":"2023-10-16","cited_by_count":9,"area":null},{"id":"2310.15165","title":"Handling Data Heterogeneity via Architectural Design for Federated Visual Recognition","created":"2023-10-23","cited_by_count":8,"area":null},{"id":"2405.18679","title":"Vim-F: Visual State Space Model Benefiting from Learning in the Frequency Domain","created":"2024-05-29","cited_by_count":8,"area":"ssm"},{"id":"2507.16559","title":"Comparative validation of surgical phase recognition, instrument keypoint estimation, and instrument instance segmentation in endoscopy: Results of the PhaKIR 2024 challenge","created":"2025-07-22","cited_by_count":8,"area":null},{"id":"2211.05781","title":"Demystify Transformers & Convolutions in Modern Image Deep Networks","created":"2022-11-10","cited_by_count":7,"area":null},{"id":"2405.11533","title":"Hierarchical Selective Classification","created":"2024-05-19","cited_by_count":7,"area":null},{"id":"2405.16555","title":"Building Vision Models upon Heat Conduction","created":"2024-05-26","cited_by_count":7,"area":null},{"id":"2407.17904","title":"Exploring the Effect of Dataset Diversity in Self-Supervised Learning for Surgical Computer Vision","created":"2024-07-25","cited_by_count":7,"area":null},{"id":"2409.02111","title":"Toward Large-scale Spiking Neural Networks: A Comprehensive Survey and Future Directions","created":"2024-08-19","cited_by_count":7,"area":null},{"id":"2305.07848","title":"Meta-Polyp: a baseline for efficient Polyp segmentation","created":"2023-05-13","cited_by_count":6,"area":null},{"id":"2311.01323","title":"Towards Evaluating Transfer-based Attacks Systematically, Practically, and Fairly","created":"2023-11-02","cited_by_count":6,"area":null},{"id":"2404.02585","title":"Unsegment Anything by Simulating Deformation","created":"2024-04-03","cited_by_count":6,"area":null},{"id":"2408.01708","title":"AVESFormer: Efficient Transformer Design for Real-Time Audio-Visual Segmentation","created":"2024-08-03","cited_by_count":6,"area":null},{"id":"2505.04720","title":"False Promises in Medical Imaging AI? Assessing Validity of Outperformance Claims","created":"2025-05-07","cited_by_count":6,"area":null},{"id":"2505.20834","title":"Fully Spiking Neural Networks for Unified Frame-Event Object Tracking","created":"2025-05-27","cited_by_count":6,"area":null},{"id":"2406.12220","title":"Hierarchical Associative Memory, Parallelized MLP-Mixer, and Symmetry Breaking","created":"2024-06-18","cited_by_count":5,"area":null},{"id":"2410.20855","title":"ByteNet: Rethinking Multimedia File Fragment Classification through Visual Perspectives","created":"2024-10-28","cited_by_count":5,"area":null},{"id":"2508.18242","title":"GSVisLoc: Generalizable Visual Localization for Gaussian Splatting Scene Representations","created":"2025-08-25","cited_by_count":5,"area":null},{"id":"2306.00817","title":"Dilated Convolution with Learnable Spacings: beyond bilinear interpolation","created":"2023-06-01","cited_by_count":4,"area":null},{"id":"2411.16129","title":"Three Cars Approaching within 100m! Enhancing Distant Geometry by Tri-Axis Voxel Scanning for Camera-based Semantic Scene Completion","created":"2024-11-25","cited_by_count":4,"area":null},{"id":"2304.13061","title":"iMixer: hierarchical Hopfield network implies an invertible, implicit and iterative MLP-Mixer","created":"2023-04-25","cited_by_count":3,"area":null},{"id":"2306.12939","title":"Feature Mixing for Writer Retrieval and Identification on Papyri Fragments","created":"2023-06-22","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":"2503.12453","title":"Shape Bias and Robustness Evaluation via Cue Decomposition for Image Classification and Segmentation","created":"2025-03-16","cited_by_count":3,"area":null},{"id":"2503.20748","title":"UniSTD: Towards Unified Spatio-Temporal Learning across Diverse Disciplines","created":"2025-03-26","cited_by_count":3,"area":null},{"id":"2505.18608","title":"Spiking Neural Networks Need High Frequency Information","created":"2025-05-24","cited_by_count":3,"area":null},{"id":"2505.22195","title":"S2AFormer: Strip Self-Attention for Efficient Vision Transformer","created":"2025-05-28","cited_by_count":3,"area":null},{"id":"2506.10361","title":"FaceLiVT: Face Recognition using Linear Vision Transformer with Structural Reparameterization For Mobile Device","created":"2025-06-12","cited_by_count":3,"area":null},{"id":"2507.11893","title":"Spatial Frequency Modulation for Semantic Segmentation","created":"2025-07-16","cited_by_count":3,"area":null},{"id":"2304.02860","title":"Towards an Effective and Efficient Transformer for Rain-by-snow Weather Removal","created":"2023-04-06","cited_by_count":2,"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":"2402.19305","title":"HyenaPixel: Global Image Context with Convolutions","created":"2024-02-29","cited_by_count":2,"area":null},{"id":"2409.09244","title":"Investigation of Hierarchical Spectral Vision Transformer Architecture for Classification of Hyperspectral Imagery","created":"2024-09-14","cited_by_count":2,"area":null},{"id":"2504.02737","title":"RBT4DNN: Requirements-based Testing of Neural Networks","created":"2025-04-03","cited_by_count":2,"area":null},{"id":"2506.02358","title":"RoadFormer : Local-Global Feature Fusion for Road Surface Classification in Autonomous Driving","created":"2025-06-03","cited_by_count":2,"area":null},{"id":"2604.05959","title":"Multi-Modal Landslide Detection from Sentinel-1 SAR and Sentinel-2 Optical Imagery Using Multi-Encoder Vision Transformers and Ensemble Learning","created":"2026-04-07","cited_by_count":2,"area":null},{"id":"2309.13972","title":"Audio classification with Dilated Convolution with Learnable Spacings","created":"2023-09-25","cited_by_count":1,"area":null},{"id":"2403.04353","title":"Spatiotemporal Pooling on Appropriate Topological Maps Represented as Two-Dimensional Images for EEG Classification","created":"2024-03-07","cited_by_count":1,"area":null},{"id":"2408.05780","title":"U-DECN: End-to-End Underwater Object Detection ConvNet with Improved DeNoising Training","created":"2024-08-11","cited_by_count":1,"area":null},{"id":"2408.05901","title":"Efficient Visual Representation Learning with Heat Conduction Equation","created":"2024-08-12","cited_by_count":1,"area":null},{"id":"2409.04082","title":"SDformerFlow: Spatiotemporal swin spikeformer for event-based optical flow estimation","created":"2024-09-06","cited_by_count":1,"area":null},{"id":"2409.05817","title":"VFA: Vision Frequency Analysis of Foundation Models and Human","created":"2024-09-09","cited_by_count":1,"area":null},{"id":"2409.14976","title":"A new baseline for edge detection: Make Encoder-Decoder great again","created":"2024-09-23","cited_by_count":1,"area":null},{"id":"2411.03098","title":"Local Lesion Generation is Effective for Capsule Endoscopy Image Data Augmentation in a Limited Data Setting","created":"2024-11-05","cited_by_count":1,"area":null},{"id":"2412.17477","title":"Predicting Satisfied User and Machine Ratio for Compressed Images: A Unified Approach","created":"2024-12-23","cited_by_count":1,"area":null},{"id":"2502.17196","title":"Disentangling Visual Transformers: Patch-level Interpretability for Image Classification","created":"2025-02-24","cited_by_count":1,"area":null},{"id":"2503.24166","title":"Foundation Models For Seismic Data Processing: An Extensive Review","created":"2025-03-31","cited_by_count":1,"area":null},{"id":"2504.03800","title":"Decision SpikeFormer: Spike-Driven Transformer for Decision Making","created":"2025-04-04","cited_by_count":1,"area":"offlinerl"},{"id":"2504.10834","title":"LightFormer: A lightweight and efficient decoder for remote sensing image segmentation","created":"2025-04-15","cited_by_count":1,"area":null},{"id":"2504.13579","title":"HDBFormer: Efficient RGB-D Semantic Segmentation with A Heterogeneous Dual-Branch Framework","created":"2025-04-18","cited_by_count":1,"area":null},{"id":"2507.16624","title":"A2Mamba: Attention-augmented State Space Models for Visual Recognition","created":"2025-07-22","cited_by_count":1,"area":"ssm"},{"id":"2508.16730","title":"Analysis of Transferability Estimation Metrics for Surgical Phase Recognition","created":"2025-08-22","cited_by_count":1,"area":null},{"id":"2508.16937","title":"NAT: Learning to Attack Neurons for Enhanced Adversarial Transferability","created":"2025-08-23","cited_by_count":1,"area":null},{"id":"2510.25166","title":"A Study on Inference Latency for Vision Transformers on Mobile Devices","created":"2025-10-29","cited_by_count":1,"area":null},{"id":"2603.15184","title":"CATFormer: When Continual Learning Meets Spiking Transformers With Dynamic Thresholds","created":"2026-03-16","cited_by_count":1,"area":null},{"id":"2606.02092","title":"LALE: Lightweight-Transformer Architecture for Land-Cover Estimation","created":"2026-06-01","cited_by_count":1,"area":null},{"id":"2302.02314","title":"CECT: Controllable Ensemble CNN and Transformer for COVID-19 Image Classification","created":"2023-02-05","cited_by_count":0,"area":null},{"id":"2306.01423","title":"Break a Lag: Triple Exponential Moving Average for Enhanced Optimization","created":"2023-06-02","cited_by_count":0,"area":null},{"id":"2402.18287","title":"Windowed-FourierMixer: Enhancing Clutter-Free Room Modeling with Fourier Transform","created":"2024-02-28","cited_by_count":0,"area":null},{"id":"2403.10124","title":"Depth-induced Saliency Comparison Network for Diagnosis of Alzheimer's Disease via Jointly Analysis of Visual Stimuli and Eye Movements","created":"2024-03-15","cited_by_count":0,"area":null},{"id":"2403.15004","title":"ParFormer: A Vision Transformer with Parallel Mixer and Sparse Channel Attention Patch Embedding","created":"2024-03-22","cited_by_count":0,"area":null}],"next_cursor":"100"}