{"total":148,"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":"2306.14289","title":"Faster Segment Anything: Towards Lightweight SAM for Mobile Applications","created":"2023-06-25","cited_by_count":352,"area":null},{"id":"2406.09394","title":"WonderWorld: Interactive 3D Scene Generation from a Single Image","created":"2024-06-13","cited_by_count":202,"area":null},{"id":"2312.00863","title":"EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything","created":"2023-12-01","cited_by_count":188,"area":null},{"id":"2406.02918","title":"U-KAN Makes Strong Backbone for Medical Image Segmentation and Generation","created":"2024-06-05","cited_by_count":179,"area":null},{"id":"2307.09283","title":"RepViT: Revisiting Mobile CNN From ViT Perspective","created":"2023-07-18","cited_by_count":123,"area":null},{"id":"2405.10300","title":"Grounding DINO 1.5: Advance the \"Edge\" of Open-Set Object Detection","created":"2024-05-16","cited_by_count":122,"area":null},{"id":"2404.10518","title":"MobileNetV4 -- Universal Models for the Mobile Ecosystem","created":"2024-04-16","cited_by_count":99,"area":null},{"id":"2311.17049","title":"MobileCLIP: Fast Image-Text Models through Multi-Modal Reinforced Training","created":"2023-11-28","cited_by_count":96,"area":null},{"id":"2412.07679","title":"RADIOv2.5: Improved Baselines for Agglomerative Vision Foundation Models","created":"2024-12-10","cited_by_count":89,"area":null},{"id":"2401.16456","title":"SHViT: Single-Head Vision Transformer with Memory Efficient Macro Design","created":"2024-01-29","cited_by_count":56,"area":null},{"id":"2402.05964","title":"A Survey on Transformer Compression","created":"2024-02-05","cited_by_count":46,"area":null},{"id":"2409.01686","title":"Frequency-Spatial Entanglement Learning for Camouflaged Object Detection","created":"2024-09-03","cited_by_count":46,"area":null},{"id":"2404.10156","title":"SegFormer3D: an Efficient Transformer for 3D Medical Image Segmentation","created":"2024-04-15","cited_by_count":31,"area":null},{"id":"2405.10313","title":"How Far Are We From AGI: Are LLMs All We Need?","created":"2024-05-16","cited_by_count":31,"area":null},{"id":"2406.19833","title":"LightStereo: Channel Boost Is All You Need for Efficient 2D Cost Aggregation","created":"2024-06-28","cited_by_count":28,"area":null},{"id":"2308.13894","title":"FwdLLM: Efficient FedLLM using Forward Gradient","created":"2023-08-26","cited_by_count":26,"area":null},{"id":"2403.05949","title":"General surgery vision transformer: A video pre-trained foundation model for general surgery","created":"2024-03-09","cited_by_count":25,"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":"2503.23844","title":"FlexiMo: A Flexible Remote Sensing Foundation Model","created":"2025-03-31","cited_by_count":24,"area":null},{"id":"2406.16073","title":"LGS: A Light-weight 4D Gaussian Splatting for Efficient Surgical Scene Reconstruction","created":"2024-06-23","cited_by_count":21,"area":null},{"id":"2411.18933","title":"Efficient Track Anything","created":"2024-11-28","cited_by_count":21,"area":null},{"id":"2312.17276","title":"PanGu-$\\pi$: Enhancing Language Model Architectures via Nonlinearity Compensation","created":"2023-12-27","cited_by_count":17,"area":null},{"id":"2404.05657","title":"MLP Can Be A Good Transformer Learner","created":"2024-04-08","cited_by_count":17,"area":null},{"id":"2512.01540","title":"FlashVGGT: Efficient and Scalable Visual Geometry Transformers with Compressed Descriptor Attention","created":"2025-12-01","cited_by_count":17,"area":null},{"id":"2503.23135","title":"LSNet: See Large, Focus Small","created":"2025-03-29","cited_by_count":15,"area":null},{"id":"2401.12422","title":"InverseMatrixVT3D: An Efficient Projection Matrix-Based Approach for 3D Occupancy Prediction","created":"2024-01-23","cited_by_count":14,"area":null},{"id":"2403.01431","title":"Image2Sentence based Asymmetrical Zero-shot Composed Image Retrieval","created":"2024-03-03","cited_by_count":14,"area":null},{"id":"2407.19809","title":"Twins-PainViT: Towards a Modality-Agnostic Vision Transformer Framework for Multimodal Automatic Pain Assessment using Facial Videos and fNIRS","created":"2024-07-29","cited_by_count":14,"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":"2502.21193","title":"Towards High-performance Spiking Transformers from ANN to SNN Conversion","created":"2025-02-28","cited_by_count":11,"area":null},{"id":"2407.05010","title":"PRANCE: Joint Token-Optimization and Structural Channel-Pruning for Adaptive ViT Inference","created":"2024-07-06","cited_by_count":10,"area":null},{"id":"2506.02692","title":"Large-scale Self-supervised Video Foundation Model for Intelligent Surgery","created":"2025-06-03","cited_by_count":10,"area":null},{"id":"2311.03747","title":"SBCFormer: Lightweight Network Capable of Full-size ImageNet Classification at 1 FPS on Single Board Computers","created":"2023-11-07","cited_by_count":9,"area":null},{"id":"2506.03714","title":"FSHNet: Fully Sparse Hybrid Network for 3D Object Detection","created":"2025-06-04","cited_by_count":9,"area":null},{"id":"2507.18264","title":"Zero-shot OCR Accuracy of Low-Resourced Languages: A Comparative Analysis on Sinhala and Tamil","created":"2025-07-24","cited_by_count":9,"area":null},{"id":"2409.03901","title":"Onboard Satellite Image Classification for Earth Observation: A Comparative Study of ViT Models","created":"2024-09-05","cited_by_count":8,"area":null},{"id":"2502.05800","title":"MicroViT: A Vision Transformer with Low Complexity Self Attention for Edge Device","created":"2025-02-09","cited_by_count":8,"area":null},{"id":"2504.06553","title":"ASHiTA: Automatic Scene-grounded HIerarchical Task Analysis","created":"2025-04-09","cited_by_count":8,"area":null},{"id":"2403.08059","title":"FluoroSAM: A Language-promptable Foundation Model for Flexible X-ray Image Segmentation","created":"2024-03-12","cited_by_count":7,"area":null},{"id":"2407.05540","title":"GTP-4o: Modality-prompted Heterogeneous Graph Learning for Omni-modal Biomedical Representation","created":"2024-07-08","cited_by_count":7,"area":null},{"id":"2512.15729","title":"TinyMyo: a Tiny Foundation Model for Flexible EMG Signal Processing at the Edge","created":"2025-12-05","cited_by_count":7,"area":null},{"id":"2404.05196","title":"HSViT: Horizontally Scalable Vision Transformer","created":"2024-04-08","cited_by_count":6,"area":null},{"id":"2404.10880","title":"HumMUSS: Human Motion Understanding using State Space Models","created":"2024-04-16","cited_by_count":6,"area":null},{"id":"2409.03460","title":"LowFormer: Hardware Efficient Design for Convolutional Transformer Backbones","created":"2024-09-05","cited_by_count":6,"area":null},{"id":"2501.10640","title":"ClusterViG: Efficient Globally Aware Vision GNNs via Image Partitioning","created":"2025-01-18","cited_by_count":6,"area":null},{"id":"2603.25336","title":"HeSS: Head Sensitivity Score for Sparsity Redistribution in VGGT","created":"2026-03-26","cited_by_count":6,"area":null},{"id":"2407.08965","title":"Lite-SAM Is Actually What You Need for Segment Everything","created":"2024-07-12","cited_by_count":5,"area":null},{"id":"2410.05500","title":"Residual Kolmogorov-Arnold Network for Enhanced Deep Learning","created":"2024-10-07","cited_by_count":5,"area":null},{"id":"2410.08860","title":"Audio Description Generation in the Era of LLMs and VLMs: A Review of Transferable Generative AI Technologies","created":"2024-10-11","cited_by_count":5,"area":null},{"id":"2410.09380","title":"Prompting Video-Language Foundation Models with Domain-specific Fine-grained Heuristics for Video Question Answering","created":"2024-10-12","cited_by_count":5,"area":null},{"id":"2506.11131","title":"Segment This Thing: Foveated Tokenization for Efficient Point-Prompted Segmentation","created":"2025-06-10","cited_by_count":5,"area":null},{"id":"2311.01526","title":"ATGNN: Audio Tagging Graph Neural Network","created":"2023-11-02","cited_by_count":4,"area":null},{"id":"2403.19882","title":"Enhancing Efficiency in Vision Transformer Networks: Design Techniques and Insights","created":"2024-03-28","cited_by_count":4,"area":null},{"id":"2404.12210","title":"An Experimental Study on Exploring Strong Lightweight Vision Transformers via Masked Image Modeling Pre-Training","created":"2024-04-18","cited_by_count":4,"area":null},{"id":"2402.11303","title":"FViT: A Focal Vision Transformer with Gabor Filter","created":"2024-02-17","cited_by_count":3,"area":null},{"id":"2402.13537","title":"EffLoc: Lightweight Vision Transformer for Efficient 6-DOF Camera Relocalization","created":"2024-02-21","cited_by_count":3,"area":null},{"id":"2403.11026","title":"EfficientMorph: Parameter-Efficient Transformer-Based Architecture for 3D Image Registration","created":"2024-03-16","cited_by_count":3,"area":null},{"id":"2408.05699","title":"MacFormer: Semantic Segmentation with Fine Object Boundaries","created":"2024-08-11","cited_by_count":3,"area":null},{"id":"2412.14680","title":"A Light-Weight Framework for Open-Set Object Detection with Decoupled Feature Alignment in Joint Space","created":"2024-12-19","cited_by_count":3,"area":null},{"id":"2501.03605","title":"ConcealGS: Concealing Invisible Copyright Information in 3D Gaussian Splatting","created":"2025-01-07","cited_by_count":3,"area":null},{"id":"2503.06473","title":"Enhancing Layer Attention Efficiency through Pruning Redundant Retrievals","created":"2025-03-09","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":"2508.07312","title":"MobileViCLIP: An Efficient Video-Text Model for Mobile Devices","created":"2025-08-10","cited_by_count":3,"area":null},{"id":"2509.21265","title":"MedVSR: Medical Video Super-Resolution with Cross State-Space Propagation","created":"2025-09-25","cited_by_count":3,"area":null},{"id":"2604.09127","title":"FaceLiVTv2: An Improved Hybrid Architecture for Efficient Mobile Face Recognition","created":"2026-04-10","cited_by_count":3,"area":null},{"id":"2403.04200","title":"ACC-ViT : Atrous Convolution's Comeback in Vision Transformers","created":"2024-03-07","cited_by_count":2,"area":null},{"id":"2406.10935","title":"Pick-or-Mix: Dynamic Channel Sampling for ConvNets","created":"2024-06-16","cited_by_count":2,"area":null},{"id":"2410.10267","title":"big.LITTLE Vision Transformer for Efficient Visual Recognition","created":"2024-10-14","cited_by_count":2,"area":null},{"id":"2410.10914","title":"Towards Better Multi-head Attention via Channel-wise Sample Permutation","created":"2024-10-14","cited_by_count":2,"area":null},{"id":"2503.09903","title":"A Semantic-Loss Function Modeling Framework With Task-Oriented Machine Learning Perspectives","created":"2025-03-12","cited_by_count":2,"area":null},{"id":"2504.02277","title":"Beyond Conventional Transformers: The Medical X-ray Attention (MXA) Block for Improved Multi-Label Diagnosis Using Knowledge Distillation","created":"2025-04-03","cited_by_count":2,"area":null},{"id":"2505.03113","title":"Image Recognition with Online Lightweight Vision Transformer: A Survey","created":"2025-05-06","cited_by_count":2,"area":null},{"id":"2505.23763","title":"Sketch Down the FLOPs: Towards Efficient Networks for Human Sketch","created":"2025-05-29","cited_by_count":2,"area":null},{"id":"2511.10004","title":"LampQ: Towards Accurate Layer-wise Mixed Precision Quantization for Vision Transformers","created":"2025-11-13","cited_by_count":2,"area":null},{"id":"2601.22563","title":"EUGens: Efficient, Unified, and General Dense Layers","created":"2026-01-30","cited_by_count":2,"area":null},{"id":"2605.11578","title":"The Midas Touch for Metric Depth","created":"2026-05-12","cited_by_count":2,"area":null},{"id":"2609.24737","title":"Ananke: Contractive Torus Attractor Networks","created":"2026-09-21","cited_by_count":2,"area":null},{"id":"2308.11421","title":"TurboViT: Generating Fast Vision Transformers via Generative Architecture Search","created":"2023-08-22","cited_by_count":1,"area":null},{"id":"2310.06629","title":"EViT: An Eagle Vision Transformer with Bi-Fovea Self-Attention","created":"2023-10-10","cited_by_count":1,"area":null},{"id":"2312.10099","title":"ADA-YOLO: Dynamic Fusion of YOLOv8 and Adaptive Heads for Precise Image Detection and Diagnosis","created":"2023-12-14","cited_by_count":1,"area":null},{"id":"2403.12317","title":"EffiPerception: an Efficient Framework for Various Perception Tasks","created":"2024-03-18","cited_by_count":1,"area":null},{"id":"2405.07524","title":"HybridHash: Hybrid Convolutional and Self-Attention Deep Hashing for Image Retrieval","created":"2024-05-13","cited_by_count":1,"area":null},{"id":"2406.02021","title":"FFNet: MetaMixer-based Efficient Convolutional Mixer Design","created":"2024-06-04","cited_by_count":1,"area":null},{"id":"2406.07536","title":"Towards Fundamentally Scalable Model Selection: Asymptotically Fast Update and Selection","created":"2024-06-11","cited_by_count":1,"area":null},{"id":"2408.06604","title":"MV-DETR: Multi-modality indoor object detection by Multi-View DEtecton TRansformers","created":"2024-08-13","cited_by_count":1,"area":null},{"id":"2408.08056","title":"DATTA: Domain Diversity Aware Test-Time Adaptation for Dynamic Domain Shift Data Streams","created":"2024-08-15","cited_by_count":1,"area":null},{"id":"2410.19166","title":"DCT-HistoTransformer: Efficient Lightweight Vision Transformer with DCT Integration for histopathological image analysis","created":"2024-10-24","cited_by_count":1,"area":null},{"id":"2412.16602","title":"V\"Mean\"ba: Visual State Space Models only need 1 hidden dimension","created":"2024-12-21","cited_by_count":1,"area":null},{"id":"2502.18323","title":"Accelerated Training on Low-Power Edge Devices","created":"2025-02-25","cited_by_count":1,"area":null},{"id":"2503.07371","title":"HGO-YOLO: Advancing Anomaly Behavior Detection with Hierarchical Features and Lightweight Optimized Detection","created":"2025-03-10","cited_by_count":1,"area":null},{"id":"2505.10689","title":"A probabilistic framework for dynamic quantization","created":"2025-05-15","cited_by_count":1,"area":null},{"id":"2506.06782","title":"Feature-Based Instance Neighbor Discovery: Advanced Stable Test-Time Adaptation in Dynamic World","created":"2025-06-07","cited_by_count":1,"area":null},{"id":"2507.15798","title":"Exploring Superposition and Interference in State-of-the-Art Low-Parameter Vision Models","created":"2025-07-21","cited_by_count":1,"area":null},{"id":"2508.05307","title":"CoCAViT: Compact Vision Transformer with Robust Global Coordination","created":"2025-08-07","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":"2509.02792","title":"Structured Basis Function Networks: Loss-Centric Multi-Hypothesis Ensembles with Controllable Diversity","created":"2025-09-02","cited_by_count":1,"area":null},{"id":"2604.02930","title":"BEVPredFormer: Spatio-temporal Attention for BEV Instance Prediction in Autonomous Driving","created":"2026-04-03","cited_by_count":1,"area":null},{"id":"2309.06902","title":"CCSPNet-Joint: Efficient Joint Training Method for Traffic Sign Detection Under Extreme Conditions","created":"2023-09-13","cited_by_count":0,"area":null},{"id":"2311.13615","title":"HEViTPose: High-Efficiency Vision Transformer for Human Pose Estimation","created":"2023-11-22","cited_by_count":0,"area":null}],"next_cursor":"100"}