{"total":41,"rows":[{"id":"2303.11331","title":"EVA-02: A Visual Representation for Neon Genesis","created":"2023-03-20","cited_by_count":381,"area":null},{"id":"2303.03667","title":"Run, Don't Walk: Chasing Higher FLOPS for Faster Neural Networks","created":"2023-03-07","cited_by_count":130,"area":null},{"id":"2307.09283","title":"RepViT: Revisiting Mobile CNN From ViT Perspective","created":"2023-07-18","cited_by_count":123,"area":null},{"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":"2301.01146","title":"Rethinking Mobile Block for Efficient Attention-based Models","created":"2023-01-03","cited_by_count":36,"area":null},{"id":"2301.01296","title":"TinyMIM: An Empirical Study of Distilling MIM Pre-trained Models","created":"2023-01-03","cited_by_count":24,"area":null},{"id":"2303.09730","title":"ElasticViT: Conflict-aware Supernet Training for Deploying Fast Vision Transformer on Diverse Mobile Devices","created":"2023-03-17","cited_by_count":10,"area":null},{"id":"2404.05196","title":"HSViT: Horizontally Scalable Vision Transformer","created":"2024-04-08","cited_by_count":6,"area":null},{"id":"2410.11650","title":"Efficient Partitioning Vision Transformer on Edge Devices for Distributed Inference","created":"2024-10-15","cited_by_count":6,"area":null},{"id":"2412.06674","title":"EMOv2: Pushing 5M Vision Model Frontier","created":"2024-12-09","cited_by_count":5,"area":null},{"id":"2309.09003","title":"RingMo-lite: A Remote Sensing Multi-task Lightweight Network with CNN-Transformer Hybrid Framework","created":"2023-09-16","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":"2406.16004","title":"RepNeXt: A Fast Multi-Scale CNN using Structural Reparameterization","created":"2024-06-23","cited_by_count":4,"area":null},{"id":"2305.11875","title":"FR-Net:A Light-weight FFT Residual Net For Gaze Estimation","created":"2023-05-04","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":"2411.18855","title":"Improving Accuracy and Generalization for Efficient Visual Tracking","created":"2024-11-28","cited_by_count":3,"area":null},{"id":"2307.09120","title":"Light-Weight Vision Transformer with Parallel Local and Global Self-Attention","created":"2023-07-18","cited_by_count":2,"area":null},{"id":"2310.19654","title":"MCAD: Multi-teacher Cross-modal Alignment Distillation for efficient image-text retrieval","created":"2023-10-30","cited_by_count":1,"area":null},{"id":"2406.14239","title":"LeYOLO, New Embedded Architecture for Object Detection","created":"2024-06-20","cited_by_count":1,"area":null},{"id":"2410.14874","title":"Beyond Isolated Heads: Multi-Overlapped-Head Self-Attention for Vision Transformers","created":"2024-10-18","cited_by_count":1,"area":null},{"id":"2410.24139","title":"COSNet: A Novel Semantic Segmentation Network using Enhanced Boundaries in Cluttered Scenes","created":"2024-10-31","cited_by_count":1,"area":null},{"id":"2412.08074","title":"EM-Net: Gaze Estimation with Expectation Maximization Algorithm","created":"2024-12-11","cited_by_count":1,"area":null},{"id":"2504.07029","title":"Distilling Textual Priors from LLM to Efficient Image Fusion","created":"2025-04-09","cited_by_count":1,"area":null},{"id":"2507.09294","title":"Geo-RepNet: Geometry-Aware Representation Learning for Surgical Phase Recognition in Endoscopic Submucosal Dissection","created":"2025-07-12","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":"2605.22132","title":"Accelerating Vision Foundation Models with Drop-in Depthwise Convolution","created":"2026-05-21","cited_by_count":1,"area":null},{"id":"2401.05968","title":"A Lightweight Feature Fusion Architecture For Resource-Constrained Crowd Counting","created":"2024-01-11","cited_by_count":0,"area":null},{"id":"2405.14024","title":"Predicting High-precision Depth on Low-Precision Devices Using 2D Hilbert Curves","created":"2024-05-22","cited_by_count":0,"area":null},{"id":"2411.18064","title":"Lightweight Gaze Estimation Model Via Fusion Global Information","created":"2024-11-27","cited_by_count":0,"area":null},{"id":"2412.07009","title":"LUIEO: A Lightweight Model for Integrating Underwater Image Enhancement and Object Detection","created":"2024-12-01","cited_by_count":0,"area":null},{"id":"2412.13273","title":"CompactFlowNet: Efficient Real-time Optical Flow Estimation on Mobile Devices","created":"2024-12-17","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":"2506.17596","title":"A Multimodal In Vitro Diagnostic Method for Parkinson's Disease Combining Facial Expressions and Behavioral Gait Data","created":"2025-06-21","cited_by_count":0,"area":null},{"id":"2507.17335","title":"TransLPRNet: Lite Vision-Language Network for Single/Dual-line Chinese License Plate Recognition","created":"2025-07-23","cited_by_count":0,"area":null},{"id":"2508.00900","title":"Sparse 3D Perception for Rose Harvesting Robots: A Two-Stage Approach Bridging Simulation and Real-World Applications","created":"2025-07-28","cited_by_count":0,"area":null},{"id":"2508.01385","title":"Lightweight Backbone Networks Only Require Adaptive Lightweight Self-Attention Mechanisms","created":"2025-08-02","cited_by_count":0,"area":null},{"id":"2511.14111","title":"CascadedViT: Cascaded Chunk-FeedForward and Cascaded Group Attention Vision Transformer","created":"2025-11-18","cited_by_count":0,"area":null},{"id":"2512.08647","title":"C-DIRA: Computationally Efficient Dynamic ROI Routing and Domain-Invariant Adversarial Learning for Lightweight Driver Behavior Recognition","created":"2025-12-09","cited_by_count":0,"area":null},{"id":"2601.08190","title":"Human-inspired Global-to-Parallel Multi-scale Encoding for Lightweight Vision Models","created":"2026-01-13","cited_by_count":0,"area":null},{"id":"2605.15423","title":"MR2-ByteTrack: CNN and Transformer-based Video Object Detection for AI-augmented Embedded Vision Sensor Nodes","created":"2026-05-14","cited_by_count":0,"area":null},{"id":"2606.13587","title":"Towards Effective Waste Segmentation for Automated Waste Recycling in Cluttered Background","created":"2026-06-11","cited_by_count":0,"area":null}],"next_cursor":null}