{"total":30,"rows":[{"id":"2304.08069","title":"DETRs Beat YOLOs on Real-time Object Detection","created":"2023-04-17","cited_by_count":533,"area":null},{"id":"2402.13616","title":"YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information","created":"2024-02-21","cited_by_count":425,"area":null},{"id":"2303.11331","title":"EVA-02: A Visual Representation for Neon Genesis","created":"2023-03-20","cited_by_count":381,"area":null},{"id":"2303.11926","title":"Exploring Object-Centric Temporal Modeling for Efficient Multi-View 3D Object Detection","created":"2023-03-21","cited_by_count":315,"area":null},{"id":"2305.11172","title":"ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities","created":"2023-05-18","cited_by_count":118,"area":null},{"id":"2403.07392","title":"ViT-CoMer: Vision Transformer with Convolutional Multi-scale Feature Interaction for Dense Predictions","created":"2024-03-12","cited_by_count":66,"area":null},{"id":"2305.17863","title":"GridFormer: Residual Dense Transformer with Grid Structure for Image Restoration in Adverse Weather Conditions","created":"2023-05-29","cited_by_count":62,"area":null},{"id":"2408.06687","title":"Masked Image Modeling: A Survey","created":"2024-08-13","cited_by_count":29,"area":null},{"id":"2406.09135","title":"AdaRevD: Adaptive Patch Exiting Reversible Decoder Pushes the Limit of Image Deblurring","created":"2024-06-13","cited_by_count":25,"area":null},{"id":"2410.08063","title":"Reversible Decoupling Network for Single Image Reflection Removal","created":"2024-10-10","cited_by_count":22,"area":null},{"id":"2310.15670","title":"Leveraging Vision-Centric Multi-Modal Expertise for 3D Object Detection","created":"2023-10-24","cited_by_count":13,"area":null},{"id":"2403.19588","title":"DenseNets Reloaded: Paradigm Shift Beyond ResNets and ViTs","created":"2024-03-28","cited_by_count":12,"area":null},{"id":"2506.18527","title":"Auto-Regressively Generating Multi-View Consistent Images","created":"2025-06-23","cited_by_count":9,"area":null},{"id":"2408.15263","title":"S4DL: Shift-sensitive Spatial-Spectral Disentangling Learning for Hyperspectral Image Unsupervised Domain Adaptation","created":"2024-08-11","cited_by_count":6,"area":null},{"id":"2410.19553","title":"On Occlusions in Video Action Detection: Benchmark Datasets And Training Recipes","created":"2024-10-25","cited_by_count":6,"area":null},{"id":"2301.11360","title":"The Power of Linear Combinations: Learning with Random Convolutions","created":"2023-01-26","cited_by_count":4,"area":null},{"id":"2309.01005","title":"RevColV2: Exploring Disentangled Representations in Masked Image Modeling","created":"2023-09-02","cited_by_count":4,"area":null},{"id":"2510.13282","title":"Universal Image Restoration Pre-training via Masked Degradation Classification","created":"2025-10-15","cited_by_count":4,"area":null},{"id":"2302.06052","title":"CEDNet: A Cascade Encoder-Decoder Network for Dense Prediction","created":"2023-02-13","cited_by_count":3,"area":null},{"id":"2407.14302","title":"Dyn-Adapter: Towards Disentangled Representation for Efficient Visual Recognition","created":"2024-07-19","cited_by_count":3,"area":null},{"id":"2505.19795","title":"The Missing Point in Vision Transformers for Universal Image Segmentation","created":"2025-05-26","cited_by_count":3,"area":null},{"id":"2406.14239","title":"LeYOLO, New Embedded Architecture for Object Detection","created":"2024-06-20","cited_by_count":1,"area":null},{"id":"2407.14792","title":"FedPartWhole: Federated domain generalization via consistent part-whole hierarchies","created":"2024-07-20","cited_by_count":1,"area":null},{"id":"2409.16838","title":"Explicitly Modeling Pre-Cortical Vision with a Neuro-Inspired Front-End Improves CNN Robustness","created":"2024-09-25","cited_by_count":1,"area":null},{"id":"2305.18988","title":"A Recipe for Efficient SBIR Models: Combining Relative Triplet Loss with Batch Normalization and Knowledge Distillation","created":"2023-05-30","cited_by_count":0,"area":null},{"id":"2411.13021","title":"Chanel-Orderer: A Channel-Ordering Predictor for Tri-Channel Natural Images","created":"2024-11-20","cited_by_count":0,"area":null},{"id":"2501.02618","title":"Identifying Surgical Instruments in Pedagogical Cataract Surgery Videos through an Optimized Aggregation Network","created":"2025-01-05","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":"2511.21132","title":"DeepRFTv2: Kernel-level Learning for Image Deblurring","created":"2025-11-26","cited_by_count":0,"area":null},{"id":"2609.19122","title":"Training-Adaptive Convolutional Sparse Coding via Information Bottleneck for Robust Visual Representation","created":"2026-09-16","cited_by_count":0,"area":null}],"next_cursor":null}