{"total":42,"rows":[{"id":"2301.00808","title":"ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders","created":"2023-01-02","cited_by_count":712,"area":null},{"id":"2111.07624","title":"Attention Mechanisms in Computer Vision: A Survey","created":"2021-11-15","cited_by_count":232,"area":null},{"id":"2101.07663","title":"Salient Object Detection via Integrity Learning","created":"2021-01-19","cited_by_count":133,"area":null},{"id":"2402.05408","title":"MIGC: Multi-Instance Generation Controller for Text-to-Image Synthesis","created":"2024-02-08","cited_by_count":124,"area":null},{"id":"2103.13258","title":"Dynamic Slimmable Network","created":"2021-03-24","cited_by_count":83,"area":null},{"id":"2106.01439","title":"NTIRE 2021 Challenge on High Dynamic Range Imaging: Dataset, Methods and Results","created":"2021-06-02","cited_by_count":36,"area":null},{"id":"2112.02853","title":"Reliable Propagation-Correction Modulation for Video Object Segmentation","created":"2021-12-06","cited_by_count":36,"area":null},{"id":"2205.11083","title":"Deep Digging into the Generalization of Self-Supervised Monocular Depth Estimation","created":"2022-05-23","cited_by_count":24,"area":null},{"id":"2104.07916","title":"Augmenting Deep Classifiers with Polynomial Neural Networks","created":"2021-04-16","cited_by_count":21,"area":null},{"id":"2203.11442","title":"Scalable Video Object Segmentation with Identification Mechanism","created":"2022-03-22","cited_by_count":18,"area":null},{"id":"2104.03658","title":"DSC-PoseNet: Learning 6DoF Object Pose Estimation via Dual-scale Consistency","created":"2021-04-08","cited_by_count":14,"area":null},{"id":"2411.01542","title":"FactorizePhys: Matrix Factorization for Multidimensional Attention in Remote Physiological Sensing","created":"2024-11-03","cited_by_count":14,"area":null},{"id":"2305.10469","title":"Object Segmentation by Mining Cross-Modal Semantics","created":"2023-05-17","cited_by_count":12,"area":null},{"id":"2207.00887","title":"Towards Robust Video Object Segmentation with Adaptive Object Calibration","created":"2022-07-02","cited_by_count":11,"area":null},{"id":"2310.11198","title":"EEG motor imagery decoding: A framework for comparative analysis with channel attention mechanisms","created":"2023-10-17","cited_by_count":11,"area":null},{"id":"2407.05128","title":"SCSA: Exploring the Synergistic Effects Between Spatial and Channel Attention","created":"2024-07-06","cited_by_count":10,"area":null},{"id":"2110.08940","title":"Dynamic Slimmable Denoising Network","created":"2021-10-17","cited_by_count":9,"area":null},{"id":"2304.03910","title":"Co-attention Propagation Network for Zero-Shot Video Object Segmentation","created":"2023-04-08","cited_by_count":9,"area":null},{"id":"2406.00721","title":"Explore Internal and External Similarity for Single Image Deraining with Graph Neural Networks","created":"2024-06-02","cited_by_count":7,"area":null},{"id":"2109.10060","title":"DS-Net++: Dynamic Weight Slicing for Efficient Inference in CNNs and Transformers","created":"2021-09-21","cited_by_count":6,"area":null},{"id":"2203.12944","title":"Transformers Meet Visual Learning Understanding: A Comprehensive Review","created":"2022-03-24","cited_by_count":5,"area":null},{"id":"2208.09211","title":"Booster-SHOT: Boosting Stacked Homography Transformations for Multiview Pedestrian Detection with Attention","created":"2022-08-19","cited_by_count":5,"area":null},{"id":"2301.03169","title":"A Study on the Generality of Neural Network Structures for Monocular Depth Estimation","created":"2023-01-09","cited_by_count":4,"area":null},{"id":"2504.09666","title":"Uncertainty Guided Refinement for Fine-Grained Salient Object Detection","created":"2025-04-13","cited_by_count":4,"area":null},{"id":"2508.03625","title":"AttZoom: Attention Zoom for Better Visual Features","created":"2025-08-05","cited_by_count":4,"area":null},{"id":"2109.02580","title":"Ultra-high Resolution Image Segmentation via Locality-aware Context Fusion and Alternating Local Enhancement","created":"2021-09-06","cited_by_count":3,"area":null},{"id":"2208.10322","title":"Mix-Pooling Strategy for Attention Mechanism","created":"2022-08-22","cited_by_count":3,"area":null},{"id":"2211.13745","title":"Attention-based Feature Compression for CNN Inference Offloading in Edge Computing","created":"2022-11-24","cited_by_count":3,"area":null},{"id":"2312.09525","title":"Hierarchical Graph Pattern Understanding for Zero-Shot VOS","created":"2023-12-15","cited_by_count":2,"area":null},{"id":"2403.01713","title":"MCA: Moment Channel Attention Networks","created":"2024-03-04","cited_by_count":2,"area":null},{"id":"2408.13341","title":"Toward Improving Synthetic Audio Spoofing Detection Robustness via Meta-Learning and Disentangled Training With Adversarial Examples","created":"2024-08-23","cited_by_count":1,"area":null},{"id":"2408.13355","title":"Disentangled Training with Adversarial Examples For Robust Small-footprint Keyword Spotting","created":"2024-08-23","cited_by_count":1,"area":null},{"id":"2601.00123","title":"A Spatially Masked Adaptive Gated Network for multimodal post-flood water extent mapping using SAR and incomplete multispectral data","created":"2025-12-31","cited_by_count":1,"area":null},{"id":"2211.02695","title":"WaveNets: Wavelet Channel Attention Networks","created":"2022-11-04","cited_by_count":0,"area":null},{"id":"2303.09668","title":"Rt-Track: Robust Tricks for Multi-Pedestrian Tracking","created":"2023-03-16","cited_by_count":0,"area":null},{"id":"2404.06941","title":"Accelerating Cardiac MRI Reconstruction with CMRatt: An Attention-Driven Approach","created":"2024-04-10","cited_by_count":0,"area":null},{"id":"2410.21670","title":"Sequential choice in ordered bundles","created":"2024-10-29","cited_by_count":0,"area":null},{"id":"2411.08333","title":"SASE: A Searching Architecture for Squeeze and Excitation Operations","created":"2024-11-13","cited_by_count":0,"area":null},{"id":"2503.10875","title":"Convolutional Rectangular Attention Module","created":"2025-03-13","cited_by_count":0,"area":null},{"id":"2505.05943","title":"Achieving 3D Attention via Triplet Squeeze and Excitation Block","created":"2025-05-09","cited_by_count":0,"area":null},{"id":"2512.24622","title":"FireRescue: A UAV-Based Dataset and Enhanced YOLO Model for Object Detection in Fire Rescue Scenes","created":"2025-12-31","cited_by_count":0,"area":null},{"id":"2610.15079","title":"Region Aware Squeeze-and-Excitation Networks for Image Segmentation","created":"2026-10-10","cited_by_count":0,"area":null}],"next_cursor":null}