{"total":136,"rows":[{"id":"2102.05095","title":"Is Space-Time Attention All You Need for Video Understanding?","created":"2021-02-09","cited_by_count":1620,"area":null},{"id":"2103.15691","title":"ViViT: A Video Vision Transformer","created":"2021-03-29","cited_by_count":1620,"area":null},{"id":"2104.00650","title":"Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval","created":"2021-04-01","cited_by_count":1177,"area":null},{"id":"2101.11986","title":"Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet","created":"2021-01-28","cited_by_count":1101,"area":null},{"id":"2111.11418","title":"MetaFormer Is Actually What You Need for Vision","created":"2021-11-22","cited_by_count":524,"area":null},{"id":"2103.10697","title":"ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biases","created":"2021-03-19","cited_by_count":484,"area":null},{"id":"2104.11178","title":"VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text","created":"2021-04-22","cited_by_count":429,"area":null},{"id":"2104.00272","title":"Mesh Graphormer","created":"2021-04-01","cited_by_count":265,"area":null},{"id":"2103.11816","title":"Incorporating Convolution Designs into Visual Transformers","created":"2021-03-22","cited_by_count":248,"area":null},{"id":"2103.02907","title":"Coordinate Attention for Efficient Mobile Network Design","created":"2021-03-04","cited_by_count":241,"area":null},{"id":"2111.07624","title":"Attention Mechanisms in Computer Vision: A Survey","created":"2021-11-15","cited_by_count":232,"area":null},{"id":"2106.05392","title":"Keeping Your Eye on the Ball: Trajectory Attention in Video Transformers","created":"2021-06-09","cited_by_count":224,"area":null},{"id":"2106.13112","title":"VOLO: Vision Outlooker for Visual Recognition","created":"2021-06-24","cited_by_count":165,"area":null},{"id":"2304.09854","title":"Transformer-Based Visual Segmentation: A Survey","created":"2023-04-19","cited_by_count":124,"area":null},{"id":"2103.01209","title":"Generative Adversarial Transformers","created":"2021-03-01","cited_by_count":120,"area":null},{"id":"2111.06091","title":"A Survey of Visual Transformers","created":"2021-11-11","cited_by_count":117,"area":null},{"id":"2105.02358","title":"Beyond Self-attention: External Attention using Two Linear Layers for Visual Tasks","created":"2021-05-05","cited_by_count":109,"area":null},{"id":"2102.08602","title":"LambdaNetworks: Modeling Long-Range Interactions Without Attention","created":"2021-02-17","cited_by_count":107,"area":null},{"id":"2106.12368","title":"Vision Permutator: A Permutable MLP-Like Architecture for Visual Recognition","created":"2021-06-23","cited_by_count":103,"area":null},{"id":"2103.06255","title":"Involution: Inverting the Inherence of Convolution for Visual Recognition","created":"2021-03-10","cited_by_count":99,"area":null},{"id":"2106.05968","title":"Space-time Mixing Attention for Video Transformer","created":"2021-06-10","cited_by_count":84,"area":null},{"id":"2203.09905","title":"Learning Affordance Grounding from Exocentric Images","created":"2022-03-18","cited_by_count":82,"area":null},{"id":"2109.04553","title":"Is Attention Better Than Matrix Decomposition?","created":"2021-09-09","cited_by_count":77,"area":null},{"id":"2104.13874","title":"Exploring Relational Context for Multi-Task Dense Prediction","created":"2021-04-28","cited_by_count":71,"area":null},{"id":"2203.09653","title":"Regional Semantic Contrast and Aggregation for Weakly Supervised Semantic Segmentation","created":"2022-03-17","cited_by_count":64,"area":null},{"id":"2103.07372","title":"ACTION-Net: Multipath Excitation for Action Recognition","created":"2021-03-11","cited_by_count":63,"area":null},{"id":"2206.08948","title":"CMT-DeepLab: Clustering Mask Transformers for Panoptic Segmentation","created":"2022-06-17","cited_by_count":60,"area":null},{"id":"2109.07036","title":"PnP-DETR: Towards Efficient Visual Analysis with Transformers","created":"2021-09-15","cited_by_count":52,"area":null},{"id":"2103.16775","title":"Attention, please! A survey of Neural Attention Models in Deep Learning","created":"2021-03-31","cited_by_count":51,"area":null},{"id":"2103.05687","title":"Capturing Omni-Range Context for Omnidirectional Segmentation","created":"2021-03-09","cited_by_count":50,"area":null},{"id":"2108.09322","title":"MM-ViT: Multi-Modal Video Transformer for Compressed Video Action Recognition","created":"2021-08-20","cited_by_count":46,"area":null},{"id":"2104.09805","title":"CTNet: Context-based Tandem Network for Semantic Segmentation","created":"2021-04-20","cited_by_count":43,"area":null},{"id":"2106.11958","title":"Prototypical Cross-Attention Networks for Multiple Object Tracking and Segmentation","created":"2021-06-22","cited_by_count":43,"area":null},{"id":"2111.00207","title":"PatchFormer: An Efficient Point Transformer with Patch Attention","created":"2021-10-30","cited_by_count":43,"area":null},{"id":"2305.13563","title":"Efficient Multi-Scale Attention Module with Cross-Spatial Learning","created":"2023-05-23","cited_by_count":41,"area":null},{"id":"2103.13164","title":"M3DSSD: Monocular 3D Single Stage Object Detector","created":"2021-03-24","cited_by_count":39,"area":null},{"id":"2103.15662","title":"Unified Graph Structured Models for Video Understanding","created":"2021-03-29","cited_by_count":38,"area":null},{"id":"2204.07756","title":"Visual Attention Methods in Deep Learning: An In-Depth Survey","created":"2022-04-16","cited_by_count":37,"area":null},{"id":"2105.00149","title":"SVT-Net: Super Light-Weight Sparse Voxel Transformer for Large Scale Place Recognition","created":"2021-05-01","cited_by_count":36,"area":null},{"id":"2201.03746","title":"TSA-Net: Tube Self-Attention Network for Action Quality Assessment","created":"2022-01-11","cited_by_count":36,"area":null},{"id":"2308.09891","title":"SwinLSTM:Improving Spatiotemporal Prediction Accuracy using Swin Transformer and LSTM","created":"2023-08-19","cited_by_count":32,"area":null},{"id":"2107.04932","title":"Aligning Correlation Information for Domain Adaptation in Action Recognition","created":"2021-07-11","cited_by_count":30,"area":null},{"id":"2207.06095","title":"Eliminating Gradient Conflict in Reference-based Line-Art Colorization","created":"2022-07-13","cited_by_count":25,"area":null},{"id":"2102.02531","title":"ABCNet: Attentive Bilateral Contextual Network for Efficient Semantic Segmentation of Fine-Resolution Remote Sensing Images","created":"2021-02-04","cited_by_count":22,"area":null},{"id":"2302.03985","title":"Cross-Layer Retrospective Retrieving via Layer Attention","created":"2023-02-08","cited_by_count":22,"area":null},{"id":"2306.04670","title":"Object Detection with Transformers: A Review","created":"2023-06-07","cited_by_count":22,"area":null},{"id":"2104.07916","title":"Augmenting Deep Classifiers with Polynomial Neural Networks","created":"2021-04-16","cited_by_count":21,"area":null},{"id":"2107.05790","title":"Visual Parser: Representing Part-whole Hierarchies with Transformers","created":"2021-07-13","cited_by_count":21,"area":null},{"id":"2111.12527","title":"MorphMLP: An Efficient MLP-Like Backbone for Spatial-Temporal Representation Learning","created":"2021-11-24","cited_by_count":21,"area":null},{"id":"2102.10212","title":"Hard-Attention for Scalable Image Classification","created":"2021-02-20","cited_by_count":18,"area":null},{"id":"2301.13156","title":"SeaFormer++: Squeeze-enhanced Axial Transformer for Mobile Visual Recognition","created":"2023-01-30","cited_by_count":18,"area":null},{"id":"2101.07034","title":"AGRNet: Adaptive Graph Representation Learning and Reasoning for Face Parsing","created":"2021-01-18","cited_by_count":16,"area":null},{"id":"2309.06891","title":"Keep It SimPool: Who Said Supervised Transformers Suffer from Attention Deficit?","created":"2023-09-13","cited_by_count":16,"area":null},{"id":"2105.14447","title":"EPSANet: An Efficient Pyramid Squeeze Attention Block on Convolutional Neural Network","created":"2021-05-30","cited_by_count":15,"area":null},{"id":"2105.13033","title":"SSAN: Separable Self-Attention Network for Video Representation Learning","created":"2021-05-27","cited_by_count":13,"area":null},{"id":"2112.01695","title":"Hybrid Instance-aware Temporal Fusion for Online Video Instance Segmentation","created":"2021-12-03","cited_by_count":13,"area":null},{"id":"2209.01339","title":"DSE-GAN: Dynamic Semantic Evolution Generative Adversarial Network for Text-to-Image Generation","created":"2022-09-03","cited_by_count":13,"area":null},{"id":"2210.02093","title":"Centralized Feature Pyramid for Object Detection","created":"2022-10-05","cited_by_count":13,"area":null},{"id":"2107.08000","title":"All the attention you need: Global-local, spatial-channel attention for image retrieval","created":"2021-07-16","cited_by_count":12,"area":null},{"id":"2111.02333","title":"HS3: Learning with Proper Task Complexity in Hierarchically Supervised Semantic Segmentation","created":"2021-11-03","cited_by_count":12,"area":null},{"id":"2207.04044","title":"kMaX-DeepLab: k-means Mask Transformer","created":"2022-07-08","cited_by_count":12,"area":null},{"id":"2401.17992","title":"Multilinear Operator Networks","created":"2024-01-31","cited_by_count":12,"area":null},{"id":"2303.12194","title":"LiDARFormer: A Unified Transformer-based Multi-task Network for LiDAR Perception","created":"2023-03-21","cited_by_count":11,"area":null},{"id":"2402.12138","title":"Perceiving Longer Sequences With Bi-Directional Cross-Attention Transformers","created":"2024-02-19","cited_by_count":11,"area":null},{"id":"2211.15595","title":"FsaNet: Frequency Self-attention for Semantic Segmentation","created":"2022-11-28","cited_by_count":10,"area":null},{"id":"2406.13392","title":"Strengthening Layer Interaction via Dynamic Layer Attention","created":"2024-06-19","cited_by_count":10,"area":null},{"id":"2104.03618","title":"MRI-based Alzheimer's disease prediction via distilling the knowledge in multi-modal data","created":"2021-04-08","cited_by_count":9,"area":null},{"id":"2107.13154","title":"Global Aggregation then Local Distribution for Scene Parsing","created":"2021-07-28","cited_by_count":8,"area":null},{"id":"2112.05909","title":"Neural Attention Models in Deep Learning: Survey and Taxonomy","created":"2021-12-11","cited_by_count":8,"area":null},{"id":"2201.09271","title":"Wavelet-Attention CNN for Image Classification","created":"2022-01-23","cited_by_count":8,"area":null},{"id":"2206.11428","title":"LidarMultiNet: Unifying LiDAR Semantic Segmentation, 3D Object Detection, and Panoptic Segmentation in a Single Multi-task Network","created":"2022-06-23","cited_by_count":8,"area":null},{"id":"2112.07106","title":"E-CRF: Embedded Conditional Random Field for Boundary-caused Class Weights Confusion in Semantic Segmentation","created":"2021-12-14","cited_by_count":7,"area":null},{"id":"2402.09329","title":"YOLOv8-AM: YOLOv8 Based on Effective Attention Mechanisms for Pediatric Wrist Fracture Detection","created":"2024-02-14","cited_by_count":7,"area":null},{"id":"2408.11593","title":"MCDubber: Multimodal Context-Aware Expressive Video Dubbing","created":"2024-08-21","cited_by_count":7,"area":null},{"id":"2104.08665","title":"Higher Order Recurrent Space-Time Transformer for Video Action Prediction","created":"2021-04-17","cited_by_count":6,"area":null},{"id":"2309.15697","title":"Physics Inspired Hybrid Attention for SAR Target Recognition","created":"2023-09-27","cited_by_count":6,"area":null},{"id":"2502.04028","title":"Deep Meta Coordination Graphs for Multi-agent Reinforcement Learning","created":"2025-02-06","cited_by_count":6,"area":null},{"id":"2409.18826","title":"YOLOv8-ResCBAM: YOLOv8 Based on An Effective Attention Module for Pediatric Wrist Fracture Detection","created":"2024-09-27","cited_by_count":5,"area":null},{"id":"2502.09928","title":"Deep Tree Tensor Networks","created":"2025-02-14","cited_by_count":5,"area":null},{"id":"2106.05795","title":"Transformed CNNs: recasting pre-trained convolutional layers with self-attention","created":"2021-06-10","cited_by_count":4,"area":null},{"id":"2111.13470","title":"TDAM: Top-Down Attention Module for Contextually Guided Feature Selection in CNNs","created":"2021-11-26","cited_by_count":4,"area":null},{"id":"2203.00172","title":"Enhancing Local Feature Learning for 3D Point Cloud Processing using Unary-Pairwise Attention","created":"2022-03-01","cited_by_count":4,"area":null},{"id":"2106.03162","title":"Transformed ROIs for Capturing Visual Transformations in Videos","created":"2021-06-06","cited_by_count":3,"area":null},{"id":"2107.07837","title":"Progressive Deep Video Dehazing without Explicit Alignment Estimation","created":"2021-07-16","cited_by_count":3,"area":null},{"id":"2108.02451","title":"Unifying Nonlocal Blocks for Neural Networks","created":"2021-08-05","cited_by_count":3,"area":null},{"id":"2108.08205","title":"An Attention Module for Convolutional Neural Networks","created":"2021-08-18","cited_by_count":3,"area":null},{"id":"2204.11045","title":"Investigating Neural Architectures by Synthetic Dataset Design","created":"2022-04-23","cited_by_count":3,"area":null},{"id":"2302.05213","title":"CEN-HDR: Computationally Efficient neural Network for real-time High Dynamic Range imaging","created":"2023-02-10","cited_by_count":3,"area":null},{"id":"2304.09059","title":"Coupling Global Context and Local Contents for Weakly-Supervised Semantic Segmentation","created":"2023-04-18","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":"2106.04400","title":"CSRNet: Cascaded Selective Resolution Network for Real-time Semantic Segmentation","created":"2021-06-08","cited_by_count":2,"area":null},{"id":"2111.07547","title":"Searching for TrioNet: Combining Convolution with Local and Global Self-Attention","created":"2021-11-15","cited_by_count":2,"area":null},{"id":"2111.15200","title":"Contrastive Learning for Local and Global Learning MRI Reconstruction","created":"2021-11-30","cited_by_count":2,"area":null},{"id":"2208.00775","title":"Pavementscapes: a large-scale hierarchical image dataset for asphalt pavement damage segmentation","created":"2022-07-24","cited_by_count":2,"area":null},{"id":"2209.07474","title":"On the Surprising Effectiveness of Transformers in Low-Labeled Video Recognition","created":"2022-09-15","cited_by_count":2,"area":null},{"id":"2308.14087","title":"A comprehensive review on Plant Leaf Disease detection using Deep learning","created":"2023-08-27","cited_by_count":2,"area":null},{"id":"2310.04719","title":"A Comprehensive Survey on Deep Neural Image Deblurring","created":"2023-10-07","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":"2101.00850","title":"Low Light Image Enhancement via Global and Local Context Modeling","created":"2021-01-04","cited_by_count":1,"area":null},{"id":"2103.11190","title":"Efficient Spatialtemporal Context Modeling for Action Recognition","created":"2021-03-20","cited_by_count":1,"area":null}],"next_cursor":"100"}