{"total":120,"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":"2312.14150","title":"DriveLM: Driving with Graph Visual Question Answering","created":"2023-12-21","cited_by_count":536,"area":"mllm"},{"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":"2111.07624","title":"Attention Mechanisms in Computer Vision: A Survey","created":"2021-11-15","cited_by_count":232,"area":null},{"id":"2103.12340","title":"Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayers","created":"2021-03-23","cited_by_count":104,"area":null},{"id":"2104.02613","title":"Mutual Graph Learning for Camouflaged Object Detection","created":"2021-04-03","cited_by_count":103,"area":null},{"id":"2105.07175","title":"Cross-Modal Progressive Comprehension for Referring Segmentation","created":"2021-05-15","cited_by_count":102,"area":null},{"id":"2103.14581","title":"Non-Salient Region Object Mining for Weakly Supervised Semantic Segmentation","created":"2021-03-26","cited_by_count":95,"area":null},{"id":"2109.04553","title":"Is Attention Better Than Matrix Decomposition?","created":"2021-09-09","cited_by_count":77,"area":null},{"id":"2209.13232","title":"A Survey on Graph Neural Networks and Graph Transformers in Computer Vision: A Task-Oriented Perspective","created":"2022-09-27","cited_by_count":56,"area":null},{"id":"2209.03299","title":"Multimodal learning with graphs","created":"2022-09-07","cited_by_count":54,"area":null},{"id":"2103.05558","title":"Exploiting Edge-Oriented Reasoning for 3D Point-based Scene Graph Analysis","created":"2021-03-09","cited_by_count":49,"area":null},{"id":"2107.00272","title":"A Survey on Graph-Based Deep Learning for Computational Histopathology","created":"2021-07-01","cited_by_count":41,"area":null},{"id":"2103.15662","title":"Unified Graph Structured Models for Video Understanding","created":"2021-03-29","cited_by_count":38,"area":null},{"id":"2201.12382","title":"Deep Learning Methods for Abstract Visual Reasoning: A Survey on Raven's Progressive Matrices","created":"2022-01-28","cited_by_count":37,"area":"lr"},{"id":"2201.13182","title":"Learning Super-Features for Image Retrieval","created":"2022-01-31","cited_by_count":35,"area":null},{"id":"2105.04066","title":"Reconstructive Sequence-Graph Network for Video Summarization","created":"2021-05-10","cited_by_count":34,"area":null},{"id":"2110.14223","title":"RRNet: Relational Reasoning Network with Parallel Multi-scale Attention for Salient Object Detection in Optical Remote Sensing Images","created":"2021-10-27","cited_by_count":34,"area":null},{"id":"2305.00278","title":"Segment Anything Model (SAM) Meets Glass: Mirror and Transparent Objects Cannot Be Easily Detected","created":"2023-04-29","cited_by_count":34,"area":null},{"id":"2112.03587","title":"TCGL: Temporal Contrastive Graph for Self-supervised Video Representation Learning","created":"2021-12-07","cited_by_count":31,"area":null},{"id":"2103.06564","title":"PointFlow: Flowing Semantics Through Points for Aerial Image Segmentation","created":"2021-03-11","cited_by_count":29,"area":null},{"id":"2303.08685","title":"Making Vision Transformers Efficient from A Token Sparsification View","created":"2023-03-15","cited_by_count":29,"area":null},{"id":"2105.04286","title":"Primitive Representation Learning for Scene Text Recognition","created":"2021-05-10","cited_by_count":28,"area":null},{"id":"2105.04823","title":"Learning Implicit Temporal Alignment for Few-shot Video Classification","created":"2021-05-11","cited_by_count":27,"area":null},{"id":"2303.11048","title":"SGFormer: Semantic Graph Transformer for Point Cloud-based 3D Scene Graph Generation","created":"2023-03-20","cited_by_count":27,"area":null},{"id":"2112.12916","title":"Visual Semantics Allow for Textual Reasoning Better in Scene Text Recognition","created":"2021-12-24","cited_by_count":25,"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":"2110.04111","title":"Discover, Hallucinate, and Adapt: Open Compound Domain Adaptation for Semantic Segmentation","created":"2021-10-08","cited_by_count":24,"area":null},{"id":"2207.10075","title":"Is an Object-Centric Video Representation Beneficial for Transfer?","created":"2022-07-20","cited_by_count":24,"area":null},{"id":"2112.04863","title":"3D Medical Point Transformer: Introducing Convolution to Attention Networks for Medical Point Cloud Analysis","created":"2021-12-09","cited_by_count":23,"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":"2401.01624","title":"Context-Aware Interaction Network for RGB-T Semantic Segmentation","created":"2024-01-03","cited_by_count":21,"area":null},{"id":"2403.10261","title":"Learning Spatiotemporal Inconsistency via Thumbnail Layout for Face Deepfake Detection","created":"2024-03-15","cited_by_count":21,"area":null},{"id":"2107.01319","title":"Learning Hierarchical Graph Neural Networks for Image Clustering","created":"2021-07-03","cited_by_count":18,"area":null},{"id":"2109.07701","title":"SPIN Road Mapper: Extracting Roads from Aerial Images via Spatial and Interaction Space Graph Reasoning for Autonomous Driving","created":"2021-09-16","cited_by_count":18,"area":null},{"id":"2110.12334","title":"SOLVER: Scene-Object Interrelated Visual Emotion Reasoning Network","created":"2021-10-24","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":"2105.03186","title":"A^2-FPN: Attention Aggregation based Feature Pyramid Network for Instance Segmentation","created":"2021-05-07","cited_by_count":15,"area":null},{"id":"2510.24038","title":"Enhancing CLIP Robustness via Cross-Modality Alignment","created":"2025-10-28","cited_by_count":15,"area":"mllm"},{"id":"2211.13491","title":"Spatial Mixture-of-Experts","created":"2022-11-24","cited_by_count":14,"area":"moe"},{"id":"2202.13402","title":"Concept Graph Neural Networks for Surgical Video Understanding","created":"2022-02-27","cited_by_count":13,"area":null},{"id":"2311.03550","title":"United We Stand, Divided We Fall: UnityGraph for Unsupervised Procedure Learning from Videos","created":"2023-11-06","cited_by_count":13,"area":null},{"id":"2301.10134","title":"Bipartite Graph Diffusion Model for Human Interaction Generation","created":"2023-01-24","cited_by_count":11,"area":"diffusion"},{"id":"2206.06637","title":"RF-Next: Efficient Receptive Field Search for Convolutional Neural Networks","created":"2022-06-14","cited_by_count":10,"area":null},{"id":"2211.15595","title":"FsaNet: Frequency Self-attention for Semantic Segmentation","created":"2022-11-28","cited_by_count":10,"area":null},{"id":"2110.14775","title":"BI-GCN: Boundary-Aware Input-Dependent Graph Convolution Network for Biomedical Image Segmentation","created":"2021-10-27","cited_by_count":9,"area":null},{"id":"2209.09545","title":"Graph Reasoning Transformer for Image Parsing","created":"2022-09-20","cited_by_count":9,"area":null},{"id":"2211.06719","title":"Bipartite Graph Reasoning GANs for Person Pose and Facial Image Synthesis","created":"2022-11-12","cited_by_count":9,"area":null},{"id":"2302.05637","title":"Dual Relation Knowledge Distillation for Object Detection","created":"2023-02-11","cited_by_count":9,"area":"distill"},{"id":"2101.02843","title":"Probabilistic Graph Attention Network with Conditional Kernels for Pixel-Wise Prediction","created":"2021-01-08","cited_by_count":8,"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":"2201.04027","title":"Representing Videos as Discriminative Sub-graphs for Action Recognition","created":"2022-01-11","cited_by_count":8,"area":null},{"id":"2307.12084","title":"Edge Guided GANs with Multi-Scale Contrastive Learning for Semantic Image Synthesis","created":"2023-07-22","cited_by_count":8,"area":null},{"id":"2312.02224","title":"Tracing Hyperparameter Dependencies for Model Parsing via Learnable Graph Pooling Network","created":"2023-12-03","cited_by_count":8,"area":null},{"id":"2101.08910","title":"Single Neuron Segmentation using Graph-based Global Reasoning with Auxiliary Skeleton Loss from 3D Optical Microscope Images","created":"2021-01-22","cited_by_count":7,"area":null},{"id":"2308.13897","title":"InsertNeRF: Instilling Generalizability into NeRF with HyperNet Modules","created":"2023-08-26","cited_by_count":7,"area":null},{"id":"2104.01888","title":"Non-Homogeneous Haze Removal via Artificial Scene Prior and Bidimensional Graph Reasoning","created":"2021-04-05","cited_by_count":6,"area":null},{"id":"2106.13952","title":"Spectral-Spatial Global Graph Reasoning for Hyperspectral Image Classification","created":"2021-06-26","cited_by_count":6,"area":null},{"id":"2201.08954","title":"Change Detection from Synthetic Aperture Radar Images via Graph-Based Knowledge Supplement Network","created":"2022-01-22","cited_by_count":6,"area":null},{"id":"2307.00212","title":"Internal-External Boundary Attention Fusion for Glass Surface Segmentation","created":"2023-07-01","cited_by_count":6,"area":null},{"id":"2103.04235","title":"Graph-based Pyramid Global Context Reasoning with a Saliency-aware Projection for COVID-19 Lung Infections Segmentation","created":"2021-03-07","cited_by_count":5,"area":null},{"id":"2104.08194","title":"Spatiotemporal Deformable Scene Graphs for Complex Activity Detection","created":"2021-04-16","cited_by_count":5,"area":null},{"id":"2107.02859","title":"Poly-NL: Linear Complexity Non-local Layers with Polynomials","created":"2021-07-06","cited_by_count":5,"area":null},{"id":"2208.04438","title":"Occlusion-Aware Instance Segmentation via BiLayer Network Architectures","created":"2022-08-08","cited_by_count":5,"area":null},{"id":"2312.04044","title":"Residual Graph Convolutional Network for Bird's-Eye-View Semantic Segmentation","created":"2023-12-07","cited_by_count":5,"area":null},{"id":"2401.08256","title":"Multitask Learning in Minimally Invasive Surgical Vision: A Review","created":"2024-01-16","cited_by_count":5,"area":null},{"id":"2508.15389","title":"Spiking Variational Graph Representation Inference for Video Summarization","created":"2025-08-21","cited_by_count":5,"area":null},{"id":"2108.12957","title":"Searching for Two-Stream Models in Multivariate Space for Video Recognition","created":"2021-08-30","cited_by_count":4,"area":null},{"id":"2111.14547","title":"LiVLR: A Lightweight Visual-Linguistic Reasoning Framework for Video Question Answering","created":"2021-11-29","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":"2204.11045","title":"Investigating Neural Architectures by Synthetic Dataset Design","created":"2022-04-23","cited_by_count":3,"area":null},{"id":"2211.12941","title":"EurNet: Efficient Multi-Range Relational Modeling of Spatial Multi-Relational Data","created":"2022-11-23","cited_by_count":3,"area":null},{"id":"2301.03194","title":"Few-shot Semantic Segmentation with Support-induced Graph Convolutional Network","created":"2023-01-09","cited_by_count":3,"area":null},{"id":"2504.02440","title":"HGFormer: Topology-Aware Vision Transformer with HyperGraph Learning","created":"2025-04-03","cited_by_count":3,"area":null},{"id":"2511.10953","title":"Language-Guided Graph Representation Learning for Video Summarization","created":"2025-11-14","cited_by_count":3,"area":null},{"id":"2103.03510","title":"Variational Structured Attention Networks for Deep Visual Representation Learning","created":"2021-03-05","cited_by_count":2,"area":null},{"id":"2201.09169","title":"Rich Action-semantic Consistent Knowledge for Early Action Prediction","created":"2022-01-23","cited_by_count":2,"area":null},{"id":"2206.08481","title":"Orientation-guided Graph Convolutional Network for Bone Surface Segmentation","created":"2022-06-16","cited_by_count":2,"area":null},{"id":"2307.05616","title":"Image Reconstruction using Enhanced Vision Transformer","created":"2023-07-11","cited_by_count":2,"area":null},{"id":"2309.14057","title":"Weakly Supervised Semantic Segmentation by Knowledge Graph Inference","created":"2023-09-25","cited_by_count":2,"area":null},{"id":"2509.23373","title":"Graph Your Own Prompt","created":"2025-09-27","cited_by_count":2,"area":null},{"id":"2511.21439","title":"EvRainDrop: HyperGraph-guided Completion for Effective Frame and Event Stream Aggregation","created":"2025-11-26","cited_by_count":2,"area":null},{"id":"2104.01792","title":"Hierarchical Pyramid Representations for Semantic Segmentation","created":"2021-04-05","cited_by_count":1,"area":null},{"id":"2104.05971","title":"Learning Multi-modal Information for Robust Light Field Depth Estimation","created":"2021-04-13","cited_by_count":1,"area":null},{"id":"2104.11176","title":"Heterogeneous Grid Convolution for Adaptive, Efficient, and Controllable Computation","created":"2021-04-22","cited_by_count":1,"area":null},{"id":"2105.13531","title":"Empirical Study of Multi-Task Hourglass Model for Semantic Segmentation Task","created":"2021-05-28","cited_by_count":1,"area":null},{"id":"2106.01805","title":"Partial Graph Reasoning for Neural Network Regularization","created":"2021-06-03","cited_by_count":1,"area":null},{"id":"2108.03791","title":"Boundary-aware Graph Reasoning for Semantic Segmentation","created":"2021-08-09","cited_by_count":1,"area":null},{"id":"2108.03809","title":"PSGR: Pixel-wise Sparse Graph Reasoning for COVID-19 Pneumonia Segmentation in CT Images","created":"2021-08-09","cited_by_count":1,"area":null},{"id":"2110.13280","title":"A Variational Graph Autoencoder for Manipulation Action Recognition and Prediction","created":"2021-10-25","cited_by_count":1,"area":null},{"id":"2111.07370","title":"Co-segmentation Inspired Attention Module for Video-based Computer Vision Tasks","created":"2021-11-14","cited_by_count":1,"area":null},{"id":"2209.13459","title":"EgoSpeed-Net: Forecasting Speed-Control in Driver Behavior from Egocentric Video Data","created":"2022-09-27","cited_by_count":1,"area":null},{"id":"2212.03338","title":"Framework-agnostic Semantically-aware Global Reasoning for Segmentation","created":"2022-12-06","cited_by_count":1,"area":null},{"id":"2304.02982","title":"Spritz-PS: Validation of Synthetic Face Images Using a Large Dataset of Printed Documents","created":"2023-04-06","cited_by_count":1,"area":null},{"id":"2305.02673","title":"Modelling Spatio-Temporal Interactions For Compositional Action Recognition","created":"2023-05-04","cited_by_count":1,"area":null},{"id":"2308.09897","title":"Spatial-Temporal Alignment Network for Action Recognition","created":"2023-08-19","cited_by_count":1,"area":null},{"id":"2403.11122","title":"LERENet: Eliminating Intra-class Differences for Metal Surface Defect Few-shot Semantic Segmentation","created":"2024-03-17","cited_by_count":1,"area":null},{"id":"2406.12944","title":"Semantic Graph Consistency: Going Beyond Patches for Regularizing Self-Supervised Vision Transformers","created":"2024-06-18","cited_by_count":1,"area":null},{"id":"2507.16119","title":"Universal Wavelet Units in 3D Retinal Layer Segmentation","created":"2025-07-22","cited_by_count":1,"area":null},{"id":"2102.07997","title":"A2-FPN for Semantic Segmentation of Fine-Resolution Remotely Sensed Images","created":"2021-02-16","cited_by_count":0,"area":null}],"next_cursor":"100"}