{"list":"other","total":117,"rows":[{"id":"1411.4038","title":"Fully Convolutional Networks for Semantic Segmentation","created":"2014-11-14","cited_by_count":4859},{"id":"1409.4842","title":"Going Deeper with Convolutions","created":"2014-09-17","cited_by_count":4241},{"id":"1612.01105","title":"Pyramid Scene Parsing Network","created":"2016-12-04","cited_by_count":2479},{"id":"1711.07971","title":"Non-local Neural Networks","created":"2017-11-21","cited_by_count":2293},{"id":"2103.13413","title":"Vision Transformers for Dense Prediction","created":"2021-03-24","cited_by_count":1803},{"id":"2009.14794","title":"Rethinking Attention with Performers","created":"2020-09-30","cited_by_count":1601},{"id":"1807.10165","title":"UNet++: A Nested U-Net Architecture for Medical Image Segmentation","created":"2018-07-18","cited_by_count":1525},{"id":"1809.02983","title":"Dual Attention Network for Scene Segmentation","created":"2018-09-09","cited_by_count":1003},{"id":"2106.03106","title":"Uformer: A General U-Shaped Transformer for Image Restoration","created":"2021-06-06","cited_by_count":866},{"id":"2105.05633","title":"Segmenter: Transformer for Semantic Segmentation","created":"2021-05-12","cited_by_count":855},{"id":"2107.00652","title":"CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windows","created":"2021-07-01","cited_by_count":527},{"id":"2204.12484","title":"ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation","created":"2022-04-26","cited_by_count":456},{"id":"2103.10455","title":"3D Human Pose Estimation with Spatial and Temporal Transformers","created":"2021-03-18","cited_by_count":272},{"id":"2106.03348","title":"ViTAE: Vision Transformer Advanced by Exploring Intrinsic Inductive Bias","created":"2021-06-07","cited_by_count":216},{"id":"2012.13392","title":"Deep Learning-Based Human Pose Estimation: A Survey","created":"2020-12-24","cited_by_count":207},{"id":"2201.09450","title":"UniFormer: Unifying Convolution and Self-attention for Visual Recognition","created":"2022-01-24","cited_by_count":206},{"id":"2212.03588","title":"ZegCLIP: Towards Adapting CLIP for Zero-shot Semantic Segmentation","created":"2022-12-07","cited_by_count":178},{"id":"2404.03384","title":"LongVLM: Efficient Long Video Understanding via Large Language Models","created":"2024-04-04","cited_by_count":147},{"id":"2212.00785","title":"Learning to Generate Text-grounded Mask for Open-world Semantic Segmentation from Only Image-Text Pairs","created":"2022-12-01","cited_by_count":130},{"id":"2107.04286","title":"Capturing, Reconstructing, and Simulating: the UrbanScene3D Dataset","created":"2021-07-09","cited_by_count":118},{"id":"2106.03650","title":"Shuffle Transformer: Rethinking Spatial Shuffle for Vision Transformer","created":"2021-06-07","cited_by_count":115},{"id":"2212.04994","title":"Open Vocabulary Semantic Segmentation with Patch Aligned Contrastive Learning","created":"2022-12-09","cited_by_count":115},{"id":"2201.10326","title":"ShapeFormer: Transformer-based Shape Completion via Sparse Representation","created":"2022-01-25","cited_by_count":106},{"id":"2210.05844","title":"SegViT: Semantic Segmentation with Plain Vision Transformers","created":"2022-10-12","cited_by_count":106},{"id":"1811.02565","title":"Point2Sequence: Learning the Shape Representation of 3D Point Clouds with an Attention-based Sequence to Sequence Network","created":"2018-11-06","cited_by_count":100},{"id":"2112.08275","title":"SeqFormer: Sequential Transformer for Video Instance Segmentation","created":"2021-12-15","cited_by_count":98},{"id":"2311.15537","title":"SED: A Simple Encoder-Decoder for Open-Vocabulary Semantic Segmentation","created":"2023-11-27","cited_by_count":97},{"id":"2011.12562","title":"Delving Deep into Label Smoothing","created":"2020-11-25","cited_by_count":94},{"id":"2006.15426","title":"Molecule Edit Graph Attention Network: Modeling Chemical Reactions as Sequences of Graph Edits","created":"2020-06-27","cited_by_count":88},{"id":"2103.10619","title":"Scalable Vision Transformers with Hierarchical Pooling","created":"2021-03-19","cited_by_count":84},{"id":"2106.12011","title":"P2T: Pyramid Pooling Transformer for Scene Understanding","created":"2021-06-22","cited_by_count":84},{"id":"2301.10222","title":"RangeViT: Towards Vision Transformers for 3D Semantic Segmentation in Autonomous Driving","created":"2023-01-24","cited_by_count":76},{"id":"2104.11896","title":"M3DeTR: Multi-representation, Multi-scale, Mutual-relation 3D Object Detection with Transformers","created":"2021-04-24","cited_by_count":74},{"id":"2303.08566","title":"Sensitivity-Aware Visual Parameter-Efficient Fine-Tuning","created":"2023-03-15","cited_by_count":74},{"id":"2203.05402","title":"Representation Compensation Networks for Continual Semantic Segmentation","created":"2022-03-10","cited_by_count":72},{"id":"2008.06614","title":"Object Detection with a Unified Label Space from Multiple Datasets","created":"2020-08-15","cited_by_count":65},{"id":"2012.13093","title":"EDN: Salient Object Detection via Extremely-Downsampled Network","created":"2020-12-24","cited_by_count":64},{"id":"2308.01045","title":"Dynamic Token Pruning in Plain Vision Transformers for Semantic Segmentation","created":"2023-08-02","cited_by_count":62},{"id":"2206.05683","title":"APT-36K: A Large-scale Benchmark for Animal Pose Estimation and Tracking","created":"2022-06-12","cited_by_count":56},{"id":"2105.14217","title":"Less is More: Pay Less Attention in Vision Transformers","created":"2021-05-29","cited_by_count":53},{"id":"1807.06708","title":"A Modulation Module for Multi-task Learning with Applications in Image Retrieval","created":"2018-07-17","cited_by_count":49},{"id":"2009.11042","title":"Few-shot Font Generation with Localized Style Representations and Factorization","created":"2020-09-23","cited_by_count":47},{"id":"2104.00887","title":"Multiple Heads are Better than One: Few-shot Font Generation with Multiple Localized Experts","created":"2021-04-02","cited_by_count":46},{"id":"2003.04676","title":"Deep Hough Transform for Semantic Line Detection","created":"2020-03-10","cited_by_count":44},{"id":"2005.10510","title":"Few-shot Compositional Font Generation with Dual Memory","created":"2020-05-21","cited_by_count":44},{"id":"2203.08485","title":"PointAttN: You Only Need Attention for Point Cloud Completion","created":"2022-03-16","cited_by_count":44},{"id":"2208.01924","title":"Per-Clip Video Object Segmentation","created":"2022-08-03","cited_by_count":40},{"id":"2302.01107","title":"A Survey on Efficient Training of Transformers","created":"2023-02-02","cited_by_count":39},{"id":"2209.07761","title":"Expansion and Shrinkage of Localization for Weakly-Supervised Semantic Segmentation","created":"2022-09-16","cited_by_count":37},{"id":"1901.01570","title":"Transductive Zero-Shot Learning with Visual Structure Constraint","created":"2019-01-06","cited_by_count":36},{"id":"2004.11563","title":"Deep Feature-preserving Normal Estimation for Point Cloud Filtering","created":"2020-04-24","cited_by_count":36},{"id":"2112.14000","title":"Pale Transformer: A General Vision Transformer Backbone with Pale-Shaped Attention","created":"2021-12-28","cited_by_count":36},{"id":"2112.00007","title":"Sound-Guided Semantic Image Manipulation","created":"2021-11-30","cited_by_count":35},{"id":"2204.09273","title":"Sound-Guided Semantic Video Generation","created":"2022-04-20","cited_by_count":35},{"id":"2406.09829","title":"Open-Vocabulary Semantic Segmentation with Image Embedding Balancing","created":"2024-06-14","cited_by_count":35},{"id":"2312.09788","title":"Collaborating Foundation Models for Domain Generalized Semantic Segmentation","created":"2023-12-15","cited_by_count":34},{"id":"2408.03178","title":"An Object is Worth 64x64 Pixels: Generating 3D Object via Image Diffusion","created":"2024-08-06","cited_by_count":34},{"id":"2108.05570","title":"LabOR: Labeling Only if Required for Domain Adaptive Semantic Segmentation","created":"2021-08-12","cited_by_count":33},{"id":"2301.12276","title":"ProtoSeg: Interpretable Semantic Segmentation with Prototypical Parts","created":"2023-01-28","cited_by_count":33},{"id":"2206.00566","title":"The Fully Convolutional Transformer for Medical Image Segmentation","created":"2022-06-01","cited_by_count":32},{"id":"2106.03180","title":"Vision Transformers with Hierarchical Attention","created":"2021-06-06","cited_by_count":31},{"id":"2005.12541","title":"Fine-Grained 3D Shape Classification with Hierarchical Part-View Attentions","created":"2020-05-26","cited_by_count":30},{"id":"2302.02057","title":"Semantic Diffusion Network for Semantic Segmentation","created":"2023-02-04","cited_by_count":30},{"id":"2106.15754","title":"Looking Outside the Window: Wide-Context Transformer for the Semantic Segmentation of High-Resolution Remote Sensing Images","created":"2021-06-29","cited_by_count":27},{"id":"2308.08162","title":"Interpretability Benchmark for Evaluating Spatial Misalignment of Prototypical Parts Explanations","created":"2023-08-16","cited_by_count":27},{"id":"2403.01482","title":"EAGLE: Eigen Aggregation Learning for Object-Centric Unsupervised Semantic Segmentation","created":"2024-03-03","cited_by_count":27},{"id":"2203.00828","title":"3DCTN: 3D Convolution-Transformer Network for Point Cloud Classification","created":"2022-03-02","cited_by_count":25},{"id":"2306.06289","title":"SegViTv2: Exploring Efficient and Continual Semantic Segmentation with Plain Vision Transformers","created":"2023-06-09","cited_by_count":25},{"id":"1902.03091","title":"FocusNet: An attention-based Fully Convolutional Network for Medical Image Segmentation","created":"2019-02-08","cited_by_count":24},{"id":"2106.04108","title":"Fully Transformer Networks for Semantic Image Segmentation","created":"2021-06-08","cited_by_count":24},{"id":"2110.04111","title":"Discover, Hallucinate, and Adapt: Open Compound Domain Adaptation for Semantic Segmentation","created":"2021-10-08","cited_by_count":24},{"id":"2111.11802","title":"Pruning Self-attentions into Convolutional Layers in Single Path","created":"2021-11-23","cited_by_count":24},{"id":"1911.12053","title":"Grapy-ML: Graph Pyramid Mutual Learning for Cross-dataset Human Parsing","created":"2019-11-27","cited_by_count":23},{"id":"2209.09004","title":"EcoFormer: Energy-Saving Attention with Linear Complexity","created":"2022-09-19","cited_by_count":21},{"id":"2303.11610","title":"Novel Class Discovery for 3D Point Cloud Semantic Segmentation","created":"2023-03-21","cited_by_count":21},{"id":"2308.11166","title":"Hierarchical Point-based Active Learning for Semi-supervised Point Cloud Semantic Segmentation","created":"2023-08-22","cited_by_count":21},{"id":"1908.07683","title":"Preserving Semantic and Temporal Consistency for Unpaired Video-to-Video Translation","created":"2019-08-21","cited_by_count":20},{"id":"2102.03026","title":"Instance and Panoptic Segmentation Using Conditional Convolutions","created":"2021-02-05","cited_by_count":19},{"id":"2105.07364","title":"BDANet: Multiscale Convolutional Neural Network with Cross-directional Attention for Building Damage Assessment from Satellite Images","created":"2021-05-16","cited_by_count":19},{"id":"2009.09197","title":"Weak-shot Fine-grained Classification via Similarity Transfer","created":"2020-09-19","cited_by_count":18},{"id":"2403.11184","title":"DuPL: Dual Student with Trustworthy Progressive Learning for Robust Weakly Supervised Semantic Segmentation","created":"2024-03-17","cited_by_count":17},{"id":"2503.00045","title":"Glad: A Streaming Scene Generator for Autonomous Driving","created":"2025-02-26","cited_by_count":17},{"id":"2503.06689","title":"DependEval: Benchmarking LLMs for Repository Dependency Understanding","created":"2025-03-09","cited_by_count":17},{"id":"2504.19189","title":"Sketch2Anim: Towards Transferring Sketch Storyboards into 3D Animation","created":"2025-04-27","cited_by_count":17},{"id":"2004.00222","title":"Video Anomaly Detection for Smart Surveillance","created":"2020-04-01","cited_by_count":16},{"id":"2204.01244","title":"Dynamic Focus-aware Positional Queries for Semantic Segmentation","created":"2022-04-04","cited_by_count":16},{"id":"2209.02556","title":"The Outcome of the 2022 Landslide4Sense Competition: Advanced Landslide Detection from Multi-Source Satellite Imagery","created":"2022-09-06","cited_by_count":15},{"id":"2209.07828","title":"Weakly Supervised Semantic Segmentation via Progressive Patch Learning","created":"2022-09-16","cited_by_count":15},{"id":"2306.08075","title":"BPKD: Boundary Privileged Knowledge Distillation For Semantic Segmentation","created":"2023-06-13","cited_by_count":15},{"id":"2406.11189","title":"Frozen CLIP: A Strong Backbone for Weakly Supervised Semantic Segmentation","created":"2024-06-17","cited_by_count":15},{"id":"2407.16696","title":"PartGLEE: A Foundation Model for Recognizing and Parsing Any Objects","created":"2024-07-23","cited_by_count":15},{"id":"2505.18142","title":"TokBench: Evaluating Your Visual Tokenizer before Visual Generation","created":"2025-05-23","cited_by_count":13},{"id":"2210.08066","title":"Optimizing Vision Transformers for Medical Image Segmentation","created":"2022-10-14","cited_by_count":12},{"id":"2310.05026","title":"Low-Resolution Self-Attention for Semantic Segmentation","created":"2023-10-08","cited_by_count":12},{"id":"2107.14428","title":"Dynamic Neural Representational Decoders for High-Resolution Semantic Segmentation","created":"2021-07-30","cited_by_count":11},{"id":"2110.14191","title":"Mixed Supervised Object Detection by Transferring Mask Prior and Semantic Similarity","created":"2021-10-27","cited_by_count":11},{"id":"2408.08093","title":"When Video Coding Meets Multimodal Large Language Models: A Unified Paradigm for Video Coding","created":"2024-08-15","cited_by_count":11},{"id":"2104.03427","title":"FatNet: A Feature-attentive Network for 3D Point Cloud Processing","created":"2021-04-07","cited_by_count":10},{"id":"2210.02270","title":"Weak-shot Semantic Segmentation via Dual Similarity Transfer","created":"2022-10-05","cited_by_count":10},{"id":"2406.10484","title":"Beyond Raw Videos: Understanding Edited Videos with Large Multimodal Model","created":"2024-06-15","cited_by_count":10}],"next_cursor":"100"}