{"list":"other","total":71,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1612.03144","title":"Feature Pyramid Networks for Object Detection","created":"2016-12-09","cited_by_count":5036},{"id":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"1802.02611","title":"Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation","created":"2018-02-07","cited_by_count":3223},{"id":"1807.06521","title":"CBAM: Convolutional Block Attention Module","created":"2018-07-17","cited_by_count":2477},{"id":"1902.09630","title":"Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression","created":"2019-02-25","cited_by_count":1368},{"id":"2106.13230","title":"Video Swin Transformer","created":"2021-06-24","cited_by_count":1091},{"id":"1608.00272","title":"Modeling Context in Referring Expressions","created":"2016-07-31","cited_by_count":1063},{"id":"1704.00675","title":"The 2017 DAVIS Challenge on Video Object Segmentation","created":"2017-04-03","cited_by_count":957},{"id":"1511.02283","title":"Generation and Comprehension of Unambiguous Object Descriptions","created":"2015-11-07","cited_by_count":904},{"id":"2104.12763","title":"MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding","created":"2021-04-26","cited_by_count":819},{"id":"2011.14503","title":"End-to-End Video Instance Segmentation with Transformers","created":"2020-11-30","cited_by_count":443},{"id":"2207.07115","title":"XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model","created":"2022-07-14","cited_by_count":439},{"id":"1904.00607","title":"Video Object Segmentation using Space-Time Memory Networks","created":"2019-04-01","cited_by_count":438},{"id":"2112.02244","title":"LAVT: Language-Aware Vision Transformer for Referring Image Segmentation","created":"2021-12-04","cited_by_count":348},{"id":"2003.05664","title":"Conditional Convolutions for Instance Segmentation","created":"2020-03-12","cited_by_count":314},{"id":"1904.04745","title":"Cross-Modal Self-Attention Network for Referring Image Segmentation","created":"2019-04-09","cited_by_count":263},{"id":"1603.06180","title":"Segmentation from Natural Language Expressions","created":"2016-03-20","cited_by_count":257},{"id":"1611.05198","title":"One-Shot Video Object Segmentation","created":"2016-11-16","cited_by_count":235},{"id":"2308.08544","title":"MeViS: A Large-scale Benchmark for Video Segmentation with Motion Expressions","created":"2023-08-16","cited_by_count":228},{"id":"2106.02638","title":"Associating Objects with Transformers for Video Object Segmentation","created":"2021-06-04","cited_by_count":226},{"id":"2106.05210","title":"Rethinking Space-Time Networks with Improved Memory Coverage for Efficient Video Object Segmentation","created":"2021-06-09","cited_by_count":203},{"id":"2303.06674","title":"Universal Instance Perception as Object Discovery and Retrieval","created":"2023-03-12","cited_by_count":192},{"id":"1911.02855","title":"Dice Loss for Data-imbalanced NLP Tasks","created":"2019-11-07","cited_by_count":182},{"id":"2201.00487","title":"Language as Queries for Referring Video Object Segmentation","created":"2022-01-03","cited_by_count":182},{"id":"1902.09513","title":"FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation","created":"2019-02-25","cited_by_count":178},{"id":"2112.10764","title":"Mask2Former for Video Instance Segmentation","created":"2021-12-20","cited_by_count":171},{"id":"1803.08006","title":"Video Object Segmentation with Language Referring Expressions","created":"2018-03-21","cited_by_count":162},{"id":"1907.12347","title":"FSS-1000: A 1000-Class Dataset for Few-Shot Segmentation","created":"2019-07-29","cited_by_count":160},{"id":"1612.02646","title":"Learning Video Object Segmentation from Static Images","created":"2016-12-08","cited_by_count":151},{"id":"2210.09782","title":"Decoupling Features in Hierarchical Propagation for Video Object Segmentation","created":"2022-10-18","cited_by_count":148},{"id":"2003.08333","title":"Collaborative Video Object Segmentation by Foreground-Background Integration","created":"2020-03-18","cited_by_count":142},{"id":"2111.14821","title":"End-to-End Referring Video Object Segmentation with Multimodal Transformers","created":"2021-11-29","cited_by_count":135},{"id":"2103.07941","title":"Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion","created":"2021-03-14","cited_by_count":129},{"id":"2005.02551","title":"CascadePSP: Toward Class-Agnostic and Very High-Resolution Segmentation via Global and Local Refinement","created":"2020-05-06","cited_by_count":113},{"id":"2007.08270","title":"Kernelized Memory Network for Video Object Segmentation","created":"2020-07-16","cited_by_count":111},{"id":"2210.15871","title":"VLT: Vision-Language Transformer and Query Generation for Referring Segmentation","created":"2022-10-28","cited_by_count":111},{"id":"1803.07485","title":"Actor and Action Video Segmentation from a Sentence","created":"2018-03-20","cited_by_count":106},{"id":"2101.08833","title":"SSTVOS: Sparse Spatiotemporal Transformers for Video Object Segmentation","created":"2021-01-21","cited_by_count":106},{"id":"2105.07175","title":"Cross-Modal Progressive Comprehension for Referring Segmentation","created":"2021-05-15","cited_by_count":102},{"id":"2010.07958","title":"Video Object Segmentation with Adaptive Feature Bank and Uncertain-Region Refinement","created":"2020-10-15","cited_by_count":101},{"id":"1802.01218","title":"Efficient Video Object Segmentation via Network Modulation","created":"2018-02-04","cited_by_count":98},{"id":"1709.06031","title":"Video Object Segmentation Without Temporal Information","created":"2017-09-18","cited_by_count":93},{"id":"1908.07274","title":"Towards High-Resolution Salient Object Detection","created":"2019-08-20","cited_by_count":92},{"id":"1807.09190","title":"PReMVOS: Proposal-generation, Refinement and Merging for Video Object Segmentation","created":"2018-07-24","cited_by_count":81},{"id":"2104.04329","title":"Learning Position and Target Consistency for Memory-based Video Object Segmentation","created":"2021-04-09","cited_by_count":63},{"id":"2307.09356","title":"OnlineRefer: A Simple Online Baseline for Referring Video Object Segmentation","created":"2023-07-18","cited_by_count":62},{"id":"1908.06647","title":"RANet: Ranking Attention Network for Fast Video Object Segmentation","created":"2019-08-19","cited_by_count":60},{"id":"1806.02323","title":"Fast and Accurate Online Video Object Segmentation via Tracking Parts","created":"2018-06-06","cited_by_count":57},{"id":"2305.17011","title":"SOC: Semantic-Assisted Object Cluster for Referring Video Object Segmentation","created":"2023-05-26","cited_by_count":57},{"id":"2004.07193","title":"A Transductive Approach for Video Object Segmentation","created":"2020-04-15","cited_by_count":55},{"id":"2003.00482","title":"State-Aware Tracker for Real-Time Video Object Segmentation","created":"2020-03-01","cited_by_count":54},{"id":"2206.03789","title":"Language-Bridged Spatial-Temporal Interaction for Referring Video Object Segmentation","created":"2022-06-08","cited_by_count":50},{"id":"2207.01203","title":"Towards Robust Referring Video Object Segmentation with Cyclic Relational Consensus","created":"2022-07-04","cited_by_count":50},{"id":"2307.13537","title":"Spectrum-guided Multi-granularity Referring Video Object Segmentation","created":"2023-07-25","cited_by_count":48},{"id":"2106.01061","title":"Rethinking Cross-modal Interaction from a Top-down Perspective for Referring Video Object Segmentation","created":"2021-06-02","cited_by_count":42},{"id":"2112.02853","title":"Reliable Propagation-Correction Modulation for Video Object Segmentation","created":"2021-12-06","cited_by_count":36},{"id":"2012.01866","title":"Make One-Shot Video Object Segmentation Efficient Again","created":"2020-12-03","cited_by_count":30},{"id":"1910.00132","title":"CapsuleVOS: Semi-Supervised Video Object Segmentation Using Capsule Routing","created":"2019-09-30","cited_by_count":29},{"id":"2207.12622","title":"Multi-Attention Network for Compressed Video Referring Object Segmentation","created":"2022-07-26","cited_by_count":28},{"id":"2309.03473","title":"Temporal Collection and Distribution for Referring Video Object Segmentation","created":"2023-09-07","cited_by_count":27},{"id":"2103.10702","title":"ClawCraneNet: Leveraging Object-level Relation for Text-based Video Segmentation","created":"2021-03-19","cited_by_count":21},{"id":"1904.08141","title":"MHP-VOS: Multiple Hypotheses Propagation for Video Object Segmentation","created":"2019-04-17","cited_by_count":20},{"id":"2207.10258","title":"Region Aware Video Object Segmentation with Deep Motion Modeling","created":"2022-07-21","cited_by_count":19},{"id":"2204.02547","title":"Modeling Motion with Multi-Modal Features for Text-Based Video Segmentation","created":"2022-04-06","cited_by_count":18},{"id":"2212.10278","title":"Fully and Weakly Supervised Referring Expression Segmentation with End-to-End Learning","created":"2022-12-17","cited_by_count":14},{"id":"2108.00399","title":"Object-to-Scene: Learning to Transfer Object Knowledge to Indoor Scene Recognition","created":"2021-08-01","cited_by_count":12},{"id":"2107.12569","title":"Self-Supervised Video Object Segmentation by Motion-Aware Mask Propagation","created":"2021-07-27","cited_by_count":11}],"next_cursor":null}