{"list":"other","total":58,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"2112.01527","title":"Masked-attention Mask Transformer for Universal Image Segmentation","created":"2021-12-02","cited_by_count":2351},{"id":"1707.01083","title":"ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices","created":"2017-07-04","cited_by_count":1200},{"id":"1511.07122","title":"Multi-Scale Context Aggregation by Dilated Convolutions","created":"2015-11-23","cited_by_count":1133},{"id":"1511.02283","title":"Generation and Comprehension of Unambiguous Object Descriptions","created":"2015-11-07","cited_by_count":904},{"id":"2308.00692","title":"LISA: Reasoning Segmentation via Large Language Model","created":"2023-08-01","cited_by_count":776},{"id":"2102.04906","title":"Dynamic Neural Networks: A Survey","created":"2021-02-09","cited_by_count":408},{"id":"1905.04804","title":"Video Instance Segmentation","created":"2019-05-12","cited_by_count":393},{"id":"2112.02244","title":"LAVT: Language-Aware Vision Transformer for Referring Image Segmentation","created":"2021-12-04","cited_by_count":348},{"id":"2303.02153","title":"Unleashing Text-to-Image Diffusion Models for Visual Perception","created":"2023-03-03","cited_by_count":269},{"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":"2308.08544","title":"MeViS: A Large-scale Benchmark for Video Segmentation with Motion Expressions","created":"2023-08-16","cited_by_count":228},{"id":"2312.02228","title":"PixelLM: Pixel Reasoning with Large Multimodal Model","created":"2023-12-04","cited_by_count":222},{"id":"2201.00487","title":"Language as Queries for Referring Video Object Segmentation","created":"2022-01-03","cited_by_count":182},{"id":"2306.16269","title":"RSPrompter: Learning to Prompt for Remote Sensing Instance Segmentation based on Visual Foundation Model","created":"2023-06-28","cited_by_count":181},{"id":"1803.08006","title":"Video Object Segmentation with Language Referring Expressions","created":"2018-03-21","cited_by_count":162},{"id":"2111.14821","title":"End-to-End Referring Video Object Segmentation with Multimodal Transformers","created":"2021-11-29","cited_by_count":135},{"id":"2210.15871","title":"VLT: Vision-Language Transformer and Query Generation for Referring Segmentation","created":"2022-10-28","cited_by_count":111},{"id":"2309.04379","title":"Language Prompt for Autonomous Driving","created":"2023-09-08","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":"2106.03299","title":"Video Instance Segmentation using Inter-Frame Communication Transformers","created":"2021-06-07","cited_by_count":105},{"id":"2105.07175","title":"Cross-Modal Progressive Comprehension for Referring Segmentation","created":"2021-05-15","cited_by_count":102},{"id":"2112.08275","title":"SeqFormer: Sequential Transformer for Video Instance Segmentation","created":"2021-12-15","cited_by_count":98},{"id":"2207.10661","title":"In Defense of Online Models for Video Instance Segmentation","created":"2022-07-21","cited_by_count":97},{"id":"2206.04403","title":"VITA: Video Instance Segmentation via Object Token Association","created":"2022-06-09","cited_by_count":94},{"id":"2208.02245","title":"MinVIS: A Minimal Video Instance Segmentation Framework without Video-based Training","created":"2022-08-03","cited_by_count":94},{"id":"2303.03366","title":"Referring Multi-Object Tracking","created":"2023-03-06","cited_by_count":93},{"id":"2104.05970","title":"Crossover Learning for Fast Online Video Instance Segmentation","created":"2021-04-13","cited_by_count":83},{"id":"2306.03413","title":"DVIS: Decoupled Video Instance Segmentation Framework","created":"2023-06-06","cited_by_count":77},{"id":"2307.09356","title":"OnlineRefer: A Simple Online Baseline for Referring Video Object Segmentation","created":"2023-07-18","cited_by_count":62},{"id":"1804.03287","title":"Understanding Humans in Crowded Scenes: Deep Nested Adversarial Learning and A New Benchmark for Multi-Human Parsing","created":"2018-04-10","cited_by_count":60},{"id":"2305.17011","title":"SOC: Semantic-Assisted Object Cluster for Referring Video Object Segmentation","created":"2023-05-26","cited_by_count":57},{"id":"2305.16318","title":"Referred by Multi-Modality: A Unified Temporal Transformer for Video Object Segmentation","created":"2023-05-25","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":"1909.13245","title":"Spatiotemporal Co-attention Recurrent Neural Networks for Human-Skeleton Motion Prediction","created":"2019-09-29","cited_by_count":47},{"id":"2312.13305","title":"DVIS++: Improved Decoupled Framework for Universal Video Segmentation","created":"2023-12-20","cited_by_count":46},{"id":"2312.08366","title":"See, Say, and Segment: Teaching LMMs to Overcome False Premises","created":"2023-12-13","cited_by_count":41},{"id":"1811.00270","title":"Hierarchical Long Short-Term Concurrent Memory for Human Interaction Recognition","created":"2018-11-01","cited_by_count":36},{"id":"2406.05821","title":"F-LMM: Grounding Frozen Large Multimodal Models","created":"2024-06-09","cited_by_count":34},{"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":"2312.15715","title":"UniRef++: Segment Every Reference Object in Spatial and Temporal Spaces","created":"2023-12-25","cited_by_count":22},{"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":"2311.18835","title":"InstructSeq: Unifying Vision Tasks with Instruction-conditioned Multi-modal Sequence Generation","created":"2023-11-30","cited_by_count":14},{"id":"2403.19407","title":"Temporally Consistent Referring Video Object Segmentation with Hybrid Memory","created":"2024-03-28","cited_by_count":14},{"id":"2202.03747","title":"STC: Spatio-Temporal Contrastive Learning for Video Instance Segmentation","created":"2022-02-08","cited_by_count":13},{"id":"2403.07564","title":"RSBuilding: Towards General Remote Sensing Image Building Extraction and Change Detection with Foundation Model","created":"2024-03-12","cited_by_count":12},{"id":"2202.11981","title":"Fully Self-Supervised Learning for Semantic Segmentation","created":"2022-02-24","cited_by_count":11},{"id":"2212.07592","title":"Solve the Puzzle of Instance Segmentation in Videos: A Weakly Supervised Framework with Spatio-Temporal Collaboration","created":"2022-12-15","cited_by_count":11},{"id":"2309.13857","title":"Adversarial Attacks on Video Object Segmentation with Hard Region Discovery","created":"2023-09-25","cited_by_count":9},{"id":"2408.06747","title":"ReCLIP++: Learn to Rectify the Bias of CLIP for Unsupervised Semantic Segmentation","created":"2024-08-13","cited_by_count":8},{"id":"1705.07206","title":"Multiple-Human Parsing in the Wild","created":"2017-05-19","cited_by_count":6},{"id":"2304.11609","title":"PiClick: Picking the desired mask from multiple candidates in click-based interactive segmentation","created":"2023-04-23","cited_by_count":4}],"next_cursor":null}