{"list":"other","total":62,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"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":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673},{"id":"1504.08083","title":"Fast R-CNN","created":"2015-04-30","cited_by_count":2933},{"id":"1909.11942","title":"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations","created":"2019-09-26","cited_by_count":2790},{"id":"1602.07332","title":"Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations","created":"2016-02-23","cited_by_count":2656},{"id":"1807.06521","title":"CBAM: Convolutional Block Attention Module","created":"2018-07-17","cited_by_count":2477},{"id":"2009.14794","title":"Rethinking Attention with Performers","created":"2020-09-30","cited_by_count":1601},{"id":"1505.04870","title":"Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models","created":"2015-05-19","cited_by_count":1362},{"id":"1705.07115","title":"Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics","created":"2017-05-19","cited_by_count":1358},{"id":"2107.08430","title":"YOLOX: Exceeding YOLO Series in 2021","created":"2021-07-18","cited_by_count":1071},{"id":"1608.00272","title":"Modeling Context in Referring Expressions","created":"2016-07-31","cited_by_count":1063},{"id":"1707.03237","title":"Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentations","created":"2017-07-11","cited_by_count":620},{"id":"1911.08287","title":"Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression","created":"2019-11-19","cited_by_count":459},{"id":"1801.08186","title":"MAttNet: Modular Attention Network for Referring Expression Comprehension","created":"2018-01-24","cited_by_count":431},{"id":"2006.04388","title":"Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection","created":"2020-06-08","cited_by_count":409},{"id":"2112.02244","title":"LAVT: Language-Aware Vision Transformer for Referring Image Segmentation","created":"2021-12-04","cited_by_count":348},{"id":"2209.02976","title":"YOLOv6: A Single-Stage Object Detection Framework for Industrial Applications","created":"2022-09-07","cited_by_count":275},{"id":"2104.08541","title":"TransVG: End-to-End Visual Grounding with Transformers","created":"2021-04-17","cited_by_count":271},{"id":"2306.00968","title":"GRES: Generalized Referring Expression Segmentation","created":"2023-06-01","cited_by_count":254},{"id":"2003.08813","title":"Multi-task Collaborative Network for Joint Referring Expression Comprehension and Segmentation","created":"2020-03-19","cited_by_count":204},{"id":"1908.06354","title":"A Fast and Accurate One-Stage Approach to Visual Grounding","created":"2019-08-18","cited_by_count":195},{"id":"2303.14189","title":"FastViT: A Fast Hybrid Vision Transformer using Structural Reparameterization","created":"2023-03-24","cited_by_count":162},{"id":"2106.03089","title":"Referring Transformer: A One-step Approach to Multi-task Visual Grounding","created":"2021-06-06","cited_by_count":143},{"id":"1909.10838","title":"Talk2Car: Taking Control of Your Self-Driving Car","created":"2019-09-24","cited_by_count":142},{"id":"1812.03299","title":"Learning to Assemble Neural Module Tree Networks for Visual Grounding","created":"2018-12-08","cited_by_count":140},{"id":"2203.16265","title":"SeqTR: A Simple yet Universal Network for Visual Grounding","created":"2022-03-30","cited_by_count":139},{"id":"2204.08721","title":"Multimodal Token Fusion for Vision Transformers","created":"2022-04-19","cited_by_count":136},{"id":"2210.12634","title":"RSVG: Exploring Data and Models for Visual Grounding on Remote Sensing Data","created":"2022-10-23","cited_by_count":123},{"id":"2303.01480","title":"Delivering Arbitrary-Modal Semantic Segmentation","created":"2023-03-02","cited_by_count":117},{"id":"1909.08164","title":"Dynamic Graph Attention for Referring Expression Comprehension","created":"2019-09-18","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":"1812.04794","title":"Neighbourhood Watch: Referring Expression Comprehension via Language-guided Graph Attention Networks","created":"2018-12-12","cited_by_count":102},{"id":"1906.01784","title":"Learning to Compose and Reason with Language Tree Structures for Visual Grounding","created":"2019-06-05","cited_by_count":98},{"id":"2303.03366","title":"Referring Multi-Object Tracking","created":"2023-03-06","cited_by_count":93},{"id":"2007.09554","title":"Referring Expression Comprehension: A Survey of Methods and Datasets","created":"2020-07-19","cited_by_count":79},{"id":"2105.01922","title":"SeaDronesSee: A Maritime Benchmark for Detecting Humans in Open Water","created":"2021-05-05","cited_by_count":61},{"id":"2304.10410","title":"Radar-Camera Fusion for Object Detection and Semantic Segmentation in Autonomous Driving: A Comprehensive Review","created":"2023-04-20","cited_by_count":58},{"id":"1812.03426","title":"Real-Time Referring Expression Comprehension by Single-Stage Grounding Network","created":"2018-12-09","cited_by_count":56},{"id":"2102.00240","title":"SA-Net: Shuffle Attention for Deep Convolutional Neural Networks","created":"2021-01-30","cited_by_count":54},{"id":"2309.01017","title":"Contrastive Grouping with Transformer for Referring Image Segmentation","created":"2023-09-02","cited_by_count":54},{"id":"2003.00403","title":"Cops-Ref: A new Dataset and Task on Compositional Referring Expression Comprehension","created":"2020-03-01","cited_by_count":50},{"id":"2105.04281","title":"Visual Grounding with Transformers","created":"2021-05-10","cited_by_count":42},{"id":"2307.06505","title":"WaterScenes: A Multi-Task 4D Radar-Camera Fusion Dataset and Benchmarks for Autonomous Driving on Water Surfaces","created":"2023-07-13","cited_by_count":35},{"id":"2204.02681","title":"PP-LiteSeg: A Superior Real-Time Semantic Segmentation Model","created":"2022-04-06","cited_by_count":33},{"id":"2104.13225","title":"Visually grounded models of spoken language: A survey of datasets, architectures and evaluation techniques","created":"2021-04-27","cited_by_count":32},{"id":"2105.02359","title":"MODS -- A USV-oriented object detection and obstacle segmentation benchmark","created":"2021-05-05","cited_by_count":27},{"id":"1503.01918","title":"Fast image-based obstacle detection from unmanned surface vehicles","created":"2015-03-06","cited_by_count":23},{"id":"2312.04861","title":"Exploring Radar Data Representations in Autonomous Driving: A Comprehensive Review","created":"2023-12-08","cited_by_count":22},{"id":"1802.07956","title":"Stereo obstacle detection for unmanned surface vehicles by IMU-assisted semantic segmentation","created":"2018-02-22","cited_by_count":21},{"id":"2103.05383","title":"Are We Ready for Unmanned Surface Vehicles in Inland Waterways? The USVInland Multisensor Dataset and Benchmark","created":"2021-03-09","cited_by_count":21},{"id":"2308.09618","title":"LaRS: A Diverse Panoptic Maritime Obstacle Detection Dataset and Benchmark","created":"2023-08-18","cited_by_count":19},{"id":"2307.07102","title":"Achelous: A Fast Unified Water-surface Panoptic Perception Framework based on Fusion of Monocular Camera and 4D mmWave Radar","created":"2023-07-14","cited_by_count":16},{"id":"2302.11283","title":"Asynchronous Trajectory Matching-Based Multimodal Maritime Data Fusion for Vessel Traffic Surveillance in Inland Waterways","created":"2023-02-22","cited_by_count":13},{"id":"2308.10287","title":"ASY-VRNet: Waterway Panoptic Driving Perception Model based on Asymmetric Fair Fusion of Vision and 4D mmWave Radar","created":"2023-08-20","cited_by_count":11},{"id":"2006.01629","title":"Give Me Something to Eat: Referring Expression Comprehension with Commonsense Knowledge","created":"2020-06-02","cited_by_count":9},{"id":"2301.06719","title":"FemtoDet: An Object Detection Baseline for Energy Versus Performance Tradeoffs","created":"2023-01-17","cited_by_count":5},{"id":"2303.05555","title":"Pohang Canal Dataset: A Multimodal Maritime Dataset for Autonomous Navigation in Restricted Waters","created":"2023-03-09","cited_by_count":5},{"id":"2312.08851","title":"Achelous++: Power-Oriented Water-Surface Panoptic Perception Framework on Edge Devices based on Vision-Radar Fusion and Pruning of Heterogeneous Modalities","created":"2023-12-14","cited_by_count":4}],"next_cursor":null}