{"list":"other","total":52,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1608.06993","title":"Densely Connected Convolutional Networks","created":"2016-08-25","cited_by_count":6720},{"id":"1411.4038","title":"Fully Convolutional Networks for Semantic Segmentation","created":"2014-11-14","cited_by_count":4859},{"id":"1506.02640","title":"You Only Look Once: Unified, Real-Time Object Detection","created":"2015-06-08","cited_by_count":4852},{"id":"1506.02142","title":"Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning","created":"2015-06-06","cited_by_count":4448},{"id":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"id":"1612.01474","title":"Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles","created":"2016-12-05","cited_by_count":3926},{"id":"1504.08083","title":"Fast R-CNN","created":"2015-04-30","cited_by_count":2933},{"id":"1703.04977","title":"What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?","created":"2017-03-15","cited_by_count":2352},{"id":"2112.01527","title":"Masked-attention Mask Transformer for Universal Image Segmentation","created":"2021-12-02","cited_by_count":2351},{"id":"2210.02303","title":"Imagen Video: High Definition Video Generation with Diffusion Models","created":"2022-10-05","cited_by_count":1778},{"id":"2209.14792","title":"Make-A-Video: Text-to-Video Generation without Text-Video Data","created":"2022-09-29","cited_by_count":1742},{"id":"1805.04687","title":"BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning","created":"2018-05-12","cited_by_count":1288},{"id":"1703.07402","title":"Simple Online and Realtime Tracking with a Deep Association Metric","created":"2017-03-21","cited_by_count":910},{"id":"1602.00763","title":"Simple Online and Realtime Tracking","created":"2016-02-02","cited_by_count":868},{"id":"2104.08860","title":"CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval","created":"2021-04-18","cited_by_count":651},{"id":"2109.13410","title":"KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3D","created":"2021-09-28","cited_by_count":575},{"id":"2004.01177","title":"Tracking Objects as Points","created":"2020-04-02","cited_by_count":483},{"id":"1903.05625","title":"Tracking without bells and whistles","created":"2019-03-13","cited_by_count":382},{"id":"2111.12417","title":"N\\\"UWA: Visual Synthesis Pre-training for Neural visUal World creAtion","created":"2021-11-24","cited_by_count":253},{"id":"1902.03604","title":"MOTS: Multi-Object Tracking and Segmentation","created":"2019-02-10","cited_by_count":223},{"id":"1912.07515","title":"Learning a Neural Solver for Multiple Object Tracking","created":"2019-12-16","cited_by_count":198},{"id":"2104.14812","title":"SegmentMeIfYouCan: A Benchmark for Anomaly Segmentation","created":"2021-04-30","cited_by_count":150},{"id":"2012.06575","title":"Entropy Maximization and Meta Classification for Out-Of-Distribution Detection in Semantic Segmentation","created":"2020-12-09","cited_by_count":133},{"id":"1912.04573","title":"Classifying, Segmenting, and Tracking Object Instances in Video with Mask Propagation","created":"2019-12-10","cited_by_count":125},{"id":"1511.04164","title":"Natural Language Object Retrieval","created":"2015-11-13","cited_by_count":124},{"id":"1609.04653","title":"Lost and Found: Detecting Small Road Hazards for Self-Driving Vehicles","created":"2016-09-15","cited_by_count":117},{"id":"1905.00737","title":"The 2019 DAVIS Challenge on VOS: Unsupervised Multi-Object Segmentation","created":"2019-05-02","cited_by_count":97},{"id":"1604.07866","title":"Learning by tracking: Siamese CNN for robust target association","created":"2016-04-26","cited_by_count":79},{"id":"2112.04446","title":"Everything at Once -- Multi-modal Fusion Transformer for Video Retrieval","created":"2021-12-08","cited_by_count":79},{"id":"1805.11327","title":"Lightweight Probabilistic Deep Networks","created":"2018-05-29","cited_by_count":77},{"id":"2107.11264","title":"Standardized Max Logits: A Simple yet Effective Approach for Identifying Unexpected Road Obstacles in Urban-Scene Segmentation","created":"2021-07-23","cited_by_count":77},{"id":"2203.07111","title":"Disentangled Representation Learning for Text-Video Retrieval","created":"2022-03-14","cited_by_count":77},{"id":"2012.00641","title":"A Decade Survey of Content Based Image Retrieval using Deep Learning","created":"2020-11-23","cited_by_count":72},{"id":"2101.11282","title":"Deep Learning for Instance Retrieval: A Survey","created":"2021-01-27","cited_by_count":70},{"id":"1604.02532","title":"T-CNN: Tubelets with Convolutional Neural Networks for Object Detection from Videos","created":"2016-04-09","cited_by_count":67},{"id":"2211.14293","title":"RbA: Segmenting Unknown Regions Rejected by All","created":"2022-11-25","cited_by_count":67},{"id":"1811.00648","title":"Prediction Error Meta Classification in Semantic Segmentation: Detection via Aggregated Dispersion Measures of Softmax Probabilities","created":"2018-11-01","cited_by_count":54},{"id":"2104.11221","title":"Opening up Open-World Tracking","created":"2021-04-22","cited_by_count":50},{"id":"2301.03407","title":"On Advantages of Mask-level Recognition for Outlier-aware Segmentation","created":"2023-01-09","cited_by_count":42},{"id":"2012.13633","title":"Detecting Road Obstacles by Erasing Them","created":"2020-12-25","cited_by_count":29},{"id":"2304.11928","title":"Survey on Unsupervised Domain Adaptation for Semantic Segmentation for Visual Perception in Automated Driving","created":"2023-04-24","cited_by_count":29},{"id":"1702.06355","title":"Object Detection in Videos with Tubelet Proposal Networks","created":"2017-02-21","cited_by_count":24},{"id":"1911.05075","title":"Time-Dynamic Estimates of the Reliability of Deep Semantic Segmentation Networks","created":"2019-11-12","cited_by_count":20},{"id":"2005.06831","title":"Detection and Retrieval of Out-of-Distribution Objects in Semantic Segmentation","created":"2020-05-14","cited_by_count":20},{"id":"2210.02074","title":"Two Video Data Sets for Tracking and Retrieval of Out of Distribution Objects","created":"2022-10-05","cited_by_count":19},{"id":"1904.04516","title":"Uncertainty Measures and Prediction Quality Rating for the Semantic Segmentation of Nested Multi Resolution Street Scene Images","created":"2019-04-09","cited_by_count":18},{"id":"2201.01073","title":"Towards Unsupervised Open World Semantic Segmentation","created":"2022-01-04","cited_by_count":13},{"id":"2305.00983","title":"Detecting Novelties with Empty Classes","created":"2023-04-30","cited_by_count":1}],"next_cursor":null}