{"list":"other","total":60,"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":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"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":"1805.04687","title":"BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning","created":"2018-05-12","cited_by_count":1288},{"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":"2110.06864","title":"ByteTrack: Multi-Object Tracking by Associating Every Detection Box","created":"2021-10-13","cited_by_count":823},{"id":"2104.12763","title":"MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding","created":"2021-04-26","cited_by_count":819},{"id":"1911.02620","title":"Argoverse: 3D Tracking and Forecasting with Rich Maps","created":"2019-11-06","cited_by_count":732},{"id":"1609.01775","title":"Performance Measures and a Data Set for Multi-Target, Multi-Camera Tracking","created":"2016-09-06","cited_by_count":692},{"id":"2009.07736","title":"HOTA: A Higher Order Metric for Evaluating Multi-Object Tracking","created":"2020-09-16","cited_by_count":552},{"id":"1604.01753","title":"Hollywood in Homes: Crowdsourcing Data Collection for Activity Understanding","created":"2016-04-06","cited_by_count":537},{"id":"1603.00831","title":"MOT16: A Benchmark for Multi-Object Tracking","created":"2016-03-02","cited_by_count":532},{"id":"2101.02702","title":"TrackFormer: Multi-Object Tracking with Transformers","created":"2021-01-07","cited_by_count":518},{"id":"2004.01177","title":"Tracking Objects as Points","created":"2020-04-02","cited_by_count":483},{"id":"1810.11981","title":"GOT-10k: A Large High-Diversity Benchmark for Generic Object Tracking in the Wild","created":"2018-10-29","cited_by_count":475},{"id":"1705.08421","title":"AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actions","created":"2017-05-23","cited_by_count":449},{"id":"2011.14503","title":"End-to-End Video Instance Segmentation with Transformers","created":"2020-11-30","cited_by_count":443},{"id":"1809.07845","title":"LaSOT: A High-quality Benchmark for Large-scale Single Object Tracking","created":"2018-09-20","cited_by_count":429},{"id":"2011.10678","title":"Open-Vocabulary Object Detection Using Captions","created":"2020-11-20","cited_by_count":427},{"id":"1905.04804","title":"Video Instance Segmentation","created":"2019-05-12","cited_by_count":393},{"id":"1809.03327","title":"YouTube-VOS: A Large-Scale Video Object Segmentation Benchmark","created":"2018-09-06","cited_by_count":383},{"id":"2105.03247","title":"MOTR: End-to-End Multiple-Object Tracking with Transformer","created":"2021-05-07","cited_by_count":381},{"id":"2012.15460","title":"TransTrack: Multiple Object Tracking with Transformer","created":"2020-12-31","cited_by_count":371},{"id":"2003.09003","title":"MOT20: A benchmark for multi object tracking in crowded scenes","created":"2020-03-19","cited_by_count":357},{"id":"1803.10794","title":"TrackingNet: A Large-Scale Dataset and Benchmark for Object Tracking in the Wild","created":"2018-03-28","cited_by_count":343},{"id":"2206.14651","title":"BoT-SORT: Robust Associations Multi-Pedestrian Tracking","created":"2022-06-29","cited_by_count":320},{"id":"2006.06664","title":"Quasi-Dense Similarity Learning for Multiple Object Tracking","created":"2020-06-11","cited_by_count":220},{"id":"1803.08006","title":"Video Object Segmentation with Language Referring Expressions","created":"2018-03-21","cited_by_count":162},{"id":"2103.08808","title":"Track to Detect and Segment: An Online Multi-Object Tracker","created":"2021-03-16","cited_by_count":156},{"id":"2102.01558","title":"Occluded Video Instance Segmentation: A Benchmark","created":"2021-02-02","cited_by_count":154},{"id":"2005.10356","title":"TAO: A Large-Scale Benchmark for Tracking Any Object","created":"2020-05-20","cited_by_count":147},{"id":"1703.05884","title":"Need for Speed: A Benchmark for Higher Frame Rate Object Tracking","created":"2017-03-17","cited_by_count":137},{"id":"2103.16746","title":"Towards More Flexible and Accurate Object Tracking with Natural Language: Algorithms and Benchmark","created":"2021-03-31","cited_by_count":126},{"id":"2212.00280","title":"GRiT: A Generative Region-to-text Transformer for Object Understanding","created":"2022-12-01","cited_by_count":121},{"id":"2007.14557","title":"Chained-Tracker: Chaining Paired Attentive Regression Results for End-to-End Joint Multiple-Object Detection and Tracking","created":"2020-07-29","cited_by_count":115},{"id":"1503.01313","title":"A Novel Performance Evaluation Methodology for Single-Target Trackers","created":"2015-03-04","cited_by_count":113},{"id":"1702.00824","title":"YouTube-BoundingBoxes: A Large High-Precision Human-Annotated Data Set for Object Detection in Video","created":"2017-02-02","cited_by_count":109},{"id":"2203.16434","title":"TubeDETR: Spatio-Temporal Video Grounding with Transformers","created":"2022-03-30","cited_by_count":98},{"id":"2303.03366","title":"Referring Multi-Object Tracking","created":"2023-03-06","cited_by_count":93},{"id":"1803.09502","title":"Long-term Tracking in the Wild: A Benchmark","created":"2018-03-26","cited_by_count":55},{"id":"2304.08408","title":"OVTrack: Open-Vocabulary Multiple Object Tracking","created":"2023-04-17","cited_by_count":53},{"id":"2104.11221","title":"Opening up Open-World Tracking","created":"2021-04-22","cited_by_count":50},{"id":"2104.00743","title":"Towards General Purpose Vision Systems","created":"2021-04-01","cited_by_count":46},{"id":"2207.12978","title":"Tracking Every Thing in the Wild","created":"2022-07-26","cited_by_count":44},{"id":"1912.06316","title":"Grounding-Tracking-Integration","created":"2019-12-13","cited_by_count":32},{"id":"2106.06856","title":"DyGLIP: A Dynamic Graph Model with Link Prediction for Accurate Multi-Camera Multiple Object Tracking","created":"2021-06-12","cited_by_count":31},{"id":"2112.00974","title":"Consensus Graph Representation Learning for Better Grounded Image Captioning","created":"2021-12-02","cited_by_count":28},{"id":"1802.01433","title":"Interactive Grounded Language Acquisition and Generalization in a 2D World","created":"2018-01-31","cited_by_count":21},{"id":"2204.09151","title":"Multi-Camera Multiple 3D Object Tracking on the Move for Autonomous Vehicles","created":"2022-04-19","cited_by_count":20},{"id":"2206.03431","title":"Self-supervised Domain Adaptation in Crowd Counting","created":"2022-06-07","cited_by_count":11},{"id":"2101.06545","title":"VideoClick: Video Object Segmentation with a Single Click","created":"2021-01-16","cited_by_count":8},{"id":"2207.04551","title":"Depth Perspective-aware Multiple Object Tracking","created":"2022-07-10","cited_by_count":8},{"id":"2211.09663","title":"Multi-Camera Multi-Object Tracking on the Move via Single-Stage Global Association Approach","created":"2022-11-17","cited_by_count":7},{"id":"2210.16431","title":"DiMBERT: Learning Vision-Language Grounded Representations with Disentangled Multimodal-Attention","created":"2022-10-28","cited_by_count":4}],"next_cursor":null}