{"list":"other","total":58,"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":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"2112.01527","title":"Masked-attention Mask Transformer for Universal Image Segmentation","created":"2021-12-02","cited_by_count":2351},{"id":"1606.04797","title":"V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation","created":"2016-06-15","cited_by_count":2292},{"id":"1908.07490","title":"LXMERT: Learning Cross-Modality Encoder Representations from Transformers","created":"2019-08-20","cited_by_count":1553},{"id":"1504.00325","title":"Microsoft COCO Captions: Data Collection and Evaluation Server","created":"2015-04-01","cited_by_count":1462},{"id":"2112.03857","title":"Grounded Language-Image Pre-training","created":"2021-12-07","cited_by_count":1156},{"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":"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":"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":"2201.12329","title":"DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETR","created":"2022-01-28","cited_by_count":573},{"id":"2009.07736","title":"HOTA: A Higher Order Metric for Evaluating Multi-Object Tracking","created":"2020-09-16","cited_by_count":552},{"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":"2004.01888","title":"FairMOT: On the Fairness of Detection and Re-Identification in Multiple Object Tracking","created":"2020-04-04","cited_by_count":490},{"id":"2004.01177","title":"Tracking Objects as Points","created":"2020-04-02","cited_by_count":483},{"id":"1801.08186","title":"MAttNet: Modular Attention Network for Referring Expression Comprehension","created":"2018-01-24","cited_by_count":431},{"id":"1905.04804","title":"Video Instance Segmentation","created":"2019-05-12","cited_by_count":393},{"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":"1909.12605","title":"Towards Real-Time Multi-Object Tracking","created":"2019-09-27","cited_by_count":311},{"id":"1608.00525","title":"Modeling Context Between Objects for Referring Expression Understanding","created":"2016-08-01","cited_by_count":251},{"id":"1902.03604","title":"MOTS: Multi-Object Tracking and Segmentation","created":"2019-02-10","cited_by_count":223},{"id":"2111.14690","title":"DanceTrack: Multi-Object Tracking in Uniform Appearance and Diverse Motion","created":"2021-11-29","cited_by_count":217},{"id":"1803.08006","title":"Video Object Segmentation with Language Referring Expressions","created":"2018-03-21","cited_by_count":162},{"id":"2211.09791","title":"MOTRv2: Bootstrapping End-to-End Multi-Object Tracking by Pretrained Object Detectors","created":"2022-11-17","cited_by_count":148},{"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":"1504.01942","title":"MOTChallenge 2015: Towards a Benchmark for Multi-Target Tracking","created":"2015-04-08","cited_by_count":133},{"id":"2203.16761","title":"MeMOT: Multi-Object Tracking with Memory","created":"2022-03-31","cited_by_count":114},{"id":"1803.07485","title":"Actor and Action Video Segmentation from a Sentence","created":"2018-03-20","cited_by_count":106},{"id":"1812.04794","title":"Neighbourhood Watch: Referring Expression Comprehension via Language-guided Graph Attention Networks","created":"2018-12-12","cited_by_count":102},{"id":"2010.12138","title":"Rethinking the competition between detection and ReID in Multi-Object Tracking","created":"2020-10-23","cited_by_count":101},{"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":"2007.09554","title":"Referring Expression Comprehension: A Survey of Methods and Datasets","created":"2020-07-19","cited_by_count":79},{"id":"2210.06984","title":"QDTrack: Quasi-Dense Similarity Learning for Appearance-Only Multiple Object Tracking","created":"2022-10-12","cited_by_count":61},{"id":"1902.10322","title":"Spatio-Temporal Dynamics and Semantic Attribute Enriched Visual Encoding for Video Captioning","created":"2019-02-27","cited_by_count":60},{"id":"1906.02549","title":"Weakly-Supervised Spatio-Temporally Grounding Natural Sentence in Video","created":"2019-06-06","cited_by_count":60},{"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":"2305.14298","title":"MOTRv3: Release-Fetch Supervision for End-to-End Multi-Object Tracking","created":"2023-05-23","cited_by_count":42},{"id":"1911.12148","title":"Towards Precise End-to-end Weakly Supervised Object Detection Network","created":"2019-11-27","cited_by_count":41},{"id":"1801.01582","title":"Object Referring in Videos with Language and Human Gaze","created":"2018-01-04","cited_by_count":40},{"id":"2312.16245","title":"iKUN: Speak to Trackers without Retraining","created":"2023-12-25","cited_by_count":32},{"id":"2011.10972","title":"Language-guided Navigation via Cross-Modal Grounding and Alternate Adversarial Learning","created":"2020-11-22","cited_by_count":22},{"id":"2305.12724","title":"Bridging the Gap Between End-to-end and Non-End-to-end Multi-Object Tracking","created":"2023-05-22","cited_by_count":20},{"id":"2306.02585","title":"MotionTrack: Learning Motion Predictor for Multiple Object Tracking","created":"2023-06-05","cited_by_count":20},{"id":"2212.01568","title":"Generalizing Multiple Object Tracking to Unseen Domains by Introducing Natural Language Representation","created":"2022-12-03","cited_by_count":17},{"id":"2110.06058","title":"Multi-Modal Interaction Graph Convolutional Network for Temporal Language Localization in Videos","created":"2021-10-12","cited_by_count":16},{"id":"2212.10278","title":"Fully and Weakly Supervised Referring Expression Segmentation with End-to-End Learning","created":"2022-12-17","cited_by_count":14}],"next_cursor":null}