{"list":"other","total":69,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"id":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"2203.03605","title":"DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection","created":"2022-03-07","cited_by_count":1319},{"id":"1406.2199","title":"Two-Stream Convolutional Networks for Action Recognition in Videos","created":"2014-06-09","cited_by_count":1068},{"id":"1608.00859","title":"Temporal Segment Networks: Towards Good Practices for Deep Action Recognition","created":"2016-08-02","cited_by_count":902},{"id":"2201.12329","title":"DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETR","created":"2022-01-28","cited_by_count":573},{"id":"1604.01753","title":"Hollywood in Homes: Crowdsourcing Data Collection for Activity Understanding","created":"2016-04-06","cited_by_count":537},{"id":"1704.00109","title":"Snapshot Ensembles: Train 1, get M for free","created":"2017-04-01","cited_by_count":350},{"id":"1907.09702","title":"BMN: Boundary-Matching Network for Temporal Action Proposal Generation","created":"2019-07-23","cited_by_count":329},{"id":"2202.07925","title":"ActionFormer: Localizing Moments of Actions with Transformers","created":"2022-02-16","cited_by_count":311},{"id":"1806.02964","title":"BSN: Boundary Sensitive Network for Temporal Action Proposal Generation","created":"2018-06-08","cited_by_count":271},{"id":"1704.06228","title":"Temporal Action Detection with Structured Segment Networks","created":"2017-04-20","cited_by_count":267},{"id":"1911.11462","title":"G-TAD: Sub-Graph Localization for Temporal Action Detection","created":"2019-11-26","cited_by_count":249},{"id":"1604.06182","title":"The THUMOS Challenge on Action Recognition for Videos \"in the Wild\"","created":"2016-04-21","cited_by_count":213},{"id":"1909.03252","title":"Graph Convolutional Networks for Temporal Action Localization","created":"2019-09-07","cited_by_count":208},{"id":"2007.10937","title":"MovieNet: A Holistic Dataset for Movie Understanding","created":"2020-07-21","cited_by_count":206},{"id":"1804.07667","title":"Rethinking the Faster R-CNN Architecture for Temporal Action Localization","created":"2018-04-20","cited_by_count":194},{"id":"1703.07814","title":"R-C3D: Region Convolutional 3D Network for Temporal Activity Detection","created":"2017-03-22","cited_by_count":161},{"id":"2103.13137","title":"Learning Salient Boundary Feature for Anchor-free Temporal Action Localization","created":"2021-03-24","cited_by_count":156},{"id":"2106.10271","title":"End-to-end Temporal Action Detection with Transformer","created":"2021-06-18","cited_by_count":151},{"id":"1804.04527","title":"SoccerNet: A Scalable Dataset for Action Spotting in Soccer Videos","created":"2018-04-12","cited_by_count":150},{"id":"2303.07347","title":"TriDet: Temporal Action Detection with Relative Boundary Modeling","created":"2023-03-13","cited_by_count":142},{"id":"2102.01894","title":"Relaxed Transformer Decoders for Direct Action Proposal Generation","created":"2021-02-03","cited_by_count":117},{"id":"2103.13141","title":"Temporal Context Aggregation Network for Temporal Action Proposal Refinement","created":"2021-03-24","cited_by_count":112},{"id":"2011.14598","title":"Video Self-Stitching Graph Network for Temporal Action Localization","created":"2020-11-30","cited_by_count":104},{"id":"2303.00440","title":"Extracting Motion and Appearance via Inter-Frame Attention for Efficient Video Frame Interpolation","created":"2023-03-01","cited_by_count":98},{"id":"1507.05738","title":"Every Moment Counts: Dense Detailed Labeling of Actions in Complex Videos","created":"2015-07-21","cited_by_count":93},{"id":"1911.04127","title":"Fast Learning of Temporal Action Proposal via Dense Boundary Generator","created":"2019-11-11","cited_by_count":89},{"id":"2008.01432","title":"Boundary Content Graph Neural Network for Temporal Action Proposal Generation","created":"2020-08-04","cited_by_count":88},{"id":"2105.07404","title":"MultiSports: A Multi-Person Video Dataset of Spatio-Temporally Localized Sports Actions","created":"2021-05-16","cited_by_count":84},{"id":"2203.16507","title":"AdaMixer: A Fast-Converging Query-Based Object Detector","created":"2022-03-30","cited_by_count":79},{"id":"1811.11524","title":"Multi-granularity Generator for Temporal Action Proposal","created":"2018-11-28","cited_by_count":77},{"id":"2107.12960","title":"Enriching Local and Global Contexts for Temporal Action Localization","created":"2021-07-27","cited_by_count":64},{"id":"2001.04608","title":"Actions as Moving Points","created":"2020-01-14","cited_by_count":55},{"id":"2012.09434","title":"Multi-shot Temporal Event Localization: a Benchmark","created":"2020-12-17","cited_by_count":52},{"id":"1904.09288","title":"STEP: Spatio-Temporal Progressive Learning for Video Action Detection","created":"2019-04-19","cited_by_count":51},{"id":"2207.07097","title":"ReAct: Temporal Action Detection with Relational Queries","created":"2022-07-14","cited_by_count":48},{"id":"2109.15130","title":"Motion-aware Contrastive Video Representation Learning via Foreground-background Merging","created":"2021-09-30","cited_by_count":45},{"id":"2010.14982","title":"Toyota Smarthome Untrimmed: Real-World Untrimmed Videos for Activity Detection","created":"2020-10-28","cited_by_count":42},{"id":"2112.03902","title":"MS-TCT: Multi-Scale Temporal ConvTransformer for Action Detection","created":"2021-12-07","cited_by_count":42},{"id":"1803.06316","title":"Temporal Gaussian Mixture Layer for Videos","created":"2018-03-16","cited_by_count":40},{"id":"2112.03612","title":"DCAN: Improving Temporal Action Detection via Dual Context Aggregation","created":"2021-12-07","cited_by_count":36},{"id":"2304.08386","title":"Progressive Visual Prompt Learning with Contrastive Feature Re-formation","created":"2023-04-17","cited_by_count":36},{"id":"2103.03027","title":"Modeling Multi-Label Action Dependencies for Temporal Action Localization","created":"2021-03-04","cited_by_count":32},{"id":"1712.01938","title":"Learning Latent Super-Events to Detect Multiple Activities in Videos","created":"2017-12-05","cited_by_count":30},{"id":"2109.07107","title":"Anchor DETR: Query Design for Transformer-Based Object Detection","created":"2021-09-15","cited_by_count":30},{"id":"2207.06580","title":"Proposal-Free Temporal Action Detection via Global Segmentation Mask Learning","created":"2022-07-14","cited_by_count":29},{"id":"1704.04671","title":"Temporal Action Localization by Structured Maximal Sums","created":"2017-04-15","cited_by_count":28},{"id":"2003.04145","title":"Accurate Temporal Action Proposal Generation with Relation-Aware Pyramid Network","created":"2020-03-09","cited_by_count":28},{"id":"2103.01302","title":"Coarse-Fine Networks for Temporal Activity Detection in Videos","created":"2021-03-01","cited_by_count":28},{"id":"2305.15701","title":"Action Sensitivity Learning for Temporal Action Localization","created":"2023-05-25","cited_by_count":28},{"id":"2203.07112","title":"RCL: Recurrent Continuous Localization for Temporal Action Detection","created":"2022-03-14","cited_by_count":25},{"id":"2308.04549","title":"Prune Spatio-temporal Tokens by Semantic-aware Temporal Accumulation","created":"2023-08-08","cited_by_count":24},{"id":"2210.11035","title":"PointTAD: Multi-Label Temporal Action Detection with Learnable Query Points","created":"2022-10-20","cited_by_count":22},{"id":"2308.10570","title":"Self-Feedback DETR for Temporal Action Detection","created":"2023-08-21","cited_by_count":22},{"id":"2207.08914","title":"Conditional DETR V2: Efficient Detection Transformer with Box Queries","created":"2022-07-18","cited_by_count":21},{"id":"2206.11493","title":"Learning to Refactor Action and Co-occurrence Features for Temporal Action Localization","created":"2022-06-23","cited_by_count":18},{"id":"2110.13473","title":"CTRN: Class-Temporal Relational Network for Action Detection","created":"2021-10-26","cited_by_count":15},{"id":"2207.05340","title":"Dual Contrastive Learning for Spatio-temporal Representation","created":"2022-07-12","cited_by_count":15},{"id":"2309.05590","title":"Temporal Action Localization with Enhanced Instant Discriminability","created":"2023-09-11","cited_by_count":13},{"id":"2203.00307","title":"Temporal Perceiver: A General Architecture for Arbitrary Boundary Detection","created":"2022-03-01","cited_by_count":12},{"id":"2308.05051","title":"PAT: Position-Aware Transformer for Dense Multi-Label Action Detection","created":"2023-08-09","cited_by_count":6},{"id":"2308.10061","title":"DPL: Decoupled Prompt Learning for Vision-Language Models","created":"2023-08-19","cited_by_count":4},{"id":"2311.03149","title":"Asymmetric Masked Distillation for Pre-Training Small Foundation Models","created":"2023-11-06","cited_by_count":2}],"next_cursor":null}