{"list":"other","total":63,"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":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"1710.09412","title":"mixup: Beyond Empirical Risk Minimization","created":"2017-10-25","cited_by_count":5183},{"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":"1412.3555","title":"Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling","created":"2014-12-11","cited_by_count":2367},{"id":"1705.06950","title":"The Kinetics Human Action Video Dataset","created":"2017-05-19","cited_by_count":1909},{"id":"1812.03982","title":"SlowFast Networks for Video Recognition","created":"2018-12-10","cited_by_count":1867},{"id":"2103.15691","title":"ViViT: A Video Vision Transformer","created":"2021-03-29","cited_by_count":1620},{"id":"2203.12602","title":"VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training","created":"2022-03-23","cited_by_count":1322},{"id":"1711.11248","title":"A Closer Look at Spatiotemporal Convolutions for Action Recognition","created":"2017-11-30","cited_by_count":1143},{"id":"2003.13678","title":"Designing Network Design Spaces","created":"2020-03-30","cited_by_count":960},{"id":"1511.07247","title":"NetVLAD: CNN architecture for weakly supervised place recognition","created":"2015-11-23","cited_by_count":941},{"id":"1907.09702","title":"BMN: Boundary-Matching Network for Temporal Action Proposal Generation","created":"2019-07-23","cited_by_count":329},{"id":"1904.02811","title":"Video Classification with Channel-Separated Convolutional Networks","created":"2019-04-04","cited_by_count":290},{"id":"2102.00719","title":"Video Transformer Network","created":"2021-02-01","cited_by_count":272},{"id":"1806.02964","title":"BSN: Boundary Sensitive Network for Temporal Action Proposal Generation","created":"2018-06-08","cited_by_count":271},{"id":"2004.06704","title":"FineGym: A Hierarchical Video Dataset for Fine-grained Action Understanding","created":"2020-04-14","cited_by_count":234},{"id":"1604.06182","title":"The THUMOS Challenge on Action Recognition for Videos \"in the Wild\"","created":"2016-04-21","cited_by_count":213},{"id":"1708.07632","title":"Learning Spatio-Temporal Features with 3D Residual Networks for Action Recognition","created":"2017-08-25","cited_by_count":178},{"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":"2011.13367","title":"SoccerNet-v2: A Dataset and Benchmarks for Holistic Understanding of Broadcast Soccer Videos","created":"2020-11-26","cited_by_count":131},{"id":"1703.06189","title":"TURN TAP: Temporal Unit Regression Network for Temporal Action Proposals","created":"2017-03-17","cited_by_count":113},{"id":"2103.13141","title":"Temporal Context Aggregation Network for Temporal Action Proposal Refinement","created":"2021-03-24","cited_by_count":112},{"id":"2204.03646","title":"FineDiving: A Fine-grained Dataset for Procedure-aware Action Quality Assessment","created":"2022-04-07","cited_by_count":107},{"id":"1912.00381","title":"Gate-Shift Networks for Video Action Recognition","created":"2019-12-01","cited_by_count":76},{"id":"2009.07641","title":"BSN++: Complementary Boundary Regressor with Scale-Balanced Relation Modeling for Temporal Action Proposal Generation","created":"2020-09-15","cited_by_count":65},{"id":"1706.06905","title":"Learnable pooling with Context Gating for video classification","created":"2017-06-21","cited_by_count":58},{"id":"1912.01326","title":"A Context-Aware Loss Function for Action Spotting in Soccer Videos","created":"2019-12-03","cited_by_count":56},{"id":"1807.04821","title":"CTAP: Complementary Temporal Action Proposal Generation","created":"2018-07-12","cited_by_count":46},{"id":"2207.10213","title":"Spotting Temporally Precise, Fine-Grained Events in Video","created":"2022-07-20","cited_by_count":40},{"id":"2203.14911","title":"Expanding Low-Density Latent Regions for Open-Set Object Detection","created":"2022-03-28","cited_by_count":38},{"id":"2004.09927","title":"TTNet: Real-time temporal and spatial video analysis of table tennis","created":"2020-04-21","cited_by_count":36},{"id":"1907.03698","title":"TrackNet: A Deep Learning Network for Tracking High-speed and Tiny Objects in Sports Applications","created":"2019-07-08","cited_by_count":33},{"id":"2008.04524","title":"Vid2Player: Controllable Video Sprites that Behave and Appear like Professional Tennis Players","created":"2020-08-11","cited_by_count":30},{"id":"2104.06779","title":"Temporally-Aware Feature Pooling for Action Spotting in Soccer Broadcasts","created":"2021-04-14","cited_by_count":30},{"id":"2109.01305","title":"Video Pose Distillation for Few-Shot, Fine-Grained Sports Action Recognition","created":"2021-09-03","cited_by_count":29},{"id":"2106.14447","title":"Feature Combination Meets Attention: Baidu Soccer Embeddings and Transformer based Temporal Detection","created":"2021-06-28","cited_by_count":27},{"id":"2205.10450","title":"Temporally Precise Action Spotting in Soccer Videos Using Dense Detection Anchors","created":"2022-05-20","cited_by_count":27},{"id":"1511.02917","title":"Detecting events and key actors in multi-person videos","created":"2015-11-09","cited_by_count":26},{"id":"2204.01899","title":"MonoTrack: Shuttle trajectory reconstruction from monocular badminton video","created":"2022-04-04","cited_by_count":24},{"id":"2011.04258","title":"Improved Soccer Action Spotting using both Audio and Video Streams","created":"2020-11-09","cited_by_count":21},{"id":"2404.05392","title":"T-DEED: Temporal-Discriminability Enhancer Encoder-Decoder for Precise Event Spotting in Sports Videos","created":"2024-04-08","cited_by_count":21},{"id":"2012.08510","title":"GTA: Global Temporal Attention for Video Action Understanding","created":"2020-12-15","cited_by_count":20},{"id":"2102.07624","title":"RMS-Net: Regression and Masking for Soccer Event Spotting","created":"2021-02-15","cited_by_count":19},{"id":"2004.06172","title":"Event detection in coarsely annotated sports videos via parallel multi receptive field 1D convolutions","created":"2020-04-13","cited_by_count":18},{"id":"2309.01270","title":"COMEDIAN: Self-Supervised Learning and Knowledge Distillation for Action Spotting using Transformers","created":"2023-09-03","cited_by_count":17},{"id":"2112.07984","title":"Temporal Action Proposal Generation with Background Constraint","created":"2021-12-15","cited_by_count":16},{"id":"2404.01891","title":"ASTRA: An Action Spotting TRAnsformer for Soccer Videos","created":"2024-04-02","cited_by_count":16},{"id":"1712.08714","title":"Towards Structured Analysis of Broadcast Badminton Videos","created":"2017-12-23","cited_by_count":15},{"id":"2304.04220","title":"Towards Active Learning for Action Spotting in Association Football Videos","created":"2023-04-09","cited_by_count":14},{"id":"2307.03353","title":"A Survey of Deep Learning in Sports Applications: Perception, Comprehension, and Decision","created":"2023-07-07","cited_by_count":11},{"id":"2404.09951","title":"Unifying Global and Local Scene Entities Modelling for Precise Action Spotting","created":"2024-04-15","cited_by_count":8},{"id":"2402.15952","title":"ViSTec: Video Modeling for Sports Technique Recognition and Tactical Analysis","created":"2024-02-25","cited_by_count":7},{"id":"2503.00147","title":"Precise Event Spotting in Sports Videos: Solving Long-Range Dependency and Class Imbalance","created":"2025-02-28","cited_by_count":6},{"id":"2207.12730","title":"P2ANet: A Dataset and Benchmark for Dense Action Detection from Table Tennis Match Broadcasting Videos","created":"2022-07-26","cited_by_count":5},{"id":"2412.16454","title":"FACTS: Fine-Grained Action Classification for Tactical Sports","created":"2024-12-21","cited_by_count":4}],"next_cursor":null}