{"list":"other","total":66,"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":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"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":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"2102.12122","title":"Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions","created":"2021-02-24","cited_by_count":1962},{"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":"2006.04768","title":"Linformer: Self-Attention with Linear Complexity","created":"2020-06-08","cited_by_count":1474},{"id":"1902.09630","title":"Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression","created":"2019-02-25","cited_by_count":1368},{"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":"1603.09382","title":"Deep Networks with Stochastic Depth","created":"2016-03-30","cited_by_count":979},{"id":"1705.00754","title":"Dense-Captioning Events in Videos","created":"2017-05-02","cited_by_count":793},{"id":"1708.01641","title":"Localizing Moments in Video with Natural Language","created":"2017-08-04","cited_by_count":663},{"id":"2103.00112","title":"Transformer in Transformer","created":"2021-02-27","cited_by_count":633},{"id":"1705.02101","title":"TALL: Temporal Activity Localization via Language Query","created":"2017-05-05","cited_by_count":584},{"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":"2111.11418","title":"MetaFormer Is Actually What You Need for Vision","created":"2021-11-22","cited_by_count":524},{"id":"2203.01305","title":"DN-DETR: Accelerate DETR Training by Introducing Query DeNoising","created":"2022-03-02","cited_by_count":488},{"id":"2206.06488","title":"Multimodal Learning with Transformers: A Survey","created":"2022-06-13","cited_by_count":400},{"id":"1812.01243","title":"Efficient Attention: Attention with Linear Complexities","created":"2018-12-04","cited_by_count":368},{"id":"2105.08050","title":"Pay Attention to MLPs","created":"2021-05-17","cited_by_count":368},{"id":"1912.03590","title":"Learning 2D Temporal Adjacent Networks for Moment Localization with Natural Language","created":"2019-12-08","cited_by_count":285},{"id":"2004.13931","title":"Span-based Localizing Network for Natural Language Video Localization","created":"2020-04-29","cited_by_count":235},{"id":"2001.09099","title":"TVR: A Large-Scale Dataset for Video-Subtitle Moment Retrieval","created":"2020-01-24","cited_by_count":215},{"id":"2107.14222","title":"Rethinking and Improving Relative Position Encoding for Vision Transformer","created":"2021-07-29","cited_by_count":207},{"id":"2004.03545","title":"Dense Regression Network for Video Grounding","created":"2020-04-07","cited_by_count":176},{"id":"2111.13196","title":"SwinBERT: End-to-End Transformers with Sparse Attention for Video Captioning","created":"2021-11-25","cited_by_count":162},{"id":"2103.13137","title":"Learning Salient Boundary Feature for Anchor-free Temporal Action Localization","created":"2021-03-24","cited_by_count":156},{"id":"2203.12745","title":"UMT: Unified Multi-modal Transformers for Joint Video Moment Retrieval and Highlight Detection","created":"2022-03-23","cited_by_count":148},{"id":"1812.00087","title":"MAN: Moment Alignment Network for Natural Language Moment Retrieval via Iterative Graph Adjustment","created":"2018-11-30","cited_by_count":145},{"id":"1605.08110","title":"Video Summarization with Long Short-term Memory","created":"2016-05-26","cited_by_count":142},{"id":"1910.14303","title":"Semantic Conditioned Dynamic Modulation for Temporal Sentence Grounding in Videos","created":"2019-10-31","cited_by_count":135},{"id":"2108.07781","title":"End-to-End Dense Video Captioning with Parallel Decoding","created":"2021-08-17","cited_by_count":133},{"id":"1804.05113","title":"Multilevel Language and Vision Integration for Text-to-Clip Retrieval","created":"2018-04-13","cited_by_count":128},{"id":"2201.08264","title":"End-to-end Generative Pretraining for Multimodal Video Captioning","created":"2022-01-20","cited_by_count":116},{"id":"2011.01819","title":"Learning Representations from Audio-Visual Spatial Alignment","created":"2020-11-03","cited_by_count":95},{"id":"1906.09777","title":"A Tensorized Transformer for Language Modeling","created":"2019-06-24","cited_by_count":86},{"id":"2101.06072","title":"Video Summarization Using Deep Neural Networks: A Survey","created":"2021-01-15","cited_by_count":85},{"id":"1809.01337","title":"Localizing Moments in Video with Temporal Language","created":"2018-09-05","cited_by_count":83},{"id":"1903.00859","title":"Less is More: Learning Highlight Detection from Video Duration","created":"2019-03-03","cited_by_count":60},{"id":"2203.13049","title":"Compositional Temporal Grounding with Structured Variational Cross-Graph Correspondence Learning","created":"2022-03-24","cited_by_count":59},{"id":"2109.06085","title":"On Pursuit of Designing Multi-modal Transformer for Video Grounding","created":"2021-09-13","cited_by_count":54},{"id":"2011.10132","title":"VLG-Net: Video-Language Graph Matching Network for Video Grounding","created":"2020-11-19","cited_by_count":50},{"id":"2008.05231","title":"Fine-grained Visual Textual Alignment for Cross-Modal Retrieval using Transformer Encoders","created":"2020-08-12","cited_by_count":47},{"id":"2107.05624","title":"End-to-end Multi-modal Video Temporal Grounding","created":"2021-07-12","cited_by_count":47},{"id":"2008.02448","title":"Fine-grained Iterative Attention Network for TemporalLanguage Localization in Videos","created":"2020-08-06","cited_by_count":46},{"id":"2006.07214","title":"Sparse and Continuous Attention Mechanisms","created":"2020-06-12","cited_by_count":39},{"id":"2108.11770","title":"Cross-category Video Highlight Detection via Set-based Learning","created":"2021-08-26","cited_by_count":38},{"id":"2109.05422","title":"Sparse MLP for Image Recognition: Is Self-Attention Really Necessary?","created":"2021-09-12","cited_by_count":38},{"id":"2208.14882","title":"Hierarchical Local-Global Transformer for Temporal Sentence Grounding","created":"2022-08-31","cited_by_count":38},{"id":"2008.08502","title":"Learning Trailer Moments in Full-Length Movies","created":"2020-08-19","cited_by_count":37},{"id":"2201.08071","title":"Temporal Sentence Grounding in Videos: A Survey and Future Directions","created":"2022-01-20","cited_by_count":37},{"id":"1609.01388","title":"To Click or Not To Click: Automatic Selection of Beautiful Thumbnails from Videos","created":"2016-09-06","cited_by_count":34},{"id":"2203.16800","title":"Fine-grained Temporal Contrastive Learning for Weakly-supervised Temporal Action Localization","created":"2022-03-31","cited_by_count":33},{"id":"2111.12476","title":"Hierarchical Modular Network for Video Captioning","created":"2021-11-24","cited_by_count":32},{"id":"2203.13609","title":"Unsupervised Pre-training for Temporal Action Localization Tasks","created":"2022-03-25","cited_by_count":31},{"id":"2106.10528","title":"Video Summarization through Reinforcement Learning with a 3D Spatio-Temporal U-Net","created":"2021-06-19","cited_by_count":22},{"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":"2204.04615","title":"Learning Pixel-Level Distinctions for Video Highlight Detection","created":"2022-04-10","cited_by_count":16},{"id":"2109.02377","title":"PermuteFormer: Efficient Relative Position Encoding for Long Sequences","created":"2021-09-06","cited_by_count":14}],"next_cursor":null}