{"list":"other","total":53,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"1609.02907","title":"Semi-Supervised Classification with Graph Convolutional Networks","created":"2016-09-09","cited_by_count":11361},{"id":"1710.10903","title":"Graph Attention Networks","created":"2017-10-30","cited_by_count":8923},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"1910.01108","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","created":"2019-10-02","cited_by_count":4307},{"id":"2006.11477","title":"wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations","created":"2020-06-20","cited_by_count":3905},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"2111.00396","title":"Efficiently Modeling Long Sequences with Structured State Spaces","created":"2021-10-31","cited_by_count":2465},{"id":"1812.03982","title":"SlowFast Networks for Video Recognition","created":"2018-12-10","cited_by_count":1867},{"id":"2205.01917","title":"CoCa: Contrastive Captioners are Image-Text Foundation Models","created":"2022-05-04","cited_by_count":1274},{"id":"2102.03334","title":"ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision","created":"2021-02-05","cited_by_count":1230},{"id":"1801.07606","title":"Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning","created":"2018-01-22","cited_by_count":1102},{"id":"1705.00754","title":"Dense-Captioning Events in Videos","created":"2017-05-02","cited_by_count":793},{"id":"2202.03555","title":"data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language","created":"2022-02-07","cited_by_count":727},{"id":"1708.01641","title":"Localizing Moments in Video with Natural Language","created":"2017-08-04","cited_by_count":663},{"id":"1705.02101","title":"TALL: Temporal Activity Localization via Language Query","created":"2017-05-05","cited_by_count":584},{"id":"1706.08566","title":"SchNet: A continuous-filter convolutional neural network for modeling quantum interactions","created":"2017-06-26","cited_by_count":571},{"id":"1604.01753","title":"Hollywood in Homes: Crowdsourcing Data Collection for Activity Understanding","created":"2016-04-06","cited_by_count":537},{"id":"2305.13516","title":"Scaling Speech Technology to 1,000+ Languages","created":"2023-05-22","cited_by_count":411},{"id":"2105.03404","title":"ResMLP: Feedforward networks for image classification with data-efficient training","created":"2021-05-07","cited_by_count":339},{"id":"1912.03590","title":"Learning 2D Temporal Adjacent Networks for Moment Localization with Natural Language","created":"2019-12-08","cited_by_count":285},{"id":"1911.11462","title":"G-TAD: Sub-Graph Localization for Temporal Action Detection","created":"2019-11-26","cited_by_count":249},{"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":"2307.16715","title":"UniVTG: Towards Unified Video-Language Temporal Grounding","created":"2023-07-31","cited_by_count":190},{"id":"2004.07514","title":"Local-Global Video-Text Interactions for Temporal Grounding","created":"2020-04-16","cited_by_count":188},{"id":"2110.07205","title":"SpeechT5: Unified-Modal Encoder-Decoder Pre-Training for Spoken Language Processing","created":"2021-10-14","cited_by_count":180},{"id":"2004.03545","title":"Dense Regression Network for Video Grounding","created":"2020-04-07","cited_by_count":176},{"id":"2303.13874","title":"Query-Dependent Video Representation for Moment Retrieval and Highlight Detection","created":"2023-03-24","cited_by_count":166},{"id":"1804.07014","title":"To Find Where You Talk: Temporal Sentence Localization in Video with Attention Based Location Regression","created":"2018-04-19","cited_by_count":157},{"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":"1909.03877","title":"Gaussian Temporal Awareness Networks for Action Localization","created":"2019-09-09","cited_by_count":135},{"id":"1910.14303","title":"Semantic Conditioned Dynamic Modulation for Temporal Sentence Grounding in Videos","created":"2019-10-31","cited_by_count":135},{"id":"2305.11172","title":"ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities","created":"2023-05-18","cited_by_count":118},{"id":"2109.04872","title":"Negative Sample Matters: A Renaissance of Metric Learning for Temporal Grounding","created":"2021-09-10","cited_by_count":90},{"id":"2103.08109","title":"Boundary Proposal Network for Two-Stage Natural Language Video Localization","created":"2021-03-15","cited_by_count":88},{"id":"1908.07236","title":"Proposal-free Temporal Moment Localization of a Natural-Language Query in Video using Guided Attention","created":"2019-08-20","cited_by_count":81},{"id":"2101.07597","title":"UniSpeech: Unified Speech Representation Learning with Labeled and Unlabeled Data","created":"2021-01-19","cited_by_count":77},{"id":"2008.01403","title":"Jointly Cross- and Self-Modal Graph Attention Network for Query-Based Moment Localization","created":"2020-08-04","cited_by_count":74},{"id":"2102.13558","title":"Natural Language Video Localization: A Revisit in Span-based Question Answering Framework","created":"2021-02-26","cited_by_count":55},{"id":"2305.00355","title":"MH-DETR: Video Moment and Highlight Detection with Cross-modal Transformer","created":"2023-04-29","cited_by_count":40},{"id":"2203.02966","title":"Exploring Optical-Flow-Guided Motion and Detection-Based Appearance for Temporal Sentence Grounding","created":"2022-03-06","cited_by_count":35},{"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":"2012.02646","title":"Multi-Scale 2D Temporal Adjacent Networks for Moment Localization with Natural Language","created":"2020-12-04","cited_by_count":29},{"id":"2110.05717","title":"Relation-aware Video Reading Comprehension for Temporal Language Grounding","created":"2021-10-12","cited_by_count":27},{"id":"2308.06009","title":"ViGT: Proposal-free Video Grounding with Learnable Token in Transformer","created":"2023-08-11","cited_by_count":22},{"id":"2207.13450","title":"Skimming, Locating, then Perusing: A Human-Like Framework for Natural Language Video Localization","created":"2022-07-27","cited_by_count":21},{"id":"2102.01282","title":"Progressive Localization Networks for Language-based Moment Localization","created":"2021-02-02","cited_by_count":17},{"id":"2205.12886","title":"You Need to Read Again: Multi-granularity Perception Network for Moment Retrieval in Videos","created":"2022-05-25","cited_by_count":13},{"id":"2305.18969","title":"MS-DETR: Natural Language Video Localization with Sampling Moment-Moment Interaction","created":"2023-05-30","cited_by_count":8},{"id":"2209.00277","title":"Video-Guided Curriculum Learning for Spoken Video Grounding","created":"2022-09-01","cited_by_count":5}],"next_cursor":null}