{"list":"other","total":79,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"1406.1078","title":"Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation","created":"2014-06-03","cited_by_count":4057},{"id":"2011.10566","title":"Exploring Simple Siamese Representation Learning","created":"2020-11-20","cited_by_count":2866},{"id":"1805.01978","title":"Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination","created":"2018-05-05","cited_by_count":1845},{"id":"2006.10029","title":"Big Self-Supervised Models are Strong Semi-Supervised Learners","created":"2020-06-17","cited_by_count":1380},{"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":"2104.00650","title":"Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval","created":"2021-04-01","cited_by_count":1177},{"id":"1705.00754","title":"Dense-Captioning Events in Videos","created":"2017-05-02","cited_by_count":793},{"id":"2105.08276","title":"NExT-QA:Next Phase of Question-Answering to Explaining Temporal Actions","created":"2021-05-18","cited_by_count":744},{"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":"2201.12329","title":"DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETR","created":"2022-01-28","cited_by_count":573},{"id":"1606.09549","title":"Fully-Convolutional Siamese Networks for Object Tracking","created":"2016-06-30","cited_by_count":568},{"id":"1906.02467","title":"ActivityNet-QA: A Dataset for Understanding Complex Web Videos via Question Answering","created":"2019-06-06","cited_by_count":561},{"id":"1604.01753","title":"Hollywood in Homes: Crowdsourcing Data Collection for Activity Understanding","created":"2016-04-06","cited_by_count":537},{"id":"1611.05267","title":"Temporal Convolutional Networks for Action Segmentation and Detection","created":"2016-11-16","cited_by_count":508},{"id":"2203.01305","title":"DN-DETR: Accelerate DETR Training by Introducing Query DeNoising","created":"2022-03-02","cited_by_count":488},{"id":"1809.01696","title":"TVQA: Localized, Compositional Video Question Answering","created":"2018-09-05","cited_by_count":467},{"id":"2108.06152","title":"Conditional DETR for Fast Training Convergence","created":"2021-08-13","cited_by_count":424},{"id":"2007.10639","title":"Multi-modal Transformer for Video Retrieval","created":"2020-07-21","cited_by_count":395},{"id":"1704.04497","title":"TGIF-QA: Toward Spatio-Temporal Reasoning in Visual Question Answering","created":"2017-04-14","cited_by_count":378},{"id":"1903.01945","title":"MS-TCN: Multi-Stage Temporal Convolutional Network for Action Segmentation","created":"2019-03-05","cited_by_count":373},{"id":"2204.07141","title":"Masked Siamese Networks for Label-Efficient Learning","created":"2022-04-14","cited_by_count":302},{"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":"1702.01806","title":"Beam Search Strategies for Neural Machine Translation","created":"2017-02-06","cited_by_count":232},{"id":"2004.07514","title":"Local-Global Video-Text Interactions for Temporal Grounding","created":"2020-04-16","cited_by_count":188},{"id":"2004.03545","title":"Dense Regression Network for Video Grounding","created":"2020-04-07","cited_by_count":176},{"id":"2002.10698","title":"Hierarchical Conditional Relation Networks for Video Question Answering","created":"2020-02-25","cited_by_count":163},{"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":"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":"1804.05113","title":"Multilevel Language and Vision Integration for Text-to-Clip Retrieval","created":"2018-04-13","cited_by_count":128},{"id":"2203.15086","title":"X-Pool: Cross-Modal Language-Video Attention for Text-Video Retrieval","created":"2022-03-28","cited_by_count":128},{"id":"2107.00650","title":"CLIP-It! Language-Guided Video Summarization","created":"2021-07-01","cited_by_count":99},{"id":"2109.04872","title":"Negative Sample Matters: A Renaissance of Metric Learning for Temporal Grounding","created":"2021-09-10","cited_by_count":90},{"id":"2301.00184","title":"Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?","created":"2022-12-31","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":"1904.03282","title":"Weakly Supervised Video Moment Retrieval From Text Queries","created":"2019-04-05","cited_by_count":85},{"id":"1909.05010","title":"Temporally Grounding Language Queries in Videos by Contextual Boundary-aware Prediction","created":"2019-09-11","cited_by_count":84},{"id":"2308.06947","title":"Knowing Where to Focus: Event-aware Transformer for Video Grounding","created":"2023-08-14","cited_by_count":79},{"id":"2206.01204","title":"Siamese Image Modeling for Self-Supervised Vision Representation Learning","created":"2022-06-02","cited_by_count":78},{"id":"2305.14344","title":"Siamese Masked Autoencoders","created":"2023-05-23","cited_by_count":76},{"id":"2303.17959","title":"Diffusion Action Segmentation","created":"2023-03-31","cited_by_count":74},{"id":"1805.10538","title":"Video Summarization Using Fully Convolutional Sequence Networks","created":"2018-05-26","cited_by_count":71},{"id":"1911.08199","title":"Weakly-Supervised Video Moment Retrieval via Semantic Completion Network","created":"2019-11-19","cited_by_count":69},{"id":"2206.02349","title":"Invariant Grounding for Video Question Answering","created":"2022-06-06","cited_by_count":68},{"id":"1812.03849","title":"Weakly Supervised Dense Event Captioning in Videos","created":"2018-12-10","cited_by_count":58},{"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":"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":"2105.13353","title":"Unsupervised Action Segmentation by Joint Representation Learning and Online Clustering","created":"2021-05-27","cited_by_count":49},{"id":"2001.06680","title":"Tree-Structured Policy based Progressive Reinforcement Learning for Temporally Language Grounding in Video","created":"2020-01-18","cited_by_count":47},{"id":"2201.00454","title":"Memory-Guided Semantic Learning Network for Temporal Sentence Grounding","created":"2022-01-03","cited_by_count":46},{"id":"2101.09028","title":"A Closer Look at Temporal Sentence Grounding in Videos: Dataset and Metric","created":"2021-01-22","cited_by_count":42},{"id":"2008.10238","title":"VLANet: Video-Language Alignment Network for Weakly-Supervised Video Moment Retrieval","created":"2020-08-24","cited_by_count":41},{"id":"2011.10830","title":"Boundary-sensitive Pre-training for Temporal Localization in Videos","created":"2020-11-21","cited_by_count":41},{"id":"1909.13784","title":"LoGAN: Latent Graph Co-Attention Network for Weakly-Supervised Video Moment Retrieval","created":"2019-09-27","cited_by_count":40},{"id":"2107.11443","title":"Cross-Sentence Temporal and Semantic Relations in Video Activity Localisation","created":"2021-07-23","cited_by_count":39},{"id":"2106.16136","title":"Weakly Supervised Temporal Adjacent Network for Language Grounding","created":"2021-06-30","cited_by_count":37},{"id":"1805.12174","title":"Video Summarization by Learning from Unpaired Data","created":"2018-05-30","cited_by_count":36},{"id":"2003.07048","title":"Weakly-Supervised Multi-Level Attentional Reconstruction Network for Grounding Textual Queries in Videos","created":"2020-03-16","cited_by_count":31},{"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":"2012.07508","title":"Temporal Relational Modeling with Self-Supervision for Action Segmentation","created":"2020-12-14","cited_by_count":29},{"id":"2109.10678","title":"Natural Language Video Localization with Learnable Moment Proposals","created":"2021-09-22","cited_by_count":27},{"id":"2008.08257","title":"Regularized Two-Branch Proposal Networks for Weakly-Supervised Moment Retrieval in Videos","created":"2020-08-19","cited_by_count":23},{"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":"2307.14277","title":"G2L: Semantically Aligned and Uniform Video Grounding via Geodesic and Game Theory","created":"2023-07-26","cited_by_count":21},{"id":"2303.04995","title":"Text-Visual Prompting for Efficient 2D Temporal Video Grounding","created":"2023-03-09","cited_by_count":18},{"id":"2201.05277","title":"Boundary-aware Self-supervised Learning for Video Scene Segmentation","created":"2022-01-14","cited_by_count":17},{"id":"2109.11265","title":"End-to-End Dense Video Grounding via Parallel Regression","created":"2021-09-23","cited_by_count":9},{"id":"2109.11475","title":"Self-supervised Learning for Semi-supervised Temporal Language Grounding","created":"2021-09-23","cited_by_count":7},{"id":"2105.05636","title":"VL-NMS: Breaking Proposal Bottlenecks in Two-Stage Visual-Language Matching","created":"2021-05-12","cited_by_count":2}],"next_cursor":null}