{"list":"other","total":60,"rows":[{"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":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"1710.10903","title":"Graph Attention Networks","created":"2017-10-30","cited_by_count":8923},{"id":"1910.13461","title":"BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension","created":"2019-10-29","cited_by_count":5893},{"id":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"1409.3215","title":"Sequence to Sequence Learning with Neural Networks","created":"2014-09-10","cited_by_count":2986},{"id":"1306.0895","title":"Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distances","created":"2013-06-04","cited_by_count":2316},{"id":"1704.04368","title":"Get To The Point: Summarization with Pointer-Generator Networks","created":"2017-04-14","cited_by_count":1292},{"id":"1506.03340","title":"Teaching Machines to Read and Comprehend","created":"2015-06-10","cited_by_count":1049},{"id":"1906.03327","title":"HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips","created":"2019-06-07","cited_by_count":950},{"id":"1908.08345","title":"Text Summarization with Pretrained Encoders","created":"2019-08-22","cited_by_count":556},{"id":"1611.05267","title":"Temporal Convolutional Networks for Action Segmentation and Detection","created":"2016-11-16","cited_by_count":508},{"id":"1707.07250","title":"Tensor Fusion Network for Multimodal Sentiment Analysis","created":"2017-07-23","cited_by_count":433},{"id":"1803.08024","title":"Stacked Cross Attention for Image-Text Matching","created":"2018-03-21","cited_by_count":416},{"id":"1903.02874","title":"COIN: A Large-scale Dataset for Comprehensive Instructional Video Analysis","created":"2019-03-07","cited_by_count":318},{"id":"1705.02953","title":"Temporal Segment Networks for Action Recognition in Videos","created":"2017-05-08","cited_by_count":279},{"id":"1704.06228","title":"Temporal Action Detection with Structured Segment Networks","created":"2017-04-20","cited_by_count":267},{"id":"1611.04230","title":"SummaRuNNer: A Recurrent Neural Network based Sequence Model for Extractive Summarization of Documents","created":"2016-11-14","cited_by_count":246},{"id":"1809.07041","title":"Exploring Visual Relationship for Image Captioning","created":"2018-09-19","cited_by_count":215},{"id":"2003.00392","title":"Fine-grained Video-Text Retrieval with Hierarchical Graph Reasoning","created":"2020-03-01","cited_by_count":180},{"id":"1802.08636","title":"Ranking Sentences for Extractive Summarization with Reinforcement Learning","created":"2018-02-23","cited_by_count":128},{"id":"1905.06566","title":"HIBERT: Document Level Pre-training of Hierarchical Bidirectional Transformers for Document Summarization","created":"2019-05-16","cited_by_count":121},{"id":"1603.07252","title":"Neural Summarization by Extracting Sentences and Words","created":"2016-03-23","cited_by_count":116},{"id":"1801.00054","title":"Deep Reinforcement Learning for Unsupervised Video Summarization with Diversity-Representativeness Reward","created":"2017-12-29","cited_by_count":105},{"id":"1810.07212","title":"Cross-Modal and Hierarchical Modeling of Video and Text","created":"2018-10-16","cited_by_count":103},{"id":"2006.14744","title":"Graph Optimal Transport for Cross-Domain Alignment","created":"2020-06-26","cited_by_count":103},{"id":"2108.09980","title":"TACo: Token-aware Cascade Contrastive Learning for Video-Text Alignment","created":"2021-08-23","cited_by_count":102},{"id":"1908.03477","title":"Fine-Grained Action Retrieval Through Multiple Parts-of-Speech Embeddings","created":"2019-08-09","cited_by_count":101},{"id":"2101.06072","title":"Video Summarization Using Deep Neural Networks: A Survey","created":"2021-01-15","cited_by_count":85},{"id":"1803.09337","title":"Text Segmentation as a Supervised Learning Task","created":"2018-03-25","cited_by_count":76},{"id":"1804.07036","title":"Learning to Extract Coherent Summary via Deep Reinforcement Learning","created":"2018-04-19","cited_by_count":64},{"id":"1708.09545","title":"Video Summarization with Attention-Based Encoder-Decoder Networks","created":"2017-08-31","cited_by_count":63},{"id":"2203.00048","title":"Multi-modal Alignment using Representation Codebook","created":"2022-02-28","cited_by_count":63},{"id":"1610.02947","title":"End-to-end Concept Word Detection for Video Captioning, Retrieval, and Question Answering","created":"2016-10-10","cited_by_count":60},{"id":"2004.02678","title":"A Local-to-Global Approach to Multi-modal Movie Scene Segmentation","created":"2020-04-06","cited_by_count":60},{"id":"2103.11264","title":"Temporally-Weighted Hierarchical Clustering for Unsupervised Action Segmentation","created":"2021-03-20","cited_by_count":58},{"id":"2004.14535","title":"Text Segmentation by Cross Segment Attention","created":"2020-04-30","cited_by_count":54},{"id":"1805.06266","title":"A Unified Model for Extractive and Abstractive Summarization using Inconsistency Loss","created":"2018-05-16","cited_by_count":47},{"id":"2010.05406","title":"VMSMO: Learning to Generate Multimodal Summary for Video-based News Articles","created":"2020-10-12","cited_by_count":44},{"id":"1609.08124","title":"Learning Language-Visual Embedding for Movie Understanding with Natural-Language","created":"2016-09-26","cited_by_count":41},{"id":"1811.04869","title":"A Perceptual Prediction Framework for Self Supervised Event Segmentation","created":"2018-11-12","cited_by_count":40},{"id":"1906.11768","title":"Hierarchical Optimal Transport for Multimodal Distribution Alignment","created":"2019-06-27","cited_by_count":38},{"id":"1806.08409","title":"End-to-End Audio Visual Scene-Aware Dialog using Multimodal Attention-Based Video Features","created":"2018-06-21","cited_by_count":37},{"id":"1906.01028","title":"A Hybrid RNN-HMM Approach for Weakly Supervised Temporal Action Segmentation","created":"2019-06-03","cited_by_count":36},{"id":"2104.13537","title":"Shot Contrastive Self-Supervised Learning for Scene Boundary Detection","created":"2021-04-28","cited_by_count":35},{"id":"1902.09774","title":"Image-Question-Answer Synergistic Network for Visual Dialog","created":"2019-02-26","cited_by_count":23},{"id":"2102.03353","title":"Cross-domain Activity Recognition via Substructural Optimal Transport","created":"2021-01-29","cited_by_count":21},{"id":"1808.09147","title":"Toward Fast and Accurate Neural Discourse Segmentation","created":"2018-08-28","cited_by_count":19},{"id":"2110.02887","title":"Using Optimal Transport as Alignment Objective for fine-tuning Multilingual Contextualized Embeddings","created":"2021-10-06","cited_by_count":19},{"id":"2105.09601","title":"See, Hear, Read: Leveraging Multimodality with Guided Attention for Abstractive Text Summarization","created":"2021-05-20","cited_by_count":18},{"id":"1609.08758","title":"Video Summarization using Deep Semantic Features","created":"2016-09-28","cited_by_count":15},{"id":"2009.08018","title":"Multi-modal Summarization for Video-containing Documents","created":"2020-09-17","cited_by_count":13},{"id":"1705.03281","title":"Large-scale, Fast and Accurate Shot Boundary Detection through Spatio-temporal Convolutional Neural Networks","created":"2017-05-09","cited_by_count":12},{"id":"1809.10324","title":"Iterative Document Representation Learning Towards Summarization with Polishing","created":"2018-09-27","cited_by_count":12},{"id":"2107.06876","title":"Scalable Optimal Transport in High Dimensions for Graph Distances, Embedding Alignment, and More","created":"2021-07-14","cited_by_count":11},{"id":"1807.03089","title":"Video Summarisation by Classification with Deep Reinforcement Learning","created":"2018-07-09","cited_by_count":10},{"id":"2010.05379","title":"MAF: Multimodal Alignment Framework for Weakly-Supervised Phrase Grounding","created":"2020-10-12","cited_by_count":9},{"id":"1804.06642","title":"Superframes, A Temporal Video Segmentation","created":"2018-04-18","cited_by_count":4}],"next_cursor":null}