{"list":"other","total":61,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"id":"1904.09675","title":"BERTScore: Evaluating Text Generation with BERT","created":"2019-04-21","cited_by_count":5512},{"id":"1504.08083","title":"Fast R-CNN","created":"2015-04-30","cited_by_count":2933},{"id":"1411.5726","title":"CIDEr: Consensus-based Image Description Evaluation","created":"2014-11-20","cited_by_count":2046},{"id":"1705.06950","title":"The Kinetics Human Action Video Dataset","created":"2017-05-19","cited_by_count":1909},{"id":"1607.04606","title":"Enriching Word Vectors with Subword Information","created":"2016-07-15","cited_by_count":1583},{"id":"1805.04833","title":"Hierarchical Neural Story Generation","created":"2018-05-13","cited_by_count":1193},{"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":"1910.14599","title":"Adversarial NLI: A New Benchmark for Natural Language Understanding","created":"2019-10-31","cited_by_count":807},{"id":"1705.00754","title":"Dense-Captioning Events in Videos","created":"2017-05-02","cited_by_count":793},{"id":"2104.08860","title":"CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval","created":"2021-04-18","cited_by_count":651},{"id":"2109.14084","title":"VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding","created":"2021-09-28","cited_by_count":602},{"id":"1712.07040","title":"The NarrativeQA Reading Comprehension Challenge","created":"2017-12-19","cited_by_count":597},{"id":"1711.09577","title":"Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?","created":"2017-11-27","cited_by_count":551},{"id":"1811.00982","title":"The Open Images Dataset V4: Unified image classification, object detection, and visual relationship detection at scale","created":"2018-11-02","cited_by_count":544},{"id":"1604.01753","title":"Hollywood in Homes: Crowdsourcing Data Collection for Activity Understanding","created":"2016-04-06","cited_by_count":537},{"id":"1712.04851","title":"Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classification","created":"2017-12-13","cited_by_count":521},{"id":"1809.01696","title":"TVQA: Localized, Compositional Video Question Answering","created":"2018-09-05","cited_by_count":467},{"id":"2106.02636","title":"MERLOT: Multimodal Neural Script Knowledge Models","created":"2021-06-04","cited_by_count":311},{"id":"1512.02902","title":"MovieQA: Understanding Stories in Movies through Question-Answering","created":"2015-12-09","cited_by_count":304},{"id":"1908.05739","title":"Abductive Commonsense Reasoning","created":"2019-08-15","cited_by_count":301},{"id":"1904.01941","title":"Character Region Awareness for Text Detection","created":"2019-04-03","cited_by_count":278},{"id":"2007.10937","title":"MovieNet: A Holistic Dataset for Movie Understanding","created":"2020-07-21","cited_by_count":206},{"id":"1501.02530","title":"A Dataset for Movie Description","created":"2015-01-12","cited_by_count":195},{"id":"1605.03705","title":"Movie Description","created":"2016-05-12","cited_by_count":181},{"id":"1604.03968","title":"Visual Storytelling","created":"2016-04-13","cited_by_count":176},{"id":"2008.04838","title":"TransNet V2: An effective deep network architecture for fast shot transition detection","created":"2020-08-11","cited_by_count":171},{"id":"2106.11310","title":"Towards Long-Form Video Understanding","created":"2021-06-21","cited_by_count":146},{"id":"2012.15738","title":"Moral Stories: Situated Reasoning about Norms, Intents, Actions, and their Consequences","created":"2020-12-31","cited_by_count":135},{"id":"2112.00431","title":"MAD: A Scalable Dataset for Language Grounding in Videos from Movie Audio Descriptions","created":"2021-12-01","cited_by_count":108},{"id":"2005.04208","title":"Condensed Movies: Story Based Retrieval with Contextual Embeddings","created":"2020-05-08","cited_by_count":95},{"id":"1805.06939","title":"Event2Mind: Commonsense Inference on Events, Intents, and Reactions","created":"2018-05-17","cited_by_count":82},{"id":"2104.07091","title":"SummScreen: A Dataset for Abstractive Screenplay Summarization","created":"2021-04-14","cited_by_count":79},{"id":"1707.00836","title":"DeepStory: Video Story QA by Deep Embedded Memory Networks","created":"2017-07-04","cited_by_count":68},{"id":"1712.06761","title":"MovieGraphs: Towards Understanding Human-Centric Situations from Videos","created":"2017-12-19","cited_by_count":67},{"id":"2005.00242","title":"TORQUE: A Reading Comprehension Dataset of Temporal Ordering Questions","created":"2020-05-01","cited_by_count":65},{"id":"1706.01331","title":"Event Representations for Automated Story Generation with Deep Neural Nets","created":"2017-06-05","cited_by_count":63},{"id":"1401.3841","title":"Narrative Planning: Balancing Plot and Character","created":"2014-01-16","cited_by_count":61},{"id":"1805.06533","title":"Modeling Naive Psychology of Characters in Simple Commonsense Stories","created":"2018-05-16","cited_by_count":60},{"id":"2104.00990","title":"Visual Semantic Role Labeling for Video Understanding","created":"2021-04-02","cited_by_count":60},{"id":"2010.12753","title":"Temporal Reasoning on Implicit Events from Distant Supervision","created":"2020-10-24","cited_by_count":58},{"id":"2010.06727","title":"Joint Constrained Learning for Event-Event Relation Extraction","created":"2020-10-13","cited_by_count":53},{"id":"2109.05438","title":"\"Let Your Characters Tell Their Story\": A Dataset for Character-Centric Narrative Understanding","created":"2021-09-12","cited_by_count":48},{"id":"1611.05118","title":"The Amazing Mysteries of the Gutter: Drawing Inferences Between Panels in Comic Book Narratives","created":"2016-11-16","cited_by_count":42},{"id":"1503.01070","title":"Using Descriptive Video Services to Create a Large Data Source for Video Annotation Research","created":"2015-03-03","cited_by_count":33},{"id":"1903.12453","title":"Frowning Frodo, Wincing Leia, and a Seriously Great Friendship: Learning to Classify Emotional Relationships of Fictional Characters","created":"2019-03-29","cited_by_count":23},{"id":"2004.12727","title":"Screenplay Summarization Using Latent Narrative Structure","created":"2020-04-27","cited_by_count":23},{"id":"2012.07536","title":"Movie Summarization via Sparse Graph Construction","created":"2020-12-14","cited_by_count":22},{"id":"1902.01390","title":"Fine-Grained Temporal Relation Extraction","created":"2019-02-04","cited_by_count":21},{"id":"2104.06669","title":"NAREOR: The Narrative Reordering Problem","created":"2021-04-14","cited_by_count":14},{"id":"1803.00057","title":"A Neural Multi-sequence Alignment TeCHnique (NeuMATCH)","created":"2018-02-19","cited_by_count":13},{"id":"1606.07493","title":"Sort Story: Sorting Jumbled Images and Captions into Stories","created":"2016-06-23","cited_by_count":12},{"id":"1604.02993","title":"Using Sentence-Level LSTM Language Models for Script Inference","created":"2016-04-11","cited_by_count":10},{"id":"2008.03546","title":"Online Multi-modal Person Search in Videos","created":"2020-08-08","cited_by_count":10},{"id":"1602.06484","title":"Computational Narrative Intelligence: A Human-Centered Goal for Artificial Intelligence","created":"2016-02-21","cited_by_count":6},{"id":"1511.09376","title":"Modeling Dynamic Relationships Between Characters in Literary Novels","created":"2015-11-30","cited_by_count":4},{"id":"1710.06917","title":"Annotating High-Level Structures of Short Stories and Personal Anecdotes","created":"2017-10-08","cited_by_count":3},{"id":"1806.05099","title":"Graph-Based Decoding for Event Sequencing and Coreference Resolution","created":"2018-06-13","cited_by_count":3},{"id":"2011.07517","title":"Data-efficient Alignment of Multimodal Sequences by Aligning Gradient Updates and Internal Feature Distributions","created":"2020-11-15","cited_by_count":2},{"id":"1811.02435","title":"WordNet-feelings: A linguistic categorisation of human feelings","created":"2018-11-06","cited_by_count":1}],"next_cursor":null}