{"list":"other","total":55,"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":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"1409.4842","title":"Going Deeper with Convolutions","created":"2014-09-17","cited_by_count":4241},{"id":"1310.4546","title":"Distributed Representations of Words and Phrases and their Compositionality","created":"2013-10-16","cited_by_count":3474},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"1712.00726","title":"Cascade R-CNN: Delving into High Quality Object Detection","created":"2017-12-03","cited_by_count":1276},{"id":"1506.06724","title":"Aligning Books and Movies: Towards Story-like Visual Explanations by Watching Movies and Reading Books","created":"2015-06-22","cited_by_count":1043},{"id":"1710.08092","title":"VGGFace2: A dataset for recognising faces across pose and age","created":"2017-10-23","cited_by_count":914},{"id":"1604.02878","title":"Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks","created":"2016-04-11","cited_by_count":903},{"id":"2104.11227","title":"Multiscale Vision Transformers","created":"2021-04-22","cited_by_count":897},{"id":"1602.00763","title":"Simple Online and Realtime Tracking","created":"2016-02-02","cited_by_count":868},{"id":"1904.01766","title":"VideoBERT: A Joint Model for Video and Language Representation Learning","created":"2019-04-03","cited_by_count":703},{"id":"1810.02508","title":"MELD: A Multimodal Multi-Party Dataset for Emotion Recognition in Conversations","created":"2018-10-05","cited_by_count":643},{"id":"1809.01696","title":"TVQA: Localized, Compositional Video Question Answering","created":"2018-09-05","cited_by_count":467},{"id":"1705.08421","title":"AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actions","created":"2017-05-23","cited_by_count":449},{"id":"1512.02902","title":"MovieQA: Understanding Stories in Movies through Question-Answering","created":"2015-12-09","cited_by_count":304},{"id":"1307.0414","title":"Challenges in Representation Learning: A report on three machine learning contests","created":"2013-07-01","cited_by_count":302},{"id":"1811.00405","title":"DialogueRNN: An Attentive RNN for Emotion Detection in Conversations","created":"2018-11-01","cited_by_count":218},{"id":"1808.02559","title":"A Joint Sequence Fusion Model for Video Question Answering and Retrieval","created":"2018-08-07","cited_by_count":208},{"id":"2007.10937","title":"MovieNet: A Holistic Dataset for Movie Understanding","created":"2020-07-21","cited_by_count":206},{"id":"1908.11540","title":"DialogueGCN: A Graph Convolutional Neural Network for Emotion Recognition in Conversation","created":"2019-08-30","cited_by_count":186},{"id":"1605.03705","title":"Movie Description","created":"2016-05-12","cited_by_count":181},{"id":"2106.11310","title":"Towards Long-Form Video Understanding","created":"2021-06-21","cited_by_count":146},{"id":"2010.02795","title":"COSMIC: COmmonSense knowledge for eMotion Identification in Conversations","created":"2020-10-06","cited_by_count":136},{"id":"2107.10834","title":"Query2Label: A Simple Transformer Way to Multi-Label Classification","created":"2021-07-22","cited_by_count":128},{"id":"1908.05913","title":"Context-Aware Emotion Recognition Networks","created":"2019-08-16","cited_by_count":99},{"id":"2005.04208","title":"Condensed Movies: Story Based Retrieval with Contextual Embeddings","created":"2020-05-08","cited_by_count":95},{"id":"2106.04632","title":"VALUE: A Multi-Task Benchmark for Video-and-Language Understanding Evaluation","created":"2021-06-08","cited_by_count":95},{"id":"2012.08695","title":"DialogXL: All-in-One XLNet for Multi-Party Conversation Emotion Recognition","created":"2020-12-16","cited_by_count":79},{"id":"1712.06761","title":"MovieGraphs: Towards Understanding Human-Centric Situations from Videos","created":"2017-12-19","cited_by_count":67},{"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":"2106.01071","title":"Topic-Driven and Knowledge-Aware Transformer for Dialogue Emotion Detection","created":"2021-06-02","cited_by_count":56},{"id":"2003.06692","title":"EmotiCon: Context-Aware Multimodal Emotion Recognition using Frege's Principle","created":"2020-03-14","cited_by_count":50},{"id":"2206.02187","title":"M2FNet: Multi-modal Fusion Network for Emotion Recognition in Conversation","created":"2022-06-05","cited_by_count":47},{"id":"1808.02212","title":"Contemplating Visual Emotions: Understanding and Overcoming Dataset Bias","created":"2018-08-07","cited_by_count":41},{"id":"1909.02144","title":"Understanding Human Gaze Communication by Spatio-Temporal Graph Reasoning","created":"2019-09-04","cited_by_count":40},{"id":"1911.09075","title":"Real-Time Emotion Recognition via Attention Gated Hierarchical Memory Network","created":"2019-11-20","cited_by_count":38},{"id":"2104.13537","title":"Shot Contrastive Self-Supervised Learning for Scene Boundary Detection","created":"2021-04-28","cited_by_count":35},{"id":"1906.05261","title":"LAEO-Net: revisiting people Looking At Each Other in videos","created":"2019-06-12","cited_by_count":34},{"id":"1910.11009","title":"A Graph-Based Framework to Bridge Movies and Synopses","created":"2019-10-24","cited_by_count":31},{"id":"2105.09939","title":"Face, Body, Voice: Video Person-Clustering with Multiple Modalities","created":"2021-05-20","cited_by_count":24},{"id":"2003.13158","title":"Learning Interactions and Relationships between Movie Characters","created":"2020-03-29","cited_by_count":22},{"id":"1801.10442","title":"From Benedict Cumberbatch to Sherlock Holmes: Character Identification in TV series without a Script","created":"2018-01-31","cited_by_count":20},{"id":"1912.05008","title":"Modeling emotion in complex stories: the Stanford Emotional Narratives Dataset","created":"2019-11-22","cited_by_count":20},{"id":"2103.06541","title":"Affect2MM: Affective Analysis of Multimedia Content Using Emotion Causality","created":"2021-03-11","cited_by_count":17},{"id":"2008.09791","title":"Identity-Aware Multi-Sentence Video Description","created":"2020-08-22","cited_by_count":13},{"id":"2208.01954","title":"Dilated Context Integrated Network with Cross-Modal Consensus for Temporal Emotion Localization in Videos","created":"2022-08-03","cited_by_count":10},{"id":"2102.05645","title":"Automated Video Labelling: Identifying Faces by Corroborative Evidence","created":"2021-02-10","cited_by_count":9},{"id":"1610.02255","title":"Learning Grimaces by Watching TV","created":"2016-10-07","cited_by_count":5},{"id":"2010.11188","title":"AttendAffectNet: Self-Attention based Networks for Predicting Affective Responses from Movies","created":"2020-10-21","cited_by_count":4}],"next_cursor":null}