{"list":"other","total":64,"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":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"1406.1078","title":"Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation","created":"2014-06-03","cited_by_count":4057},{"id":"1409.3215","title":"Sequence to Sequence Learning with Neural Networks","created":"2014-09-10","cited_by_count":2986},{"id":"1904.09751","title":"The Curious Case of Neural Text Degeneration","created":"2019-04-22","cited_by_count":2916},{"id":"1411.5726","title":"CIDEr: Consensus-based Image Description Evaluation","created":"2014-11-20","cited_by_count":2046},{"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":"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":"1506.03099","title":"Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks","created":"2015-06-09","cited_by_count":803},{"id":"1804.02748","title":"Scaling Egocentric Vision: The EPIC-KITCHENS Dataset","created":"2018-04-08","cited_by_count":795},{"id":"1904.01766","title":"VideoBERT: A Joint Model for Video and Language Representation Learning","created":"2019-04-03","cited_by_count":703},{"id":"1703.09788","title":"Towards Automatic Learning of Procedures from Web Instructional Videos","created":"2017-03-28","cited_by_count":619},{"id":"1611.05267","title":"Temporal Convolutional Networks for Action Segmentation and Detection","created":"2016-11-16","cited_by_count":508},{"id":"1912.06430","title":"End-to-End Learning of Visual Representations from Uncurated Instructional Videos","created":"2019-12-13","cited_by_count":507},{"id":"1904.05046","title":"Generalizing from a Few Examples: A Survey on Few-Shot Learning","created":"2019-04-10","cited_by_count":463},{"id":"1705.02364","title":"Supervised Learning of Universal Sentence Representations from Natural Language Inference Data","created":"2017-05-05","cited_by_count":432},{"id":"1903.01945","title":"MS-TCN: Multi-Stage Temporal Convolutional Network for Action Segmentation","created":"2019-03-05","cited_by_count":373},{"id":"1603.08023","title":"How NOT To Evaluate Your Dialogue System: An Empirical Study of Unsupervised Evaluation Metrics for Dialogue Response Generation","created":"2016-03-25","cited_by_count":356},{"id":"1506.06726","title":"Skip-Thought Vectors","created":"2015-06-22","cited_by_count":322},{"id":"1903.02874","title":"COIN: A Large-scale Dataset for Comprehensive Instructional Video Analysis","created":"2019-03-07","cited_by_count":318},{"id":"1702.01806","title":"Beam Search Strategies for Neural Machine Translation","created":"2017-02-06","cited_by_count":232},{"id":"1709.04905","title":"One-Shot Visual Imitation Learning via Meta-Learning","created":"2017-09-14","cited_by_count":228},{"id":"1804.00819","title":"End-to-End Dense Video Captioning with Masked Transformer","created":"2018-04-03","cited_by_count":214},{"id":"1903.08225","title":"Cross-task weakly supervised learning from instructional videos","created":"2019-03-19","cited_by_count":199},{"id":"1506.05869","title":"A Neural Conversational Model","created":"2015-06-19","cited_by_count":196},{"id":"1810.06553","title":"Recipe1M+: A Dataset for Learning Cross-Modal Embeddings for Cooking Recipes and Food Images","created":"2018-10-14","cited_by_count":118},{"id":"1506.09215","title":"Unsupervised Learning from Narrated Instruction Videos","created":"2015-06-30","cited_by_count":116},{"id":"1804.00892","title":"When will you do what? - Anticipating Temporal Occurrences of Activities","created":"2018-04-03","cited_by_count":107},{"id":"1905.09035","title":"What Would You Expect? Anticipating Egocentric Actions with Rolling-Unrolling LSTMs and Modality Attention","created":"2019-05-22","cited_by_count":105},{"id":"1804.06557","title":"The Limits and Potentials of Deep Learning for Robotics","created":"2018-04-18","cited_by_count":104},{"id":"1810.07212","title":"Cross-Modal and Hierarchical Modeling of Video and Text","created":"2018-10-16","cited_by_count":103},{"id":"1602.03483","title":"Learning Distributed Representations of Sentences from Unlabelled Data","created":"2016-02-10","cited_by_count":91},{"id":"1502.08029","title":"Describing Videos by Exploiting Temporal Structure","created":"2015-02-27","cited_by_count":88},{"id":"1901.02598","title":"D3TW: Discriminative Differentiable Dynamic Time Warping for Weakly Supervised Action Alignment and Segmentation","created":"2019-01-09","cited_by_count":83},{"id":"2003.01455","title":"Rethinking Zero-shot Video Classification: End-to-end Training for Realistic Applications","created":"2020-03-03","cited_by_count":80},{"id":"1602.02995","title":"Segmental Spatiotemporal CNNs for Fine-grained Action Segmentation","created":"2016-02-09","cited_by_count":78},{"id":"1707.04818","title":"RED: Reinforced Encoder-Decoder Networks for Action Anticipation","created":"2017-07-16","cited_by_count":78},{"id":"1904.04189","title":"Unsupervised learning of action classes with continuous temporal embedding","created":"2019-04-08","cited_by_count":76},{"id":"1607.08584","title":"Connectionist Temporal Modeling for Weakly Supervised Action Labeling","created":"2016-07-28","cited_by_count":70},{"id":"1703.08132","title":"Weakly Supervised Action Learning with RNN based Fine-to-coarse Modeling","created":"2017-03-23","cited_by_count":70},{"id":"1803.09490","title":"Unsupervised Learning and Segmentation of Complex Activities from Video","created":"2018-03-26","cited_by_count":61},{"id":"1804.08274","title":"Jointly Localizing and Describing Events for Dense Video Captioning","created":"2018-04-23","cited_by_count":60},{"id":"1812.06164","title":"Inverse Cooking: Recipe Generation from Food Images","created":"2018-12-14","cited_by_count":47},{"id":"1605.00743","title":"Learning Attributes Equals Multi-Source Domain Generalization","created":"2016-05-03","cited_by_count":44},{"id":"1803.08460","title":"Towards Universal Representation for Unseen Action Recognition","created":"2018-03-22","cited_by_count":44},{"id":"1812.02501","title":"Zero-Shot Anticipation for Instructional Activities","created":"2018-12-06","cited_by_count":43},{"id":"1905.01273","title":"Learning Cross-Modal Embeddings with Adversarial Networks for Cooking Recipes and Food Images","created":"2019-05-03","cited_by_count":39},{"id":"1804.11146","title":"Cross-Modal Retrieval in the Cooking Context: Learning Semantic Text-Image Embeddings","created":"2018-04-30","cited_by_count":35},{"id":"2003.02498","title":"RecipeGPT: Generative Pre-training Based Cooking Recipe Generation and Evaluation System","created":"2020-03-05","cited_by_count":34},{"id":"1503.01558","title":"What's Cookin'? Interpreting Cooking Videos using Text, Speech and Vision","created":"2015-03-05","cited_by_count":31},{"id":"1805.03766","title":"Discourse-Aware Neural Rewards for Coherent Text Generation","created":"2018-05-10","cited_by_count":28},{"id":"1506.08438","title":"Unsupervised Semantic Parsing of Video Collections","created":"2015-06-28","cited_by_count":26},{"id":"2004.07711","title":"Knowledge Distillation for Action Anticipation via Label Smoothing","created":"2020-04-16","cited_by_count":21},{"id":"1901.00484","title":"Action2Vec: A Crossmodal Embedding Approach to Action Learning","created":"2019-01-02","cited_by_count":19},{"id":"2006.03201","title":"Egocentric Object Manipulation Graphs","created":"2020-06-05","cited_by_count":17},{"id":"2005.09606","title":"A Recipe for Creating Multimodal Aligned Datasets for Sequential Tasks","created":"2020-05-19","cited_by_count":15},{"id":"1911.10967","title":"Forecasting Human-Object Interaction: Joint Prediction of Motor Attention and Actions in First Person Video","created":"2019-11-25","cited_by_count":14},{"id":"1503.00064","title":"Generating Multi-Sentence Lingual Descriptions of Indoor Scenes","created":"2015-02-28","cited_by_count":3},{"id":"1801.07239","title":"Food recognition and recipe analysis: integrating visual content, context and external knowledge","created":"2018-01-22","cited_by_count":3},{"id":"1908.00943","title":"Prediction and Description of Near-Future Activities in Video","created":"2019-08-02","cited_by_count":3},{"id":"1512.04208","title":"Watch-Bot: Unsupervised Learning for Reminding Humans of Forgotten Actions","created":"2015-12-14","cited_by_count":1},{"id":"1905.03578","title":"Learning Representations for Predicting Future Activities","created":"2019-05-09","cited_by_count":1}],"next_cursor":null}