{"list":"other","total":54,"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":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1709.01507","title":"Squeeze-and-Excitation Networks","created":"2017-09-05","cited_by_count":4789},{"id":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"1503.03832","title":"FaceNet: A Unified Embedding for Face Recognition and Clustering","created":"2015-03-12","cited_by_count":2849},{"id":"1807.06521","title":"CBAM: Convolutional Block Attention Module","created":"2018-07-17","cited_by_count":2477},{"id":"1512.04150","title":"Learning Deep Features for Discriminative Localization","created":"2015-12-14","cited_by_count":2436},{"id":"1711.07971","title":"Non-local Neural Networks","created":"2017-11-21","cited_by_count":2293},{"id":"1707.07998","title":"Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering","created":"2017-07-25","cited_by_count":1312},{"id":"1506.04757","title":"Image-based Recommendations on Styles and Substitutes","created":"2015-06-15","cited_by_count":706},{"id":"1704.06904","title":"Residual Attention Network for Image Classification","created":"2017-04-23","cited_by_count":386},{"id":"1904.06627","title":"Multi-Similarity Loss with General Pair Weighting for Deep Metric Learning","created":"2019-04-14","cited_by_count":368},{"id":"1904.09925","title":"Attention Augmented Convolutional Networks","created":"2019-04-22","cited_by_count":363},{"id":"1708.01311","title":"Automatic Spatially-aware Fashion Concept Discovery","created":"2017-08-03","cited_by_count":134},{"id":"1611.00471","title":"Dual Attention Networks for Multimodal Reasoning and Matching","created":"2016-11-02","cited_by_count":114},{"id":"2103.11555","title":"Context-aware Biaffine Localizing Network for Temporal Sentence Grounding","created":"2021-03-22","cited_by_count":107},{"id":"1809.06181","title":"Dual Encoding for Zero-Example Video Retrieval","created":"2018-09-17","cited_by_count":85},{"id":"1805.00145","title":"Dialog-based Interactive Image Retrieval","created":"2018-05-01","cited_by_count":84},{"id":"2008.01403","title":"Jointly Cross- and Self-Modal Graph Attention Network for Query-Based Moment Localization","created":"2020-08-04","cited_by_count":74},{"id":"1707.05691","title":"Learning Fashion Compatibility with Bidirectional LSTMs","created":"2017-07-18","cited_by_count":69},{"id":"1511.05234","title":"Ask, Attend and Answer: Exploring Question-Guided Spatial Attention for Visual Question Answering","created":"2015-11-17","cited_by_count":66},{"id":"1803.09196","title":"Learning Type-Aware Embeddings for Fashion Compatibility","created":"2018-03-25","cited_by_count":61},{"id":"1704.01740","title":"Object-Part Attention Model for Fine-grained Image Classification","created":"2017-04-06","cited_by_count":54},{"id":"1505.07922","title":"Cross-domain Image Retrieval with a Dual Attribute-aware Ranking Network","created":"2015-05-29","cited_by_count":53},{"id":"1809.07053","title":"NAIS: Neural Attentive Item Similarity Model for Recommendation","created":"2018-09-19","cited_by_count":52},{"id":"1704.02792","title":"Fine-graind Image Classification via Combining Vision and Language","created":"2017-04-10","cited_by_count":51},{"id":"2007.02503","title":"Tree-Augmented Cross-Modal Encoding for Complex-Query Video Retrieval","created":"2020-07-06","cited_by_count":47},{"id":"2008.02448","title":"Fine-grained Iterative Attention Network for TemporalLanguage Localization in Videos","created":"2020-08-06","cited_by_count":46},{"id":"1604.04994","title":"Selective Convolutional Descriptor Aggregation for Fine-Grained Image Retrieval","created":"2016-04-18","cited_by_count":44},{"id":"1912.08967","title":"Fashion Outfit Complementary Item Retrieval","created":"2019-12-19","cited_by_count":42},{"id":"1709.06308","title":"Exploring Human-like Attention Supervision in Visual Question Answering","created":"2017-09-19","cited_by_count":36},{"id":"1908.08589","title":"Learning Similarity Conditions Without Explicit Supervision","created":"2019-08-22","cited_by_count":36},{"id":"1509.07473","title":"Learning Visual Clothing Style with Heterogeneous Dyadic Co-occurrences","created":"2015-09-24","cited_by_count":33},{"id":"1908.11754","title":"Fashion Retrieval via Graph Reasoning Networks on a Similarity Pyramid","created":"2019-08-30","cited_by_count":28},{"id":"1709.00340","title":"Fine-grained Visual-textual Representation Learning","created":"2017-08-31","cited_by_count":27},{"id":"1904.05005","title":"Person Re-identification with Metric Learning using Privileged Information","created":"2019-04-10","cited_by_count":20},{"id":"1907.03069","title":"Deep Learning for Fine-Grained Image Analysis: A Survey","created":"2019-07-06","cited_by_count":18},{"id":"2005.03297","title":"Knowledge Enhanced Neural Fashion Trend Forecasting","created":"2020-05-07","cited_by_count":18},{"id":"2002.02814","title":"Fine-Grained Fashion Similarity Learning by Attribute-Specific Embedding Network","created":"2020-02-07","cited_by_count":17},{"id":"1608.03016","title":"Mining Fashion Outfit Composition Using An End-to-End Deep Learning Approach on Set Data","created":"2016-08-10","cited_by_count":16},{"id":"1703.02344","title":"Deep Learning based Large Scale Visual Recommendation and Search for E-Commerce","created":"2017-03-07","cited_by_count":16},{"id":"2008.01369","title":"ExchNet: A Unified Hashing Network for Large-Scale Fine-Grained Image Retrieval","created":"2020-08-04","cited_by_count":16},{"id":"1709.01784","title":"Cross-Domain Image Retrieval with Attention Modeling","created":"2017-09-06","cited_by_count":14},{"id":"2010.08020","title":"On the Exploration of Incremental Learning for Fine-grained Image Retrieval","created":"2020-10-15","cited_by_count":12},{"id":"1908.08985","title":"Who, Where, and What to Wear? Extracting Fashion Knowledge from Social Media","created":"2019-08-12","cited_by_count":10},{"id":"1804.09979","title":"Recommending Outfits from Personal Closet","created":"2018-04-26","cited_by_count":8},{"id":"1812.10021","title":"TransNFCM: Translation-Based Neural Fashion Compatibility Modeling","created":"2018-12-25","cited_by_count":7},{"id":"1710.11446","title":"Clothing Retrieval with Visual Attention Model","created":"2017-10-31","cited_by_count":6},{"id":"1709.01305","title":"Cross-Media Similarity Evaluation for Web Image Retrieval in the Wild","created":"2017-09-05","cited_by_count":5},{"id":"2004.03815","title":"Feature Re-Learning with Data Augmentation for Video Relevance Prediction","created":"2020-04-08","cited_by_count":5},{"id":"1908.09943","title":"Fashion Image Retrieval with Capsule Networks","created":"2019-08-26","cited_by_count":3}],"next_cursor":null}