{"list":"other","total":51,"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":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"1506.02142","title":"Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning","created":"2015-06-06","cited_by_count":4448},{"id":"2201.12086","title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation","created":"2022-01-28","cited_by_count":4322},{"id":"1703.05175","title":"Prototypical Networks for Few-shot Learning","created":"2017-03-15","cited_by_count":3015},{"id":"1703.04977","title":"What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?","created":"2017-03-15","cited_by_count":2352},{"id":"1709.07871","title":"FiLM: Visual Reasoning with a General Conditioning Layer","created":"2017-09-22","cited_by_count":2333},{"id":"1703.07737","title":"In Defense of the Triplet Loss for Person Re-Identification","created":"2017-03-22","cited_by_count":786},{"id":"1908.03265","title":"On the Variance of the Adaptive Learning Rate and Beyond","created":"2019-08-08","cited_by_count":772},{"id":"1706.00384","title":"Deep Mutual Learning","created":"2017-06-01","cited_by_count":628},{"id":"1711.02512","title":"Fine-tuning CNN Image Retrieval with No Human Annotation","created":"2017-11-03","cited_by_count":499},{"id":"1511.06452","title":"Deep Metric Learning via Lifted Structured Feature Embedding","created":"2015-11-19","cited_by_count":449},{"id":"1804.09458","title":"Dynamic Few-Shot Visual Learning without Forgetting","created":"2018-04-25","cited_by_count":385},{"id":"1511.02274","title":"Stacked Attention Networks for Image Question Answering","created":"2015-11-07","cited_by_count":273},{"id":"2108.04024","title":"Image Retrieval on Real-life Images with Pre-trained Vision-and-Language Models","created":"2021-08-09","cited_by_count":251},{"id":"1812.07119","title":"Composing Text and Image for Image Retrieval - An Empirical Odyssey","created":"2018-12-18","cited_by_count":236},{"id":"1703.07464","title":"No Fuss Distance Metric Learning using Proxies","created":"2017-03-21","cited_by_count":226},{"id":"2003.03773","title":"Rectifying Pseudo Label Learning via Uncertainty Estimation for Domain Adaptive Semantic Segmentation","created":"2020-03-08","cited_by_count":222},{"id":"2002.12186","title":"University-1652: A Multi-view Multi-source Benchmark for Drone-based Geo-localization","created":"2020-02-27","cited_by_count":157},{"id":"2101.05068","title":"Probabilistic Embeddings for Cross-Modal Retrieval","created":"2021-01-13","cited_by_count":151},{"id":"1711.05535","title":"Dual-Path Convolutional Image-Text Embeddings with Instance Loss","created":"2017-11-15","cited_by_count":145},{"id":"1708.01311","title":"Automatic Spatially-aware Fashion Concept Discovery","created":"2017-08-03","cited_by_count":134},{"id":"2003.11339","title":"Data Uncertainty Learning in Face Recognition","created":"2020-03-25","cited_by_count":134},{"id":"1805.00145","title":"Dialog-based Interactive Image Retrieval","created":"2018-05-01","cited_by_count":84},{"id":"2203.08101","title":"ARTEMIS: Attention-based Retrieval with Text-Explicit Matching and Implicit Similarity","created":"2022-03-15","cited_by_count":83},{"id":"2109.13912","title":"PDC-Net+: Enhanced Probabilistic Dense Correspondence Network","created":"2021-09-28","cited_by_count":80},{"id":"1611.05666","title":"A Discriminatively Learned CNN Embedding for Person Re-identification","created":"2016-11-17","cited_by_count":78},{"id":"1608.01807","title":"SIFT Meets CNN: A Decade Survey of Instance Retrieval","created":"2016-08-05","cited_by_count":67},{"id":"1806.08317","title":"Fashion-Gen: The Generative Fashion Dataset and Challenge","created":"2018-06-21","cited_by_count":65},{"id":"2107.00649","title":"On the Practicality of Deterministic Epistemic Uncertainty","created":"2021-07-01","cited_by_count":62},{"id":"2006.11149","title":"Compositional Learning of Image-Text Query for Image Retrieval","created":"2020-06-19","cited_by_count":57},{"id":"1810.00319","title":"Modeling Uncertainty with Hedged Instance Embedding","created":"2018-09-30","cited_by_count":52},{"id":"2210.01738","title":"ASIF: Coupled Data Turns Unimodal Models to Multimodal Without Training","created":"2022-10-04","cited_by_count":47},{"id":"1905.12794","title":"Fashion IQ: A New Dataset Towards Retrieving Images by Natural Language Feedback","created":"2019-05-30","cited_by_count":43},{"id":"1606.01455","title":"Multimodal Residual Learning for Visual QA","created":"2016-06-05","cited_by_count":42},{"id":"2008.02693","title":"Fashion Captioning: Towards Generating Accurate Descriptions with Semantic Rewards","created":"2020-08-06","cited_by_count":38},{"id":"2011.12663","title":"Bayesian Triplet Loss: Uncertainty Quantification in Image Retrieval","created":"2020-11-25","cited_by_count":32},{"id":"2207.08150","title":"FashionViL: Fashion-Focused Vision-and-Language Representation Learning","created":"2022-07-17","cited_by_count":32},{"id":"2204.06892","title":"Implicit Sample Extension for Unsupervised Person Re-Identification","created":"2022-04-14","cited_by_count":31},{"id":"2104.03015","title":"RTIC: Residual Learning for Text and Image Composition using Graph Convolutional Network","created":"2021-04-07","cited_by_count":27},{"id":"2204.11212","title":"Progressive Learning for Image Retrieval with Hybrid-Modality Queries","created":"2022-04-24","cited_by_count":26},{"id":"2009.01485","title":"SAC: Semantic Attention Composition for Text-Conditioned Image Retrieval","created":"2020-09-03","cited_by_count":23},{"id":"2210.10362","title":"CPL: Counterfactual Prompt Learning for Vision and Language Models","created":"2022-10-19","cited_by_count":18},{"id":"2210.13440","title":"Reliability-Aware Prediction via Uncertainty Learning for Person Image Retrieval","created":"2022-10-24","cited_by_count":12},{"id":"2103.11781","title":"Dynamic Metric Learning: Towards a Scalable Metric Space to Accommodate Multiple Semantic Scales","created":"2021-03-22","cited_by_count":11},{"id":"2207.04211","title":"BOSS: Bottom-up Cross-modal Semantic Composition with Hybrid Counterfactual Training for Robust Content-based Image Retrieval","created":"2022-07-09","cited_by_count":4},{"id":"2204.09268","title":"Uncertainty-based Cross-Modal Retrieval with Probabilistic Representations","created":"2022-04-20","cited_by_count":2}],"next_cursor":null}