{"list":"other","total":58,"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":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1406.1078","title":"Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation","created":"2014-06-03","cited_by_count":4057},{"id":"1508.07909","title":"Neural Machine Translation of Rare Words with Subword Units","created":"2015-08-31","cited_by_count":2918},{"id":"1412.6550","title":"FitNets: Hints for Thin Deep Nets","created":"2014-12-19","cited_by_count":1653},{"id":"1708.04896","title":"Random Erasing Data Augmentation","created":"2017-08-16","cited_by_count":1239},{"id":"1603.09382","title":"Deep Networks with Stochastic Depth","created":"2016-03-30","cited_by_count":979},{"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":"2108.10904","title":"SimVLM: Simple Visual Language Model Pretraining with Weak Supervision","created":"2021-08-24","cited_by_count":647},{"id":"1912.06430","title":"End-to-End Learning of Visual Representations from Uncurated Instructional Videos","created":"2019-12-13","cited_by_count":507},{"id":"1711.08565","title":"Person Transfer GAN to Bridge Domain Gap for Person Re-Identification","created":"2017-11-23","cited_by_count":480},{"id":"1711.09349","title":"Beyond Part Models: Person Retrieval with Refined Part Pooling (and a Strong Convolutional Baseline)","created":"2017-11-26","cited_by_count":473},{"id":"2102.04378","title":"TransReID: Transformer-based Object Re-Identification","created":"2021-02-08","cited_by_count":435},{"id":"1803.08024","title":"Stacked Cross Attention for Image-Text Matching","created":"2018-03-21","cited_by_count":416},{"id":"2111.15174","title":"CRIS: CLIP-Driven Referring Image Segmentation","created":"2021-11-30","cited_by_count":353},{"id":"1804.01438","title":"Learning Discriminative Features with Multiple Granularities for Person Re-Identification","created":"2018-04-04","cited_by_count":291},{"id":"2306.00968","title":"GRES: Generalized Referring Expression Segmentation","created":"2023-06-01","cited_by_count":254},{"id":"2108.05565","title":"Vision-Language Transformer and Query Generation for Referring Segmentation","created":"2021-08-12","cited_by_count":240},{"id":"2302.01872","title":"MOSE: A New Dataset for Video Object Segmentation in Complex Scenes","created":"2023-02-03","cited_by_count":234},{"id":"2308.08544","title":"MeViS: A Large-scale Benchmark for Video Segmentation with Motion Expressions","created":"2023-08-16","cited_by_count":228},{"id":"2106.11097","title":"CLIP2Video: Mastering Video-Text Retrieval via Image CLIP","created":"2021-06-21","cited_by_count":225},{"id":"1511.06342","title":"Actor-Mimic: Deep Multitask and Transfer Reinforcement Learning","created":"2015-11-19","cited_by_count":178},{"id":"1702.05729","title":"Person Search with Natural Language Description","created":"2017-02-19","cited_by_count":149},{"id":"1711.05535","title":"Dual-Path Convolutional Image-Text Embeddings with Instance Loss","created":"2017-11-15","cited_by_count":145},{"id":"2210.15871","title":"VLT: Vision-Language Transformer and Query Generation for Referring Segmentation","created":"2022-10-28","cited_by_count":111},{"id":"2107.12666","title":"Semantically Self-Aligned Network for Text-to-Image Part-aware Person Re-identification","created":"2021-07-27","cited_by_count":110},{"id":"2110.06615","title":"CLIP4Caption: CLIP for Video Caption","created":"2021-10-13","cited_by_count":88},{"id":"2112.05142","title":"HairCLIP: Design Your Hair by Text and Reference Image","created":"2021-12-09","cited_by_count":80},{"id":"2210.10276","title":"CLIP-Driven Fine-grained Text-Image Person Re-identification","created":"2022-10-19","cited_by_count":79},{"id":"2005.07327","title":"ViTAA: Visual-Textual Attributes Alignment in Person Search by Natural Language","created":"2020-05-15","cited_by_count":78},{"id":"1908.10534","title":"Adversarial Representation Learning for Text-to-Image Matching","created":"2019-08-28","cited_by_count":65},{"id":"2208.08608","title":"See Finer, See More: Implicit Modality Alignment for Text-based Person Retrieval","created":"2022-08-18","cited_by_count":65},{"id":"1906.09610","title":"Improving Description-based Person Re-identification by Multi-granularity Image-text Alignments","created":"2019-06-23","cited_by_count":64},{"id":"2101.03036","title":"Contextual Non-Local Alignment over Full-Scale Representation for Text-Based Person Search","created":"2021-01-08","cited_by_count":62},{"id":"2207.07802","title":"Learning Granularity-Unified Representations for Text-to-Image Person Re-identification","created":"2022-07-16","cited_by_count":62},{"id":"2102.01645","title":"Generating images from caption and vice versa via CLIP-Guided Generative Latent Space Search","created":"2021-02-02","cited_by_count":57},{"id":"2105.11628","title":"TIPCB: A Simple but Effective Part-based Convolutional Baseline for Text-based Person Search","created":"2021-05-25","cited_by_count":57},{"id":"1707.01220","title":"DarkRank: Accelerating Deep Metric Learning via Cross Sample Similarities Transfer","created":"2017-07-05","cited_by_count":56},{"id":"1708.01988","title":"Identity-Aware Textual-Visual Matching with Latent Co-attention","created":"2017-08-07","cited_by_count":54},{"id":"2110.10807","title":"Text-Based Person Search with Limited Data","created":"2021-10-20","cited_by_count":54},{"id":"1809.08440","title":"Pose-Guided Multi-Granularity Attention Network for Text-Based Person Search","created":"2018-09-22","cited_by_count":52},{"id":"2209.05773","title":"CAIBC: Capturing All-round Information Beyond Color for Text-based Person Retrieval","created":"2022-09-13","cited_by_count":39},{"id":"2208.14365","title":"Image-Specific Information Suppression and Implicit Local Alignment for Text-based Person Search","created":"2022-08-30","cited_by_count":38},{"id":"2209.06209","title":"Look Before You Leap: Improving Text-based Person Retrieval by Learning A Consistent Cross-modal Common Manifold","created":"2022-09-13","cited_by_count":38},{"id":"2101.08238","title":"AXM-Net: Implicit Cross-Modal Feature Alignment for Person Re-identification","created":"2021-01-19","cited_by_count":34},{"id":"2109.07107","title":"Anchor DETR: Query Design for Transformer-Based Object Detection","created":"2021-09-15","cited_by_count":30},{"id":"2306.11087","title":"Primitive Generation and Semantic-related Alignment for Universal Zero-Shot Segmentation","created":"2023-06-19","cited_by_count":28},{"id":"2305.14335","title":"Prototype Adaption and Projection for Few- and Zero-shot 3D Point Cloud Semantic Segmentation","created":"2023-05-23","cited_by_count":26},{"id":"2103.01451","title":"Explainable Person Re-Identification with Attribute-guided Metric Distillation","created":"2021-03-02","cited_by_count":24},{"id":"2309.03558","title":"Region Generation and Assessment Network for Occluded Person Re-Identification","created":"2023-09-07","cited_by_count":20},{"id":"2212.11958","title":"Asymmetric Cross-Scale Alignment for Text-Based Person Search","created":"2022-11-26","cited_by_count":18},{"id":"2305.13173","title":"Semantic-Promoted Debiasing and Background Disambiguation for Zero-Shot Instance Segmentation","created":"2023-05-22","cited_by_count":16}],"next_cursor":null}