{"list":"other","total":108,"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":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"2102.05918","title":"Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision","created":"2021-02-11","cited_by_count":3864},{"id":"2208.01626","title":"Prompt-to-Prompt Image Editing with Cross Attention Control","created":"2022-08-02","cited_by_count":2431},{"id":"2107.07651","title":"Align before Fuse: Vision and Language Representation Learning with Momentum Distillation","created":"2021-07-16","cited_by_count":1619},{"id":"2102.08981","title":"Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts","created":"2021-02-17","cited_by_count":1216},{"id":"1812.08008","title":"OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields","created":"2018-12-18","cited_by_count":1162},{"id":"1411.4555","title":"Show and Tell: A Neural Image Caption Generator","created":"2014-11-17","cited_by_count":879},{"id":"1703.07737","title":"In Defense of the Triplet Loss for Person Re-Identification","created":"2017-03-22","cited_by_count":786},{"id":"1811.10830","title":"From Recognition to Cognition: Visual Commonsense Reasoning","created":"2018-11-27","cited_by_count":556},{"id":"2001.04193","title":"Deep Learning for Person Re-identification: A Survey and Outlook","created":"2020-01-13","cited_by_count":549},{"id":"2208.10442","title":"Image as a Foreign Language: BEiT Pretraining for All Vision and Vision-Language Tasks","created":"2022-08-22","cited_by_count":511},{"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":"1511.06452","title":"Deep Metric Learning via Lifted Structured Feature Embedding","created":"2015-11-19","cited_by_count":449},{"id":"1803.08024","title":"Stacked Cross Attention for Image-Text Matching","created":"2018-03-21","cited_by_count":416},{"id":"1807.09441","title":"Two at Once: Enhancing Learning and Generalization Capacities via IBN-Net","created":"2018-07-25","cited_by_count":364},{"id":"2208.02816","title":"Expanding Language-Image Pretrained Models for General Video Recognition","created":"2022-08-04","cited_by_count":321},{"id":"2206.05836","title":"GLIPv2: Unifying Localization and Vision-Language Understanding","created":"2022-06-12","cited_by_count":275},{"id":"1404.4661","title":"Learning Fine-grained Image Similarity with Deep Ranking","created":"2014-04-17","cited_by_count":190},{"id":"1604.01850","title":"Joint Detection and Identification Feature Learning for Person Search","created":"2016-04-07","cited_by_count":190},{"id":"2104.03135","title":"Seeing Out of tHe bOx: End-to-End Pre-training for Vision-Language Representation Learning","created":"2021-04-07","cited_by_count":187},{"id":"1605.05395","title":"Learning Deep Representations of Fine-grained Visual Descriptions","created":"2016-05-17","cited_by_count":182},{"id":"1610.02984","title":"Person Re-identification: Past, Present and Future","created":"2016-10-10","cited_by_count":181},{"id":"1704.01719","title":"Beyond triplet loss: a deep quadruplet network for person re-identification","created":"2017-04-06","cited_by_count":172},{"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":"2111.06119","title":"Fine-Grained Image Analysis with Deep Learning: A Survey","created":"2021-11-11","cited_by_count":135},{"id":"2303.12501","title":"Cross-Modal Implicit Relation Reasoning and Aligning for Text-to-Image Person Retrieval","created":"2023-03-22","cited_by_count":132},{"id":"1804.05113","title":"Multilevel Language and Vision Integration for Text-to-Clip Retrieval","created":"2018-04-13","cited_by_count":128},{"id":"2007.13467","title":"Identity-Guided Human Semantic Parsing for Person Re-Identification","created":"2020-07-27","cited_by_count":118},{"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":"2207.07852","title":"TS2-Net: Token Shift and Selection Transformer for Text-Video Retrieval","created":"2022-07-16","cited_by_count":104},{"id":"2109.05534","title":"DSSL: Deep Surroundings-person Separation Learning for Text-based Person Retrieval","created":"2021-09-12","cited_by_count":102},{"id":"1703.07220","title":"Improving Person Re-identification by Attribute and Identity Learning","created":"2017-03-21","cited_by_count":96},{"id":"2104.00946","title":"UAV-Human: A Large Benchmark for Human Behavior Understanding with Unmanned Aerial Vehicles","created":"2021-04-02","cited_by_count":96},{"id":"2004.00277","title":"Graph Structured Network for Image-Text Matching","created":"2020-04-01","cited_by_count":93},{"id":"1709.09930","title":"HydraPlus-Net: Attentive Deep Features for Pedestrian Analysis","created":"2017-09-28","cited_by_count":89},{"id":"2106.01804","title":"E2E-VLP: End-to-End Vision-Language Pre-training Enhanced by Visual Learning","created":"2021-06-03","cited_by_count":85},{"id":"2210.10276","title":"CLIP-Driven Fine-grained Text-Image Person Re-identification","created":"2022-10-19","cited_by_count":79},{"id":"1611.05666","title":"A Discriminatively Learned CNN Embedding for Person Re-identification","created":"2016-11-17","cited_by_count":78},{"id":"2005.07327","title":"ViTAA: Visual-Textual Attributes Alignment in Person Search by Natural Language","created":"2020-05-15","cited_by_count":78},{"id":"2205.02151","title":"Dual Cross-Attention Learning for Fine-Grained Visual Categorization and Object Re-Identification","created":"2022-05-04","cited_by_count":78},{"id":"2306.02898","title":"Towards Unified Text-based Person Retrieval: A Large-scale Multi-Attribute and Language Search Benchmark","created":"2023-06-05","cited_by_count":75},{"id":"1712.02225","title":"Pose-Normalized Image Generation for Person Re-identification","created":"2017-12-06","cited_by_count":70},{"id":"2112.02466","title":"Pose-guided Feature Disentangling for Occluded Person Re-identification Based on Transformer","created":"2021-12-05","cited_by_count":68},{"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":"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":"2308.09911","title":"Noisy-Correspondence Learning for Text-to-Image Person Re-identification","created":"2023-08-19","cited_by_count":56},{"id":"1803.09882","title":"Diversity Regularized Spatiotemporal Attention for Video-based Person Re-identification","created":"2018-03-27","cited_by_count":55},{"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":"2305.13653","title":"RaSa: Relation and Sensitivity Aware Representation Learning for Text-based Person Search","created":"2023-05-23","cited_by_count":54},{"id":"1711.06420","title":"Look, Imagine and Match: Improving Textual-Visual Cross-Modal Retrieval with Generative Models","created":"2017-11-17","cited_by_count":53},{"id":"1809.08440","title":"Pose-Guided Multi-Granularity Attention Network for Text-Based Person Search","created":"2018-09-22","cited_by_count":52},{"id":"2101.09983","title":"Adversarial Text-to-Image Synthesis: A Review","created":"2021-01-25","cited_by_count":52},{"id":"1901.07474","title":"Pedestrian Attribute Recognition: A Survey","created":"2019-01-22","cited_by_count":50},{"id":"1910.04562","title":"Improving Pedestrian Attribute Recognition With Weakly-Supervised Multi-Scale Attribute-Specific Localization","created":"2019-10-10","cited_by_count":46},{"id":"1703.05693","title":"SVDNet for Pedestrian Retrieval","created":"2017-03-16","cited_by_count":43},{"id":"1811.07487","title":"Re-Identification with Consistent Attentive Siamese Networks","created":"2018-11-19","cited_by_count":40},{"id":"2112.06714","title":"Learning Semantic-Aligned Feature Representation for Text-based Person Search","created":"2021-12-13","cited_by_count":40},{"id":"1811.11405","title":"Spectral Feature Transformation for Person Re-identification","created":"2018-11-28","cited_by_count":39},{"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":"1603.07054","title":"A Richly Annotated Dataset for Pedestrian Attribute Recognition","created":"2016-03-23","cited_by_count":33},{"id":"1607.08381","title":"A Siamese Long Short-Term Memory Architecture for Human Re-Identification","created":"2016-07-28","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":"2203.09642","title":"Cascade Transformers for End-to-End Person Search","created":"2022-03-17","cited_by_count":31},{"id":"2312.03441","title":"UFineBench: Towards Text-based Person Retrieval with Ultra-fine Granularity","created":"2023-12-06","cited_by_count":30},{"id":"1808.01571","title":"Improving Deep Visual Representation for Person Re-identification by Global and Local Image-language Association","created":"2018-08-05","cited_by_count":29},{"id":"1804.01720","title":"Finding beans in burgers: Deep semantic-visual embedding with localization","created":"2018-04-05","cited_by_count":28},{"id":"2110.04764","title":"Deep learning-based person re-identification methods: A survey and outlook of recent works","created":"2021-10-10","cited_by_count":23},{"id":"2109.10498","title":"Less is More: Learning from Synthetic Data with Fine-grained Attributes for Person Re-Identification","created":"2021-09-22","cited_by_count":20},{"id":"1502.02171","title":"Person Re-identification Meets Image Search","created":"2015-02-07","cited_by_count":19},{"id":"1905.10048","title":"Beyond Intra-modality: A Survey of Heterogeneous Person Re-identification","created":"2019-05-24","cited_by_count":19},{"id":"2212.11958","title":"Asymmetric Cross-Scale Alignment for Text-Based Person Search","created":"2022-11-26","cited_by_count":18},{"id":"2202.13121","title":"Person Re-identification: A Retrospective on Domain Specific Open Challenges and Future Trends","created":"2022-02-26","cited_by_count":15},{"id":"2207.14452","title":"Deep Learning-based Occluded Person Re-identification: A Survey","created":"2022-07-29","cited_by_count":12},{"id":"2108.04533","title":"ASMR: Learning Attribute-Based Person Search with Adaptive Semantic Margin Regularizer","created":"2021-08-10","cited_by_count":11},{"id":"2109.12965","title":"Text-based Person Search in Full Images via Semantic-Driven Proposal Generation","created":"2021-09-27","cited_by_count":9},{"id":"2111.08279","title":"Keypoint Message Passing for Video-based Person Re-Identification","created":"2021-11-16","cited_by_count":8},{"id":"1912.03083","title":"Visual-Textual Association with Hardest and Semi-Hard Negative Pairs Mining for Person Search","created":"2019-12-06","cited_by_count":7},{"id":"2003.00808","title":"A Convolutional Baseline for Person Re-Identification Using Vision and Language Descriptions","created":"2020-02-20","cited_by_count":7},{"id":"2007.09609","title":"Symbiotic Adversarial Learning for Attribute-based Person Search","created":"2020-07-19","cited_by_count":7},{"id":"2303.04497","title":"Exploiting the Textual Potential from Vision-Language Pre-training for Text-based Person Search","created":"2023-03-08","cited_by_count":7},{"id":"2005.00355","title":"Survey on Reliable Deep Learning-Based Person Re-Identification Models: Are We There Yet?","created":"2020-04-30","cited_by_count":6},{"id":"2104.04991","title":"Integrating Information Theory and Adversarial Learning for Cross-modal Retrieval","created":"2021-04-11","cited_by_count":6}],"next_cursor":"100"}