{"list":"other","total":55,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"2210.11416","title":"Scaling Instruction-Finetuned Language Models","created":"2022-10-20","cited_by_count":3024},{"id":"2305.06500","title":"InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning","created":"2023-05-11","cited_by_count":2876},{"id":"1503.03832","title":"FaceNet: A Unified Embedding for Face Recognition and Clustering","created":"2015-03-12","cited_by_count":2849},{"id":"2107.07651","title":"Align before Fuse: Vision and Language Representation Learning with Momentum Distillation","created":"2021-07-16","cited_by_count":1619},{"id":"2303.16199","title":"LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention","created":"2023-03-28","cited_by_count":781},{"id":"2109.14084","title":"VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding","created":"2021-09-28","cited_by_count":602},{"id":"2001.04193","title":"Deep Learning for Person Re-identification: A Survey and Outlook","created":"2020-01-13","cited_by_count":549},{"id":"2302.14045","title":"Language Is Not All You Need: Aligning Perception with Language Models","created":"2023-02-27","cited_by_count":543},{"id":"2102.06183","title":"Less is More: ClipBERT for Video-and-Language Learning via Sparse Sampling","created":"2021-02-11","cited_by_count":484},{"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":"2005.00200","title":"HERO: Hierarchical Encoder for Video+Language Omni-representation Pre-training","created":"2020-05-01","cited_by_count":362},{"id":"1701.07717","title":"Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in vitro","created":"2017-01-26","cited_by_count":281},{"id":"2006.16228","title":"Self-Supervised MultiModal Versatile Networks","created":"2020-06-29","cited_by_count":276},{"id":"2002.06353","title":"UniVL: A Unified Video and Language Pre-Training Model for Multimodal Understanding and Generation","created":"2020-02-15","cited_by_count":259},{"id":"1802.08122","title":"Harmonious Attention Network for Person Re-Identification","created":"2018-02-22","cited_by_count":211},{"id":"1610.02984","title":"Person Re-identification: Past, Present and Future","created":"2016-10-10","cited_by_count":181},{"id":"1910.09777","title":"Self-Correction for Human Parsing","created":"2019-10-22","cited_by_count":180},{"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":"1904.02998","title":"Relation-Aware Global Attention for Person Re-identification","created":"2019-04-05","cited_by_count":124},{"id":"2105.09996","title":"VLM: Task-agnostic Video-Language Model Pre-training for Video Understanding","created":"2021-05-20","cited_by_count":102},{"id":"2011.00597","title":"COOT: Cooperative Hierarchical Transformer for Video-Text Representation Learning","created":"2020-11-01","cited_by_count":100},{"id":"2204.06890","title":"Clothes-Changing Person Re-identification with RGB Modality Only","created":"2022-04-14","cited_by_count":98},{"id":"2303.17602","title":"Beyond Appearance: a Semantic Controllable Self-Supervised Learning Framework for Human-Centric Visual Tasks","created":"2023-03-30","cited_by_count":96},{"id":"2002.02295","title":"Person Re-identification by Contour Sketch under Moderate Clothing Change","created":"2020-02-06","cited_by_count":91},{"id":"2301.06267","title":"Multimodality Helps Unimodality: Cross-Modal Few-Shot Learning with Multimodal Models","created":"2023-01-16","cited_by_count":91},{"id":"2005.12633","title":"Long-Term Cloth-Changing Person Re-identification","created":"2020-05-26","cited_by_count":85},{"id":"1907.08435","title":"Interaction-and-Aggregation Network for Person Re-identification","created":"2019-07-19","cited_by_count":80},{"id":"2303.14481","title":"Diverse Embedding Expansion Network and Low-Light Cross-Modality Benchmark for Visible-Infrared Person Re-identification","created":"2023-03-25","cited_by_count":79},{"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":"2103.15537","title":"Cloth-Changing Person Re-identification from A Single Image with Gait Prediction and Regularization","created":"2021-03-29","cited_by_count":69},{"id":"2303.02936","title":"UniHCP: A Unified Model for Human-Centric Perceptions","created":"2023-03-06","cited_by_count":59},{"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":"1905.13143","title":"Semantics-Aligned Representation Learning for Person Re-identification","created":"2019-05-30","cited_by_count":51},{"id":"2003.04070","title":"When Person Re-identification Meets Changing Clothes","created":"2020-03-09","cited_by_count":51},{"id":"2305.08386","title":"PLIP: Language-Image Pre-training for Person Representation Learning","created":"2023-05-15","cited_by_count":49},{"id":"2105.15076","title":"Large-Scale Spatio-Temporal Person Re-identification: Algorithms and Benchmark","created":"2021-05-31","cited_by_count":47},{"id":"2112.08740","title":"Feature Erasing and Diffusion Network for Occluded Person Re-Identification","created":"2021-12-16","cited_by_count":42},{"id":"2112.06714","title":"Learning Semantic-Aligned Feature Representation for Text-based Person Search","created":"2021-12-13","cited_by_count":40},{"id":"2303.05675","title":"HumanBench: Towards General Human-centric Perception with Projector Assisted Pretraining","created":"2023-03-10","cited_by_count":38},{"id":"1703.08837","title":"Person Re-Identification by Camera Correlation Aware Feature Augmentation","created":"2017-03-26","cited_by_count":35},{"id":"2005.07862","title":"COCAS: A Large-Scale Clothes Changing Person Dataset for Re-identification","created":"2020-05-16","cited_by_count":35},{"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":"2107.11522","title":"Semantic-guided Pixel Sampling for Cloth-Changing Person Re-identification","created":"2021-07-24","cited_by_count":22},{"id":"2303.18247","title":"Adaptive Sparse Pairwise Loss for Object Re-Identification","created":"2023-03-31","cited_by_count":20},{"id":"1502.02171","title":"Person Re-identification Meets Image Search","created":"2015-02-07","cited_by_count":19},{"id":"2210.15110","title":"Masked Vision-Language Transformer in Fashion","created":"2022-10-27","cited_by_count":14}],"next_cursor":null}