{"list":"other","total":102,"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":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"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":"1612.03144","title":"Feature Pyramid Networks for Object Detection","created":"2016-12-09","cited_by_count":5036},{"id":"2006.07733","title":"Bootstrap your own latent: A new approach to self-supervised Learning","created":"2020-06-13","cited_by_count":4750},{"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":"2102.05918","title":"Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision","created":"2021-02-11","cited_by_count":3864},{"id":"2011.10566","title":"Exploring Simple Siamese Representation Learning","created":"2020-11-20","cited_by_count":2866},{"id":"2106.08254","title":"BEiT: BERT Pre-Training of Image Transformers","created":"2021-06-15","cited_by_count":2375},{"id":"2003.04297","title":"Improved Baselines with Momentum Contrastive Learning","created":"2020-03-09","cited_by_count":2287},{"id":"1805.01978","title":"Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination","created":"2018-05-05","cited_by_count":1845},{"id":"2104.02057","title":"An Empirical Study of Training Self-Supervised Vision Transformers","created":"2021-04-05","cited_by_count":1616},{"id":"1612.08242","title":"YOLO9000: Better, Faster, Stronger","created":"2016-12-25","cited_by_count":1431},{"id":"1502.03044","title":"Show, Attend and Tell: Neural Image Caption Generation with Visual Attention","created":"2015-02-10","cited_by_count":1423},{"id":"2111.09886","title":"SimMIM: A Simple Framework for Masked Image Modeling","created":"2021-11-18","cited_by_count":1153},{"id":"1703.07737","title":"In Defense of the Triplet Loss for Person Re-Identification","created":"2017-03-22","cited_by_count":786},{"id":"2111.09734","title":"ClipCap: CLIP Prefix for Image Captioning","created":"2021-11-18","cited_by_count":559},{"id":"1909.11059","title":"Unified Vision-Language Pre-Training for Image Captioning and VQA","created":"2019-09-24","cited_by_count":494},{"id":"2004.01888","title":"FairMOT: On the Fairness of Detection and Re-Identification in Multiple Object Tracking","created":"2020-04-04","cited_by_count":490},{"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":"2202.03026","title":"Context Autoencoder for Self-Supervised Representation Learning","created":"2022-02-07","cited_by_count":297},{"id":"1905.00953","title":"Omni-Scale Feature Learning for Person Re-Identification","created":"2019-05-02","cited_by_count":295},{"id":"1804.01438","title":"Learning Discriminative Features with Multiple Granularities for Person Re-Identification","created":"2018-04-04","cited_by_count":291},{"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":"1701.08398","title":"Re-ranking Person Re-identification with k-reciprocal Encoding","created":"2017-01-29","cited_by_count":262},{"id":"1406.2031","title":"Detect What You Can: Detecting and Representing Objects using Holistic Models and Body Parts","created":"2014-06-08","cited_by_count":232},{"id":"1604.01850","title":"Joint Detection and Identification Feature Learning for Person Search","created":"2016-04-07","cited_by_count":190},{"id":"1910.09777","title":"Self-Correction for Human Parsing","created":"2019-10-22","cited_by_count":180},{"id":"2208.06677","title":"Adan: Adaptive Nesterov Momentum Algorithm for Faster Optimizing Deep Models","created":"2022-08-13","cited_by_count":174},{"id":"1704.01719","title":"Beyond triplet loss: a deep quadruplet network for person re-identification","created":"2017-04-06","cited_by_count":172},{"id":"1511.03339","title":"Attention to Scale: Scale-aware Semantic Image Segmentation","created":"2015-11-10","cited_by_count":169},{"id":"1604.02531","title":"Person Re-identification in the Wild","created":"2016-04-09","cited_by_count":157},{"id":"1906.08332","title":"A Strong Baseline and Batch Normalization Neck for Deep Person Re-identification","created":"2019-06-19","cited_by_count":155},{"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":"2107.06912","title":"From Show to Tell: A Survey on Deep Learning-based Image Captioning","created":"2021-07-14","cited_by_count":138},{"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":"1908.01114","title":"ABD-Net: Attentive but Diverse Person Re-Identification","created":"2019-08-03","cited_by_count":126},{"id":"2007.13467","title":"Identity-Guided Human Semantic Parsing for Person Re-Identification","created":"2020-07-27","cited_by_count":118},{"id":"2108.08728","title":"Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification","created":"2021-08-19","cited_by_count":114},{"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":"1703.05446","title":"Look into Person: Self-supervised Structure-sensitive Learning and A New Benchmark for Human Parsing","created":"2017-03-16","cited_by_count":109},{"id":"2109.05534","title":"DSSL: Deep Surroundings-person Separation Learning for Text-based Person Retrieval","created":"2021-09-12","cited_by_count":102},{"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":"2012.03753","title":"Unsupervised Pre-training for Person Re-identification","created":"2020-12-07","cited_by_count":95},{"id":"1804.07094","title":"Part-Aligned Bilinear Representations for Person Re-identification","created":"2018-04-19","cited_by_count":90},{"id":"1709.09930","title":"HydraPlus-Net: Attentive Deep Features for Pedestrian Analysis","created":"2017-09-28","cited_by_count":89},{"id":"1910.12278","title":"Hierarchical Clustering with Hard-batch Triplet Loss for Person Re-identification","created":"2019-10-27","cited_by_count":83},{"id":"1904.04536","title":"Graphonomy: Universal Human Parsing via Graph Transfer Learning","created":"2019-04-09","cited_by_count":81},{"id":"1804.01984","title":"Look into Person: Joint Body Parsing & Pose Estimation Network and A New Benchmark","created":"2018-04-05","cited_by_count":79},{"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":"1908.05819","title":"Mixed High-Order Attention Network for Person Re-Identification","created":"2019-08-16","cited_by_count":65},{"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":"1809.05996","title":"Devil in the Details: Towards Accurate Single and Multiple Human Parsing","created":"2018-09-17","cited_by_count":64},{"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":"2211.03679","title":"Body Part-Based Representation Learning for Occluded Person Re-Identification","created":"2022-11-07","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":"2203.14675","title":"Part-based Pseudo Label Refinement for Unsupervised Person Re-identification","created":"2022-03-28","cited_by_count":59},{"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":"1904.01830","title":"Learning Context Graph for Person Search","created":"2019-04-03","cited_by_count":55},{"id":"1905.13143","title":"Semantics-Aligned Representation Learning for Person Re-identification","created":"2019-05-30","cited_by_count":51},{"id":"1807.09975","title":"Person Re-identification with Deep Similarity-Guided Graph Neural Network","created":"2018-07-26","cited_by_count":49},{"id":"1811.07130","title":"Batch DropBlock Network for Person Re-identification and Beyond","created":"2018-11-17","cited_by_count":45},{"id":"2103.08784","title":"LightningDOT: Pre-training Visual-Semantic Embeddings for Real-Time Image-Text Retrieval","created":"2021-03-16","cited_by_count":44},{"id":"2006.12774","title":"Surpassing Real-World Source Training Data: Random 3D Characters for Generalizable Person Re-Identification","created":"2020-06-23","cited_by_count":42},{"id":"1708.03383","title":"Joint Multi-Person Pose Estimation and Semantic Part Segmentation","created":"2017-08-10","cited_by_count":41},{"id":"2203.16533","title":"Large-Scale Pre-training for Person Re-identification with Noisy Labels","created":"2022-03-30","cited_by_count":41},{"id":"1905.01203","title":"Query-guided End-to-End Person Search","created":"2019-05-03","cited_by_count":40},{"id":"1909.00295","title":"Second-order Non-local Attention Networks for Person Re-identification","created":"2019-08-31","cited_by_count":38},{"id":"2103.10148","title":"Sequential End-to-end Network for Efficient Person Search","created":"2021-03-18","cited_by_count":38},{"id":"2001.06804","title":"Learning Compositional Neural Information Fusion for Human Parsing","created":"2020-01-19","cited_by_count":36},{"id":"2012.04268","title":"UnrealPerson: An Adaptive Pipeline towards Costless Person Re-identification","created":"2020-12-08","cited_by_count":36},{"id":"1707.06777","title":"Neural Person Search Machines","created":"2017-07-21","cited_by_count":35},{"id":"1912.07863","title":"In Defense of the Triplet Loss Again: Learning Robust Person Re-Identification with Fast Approximated Triplet Loss and Label Distillation","created":"2019-12-17","cited_by_count":34},{"id":"1711.08766","title":"Region-based Quality Estimation Network for Large-scale Person Re-identification","created":"2017-11-23","cited_by_count":33},{"id":"2105.14432","title":"TransMatcher: Deep Image Matching Through Transformers for Generalizable Person Re-identification","created":"2021-05-30","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":"2104.12961","title":"Unsupervised Multi-Source Domain Adaptation for Person Re-Identification","created":"2021-04-27","cited_by_count":30},{"id":"1911.09318","title":"Relation Network for Person Re-identification","created":"2019-11-21","cited_by_count":29},{"id":"1807.08260","title":"Macro-Micro Adversarial Network for Human Parsing","created":"2018-07-22","cited_by_count":28},{"id":"2107.03576","title":"Rethinking of Pedestrian Attribute Recognition: A Reliable Evaluation under Zero-Shot Pedestrian Identity Setting","created":"2021-07-08","cited_by_count":27},{"id":"2111.14173","title":"CDGNet: Class Distribution Guided Network for Human Parsing","created":"2021-11-28","cited_by_count":26},{"id":"1709.08553","title":"Attribute Recognition by Joint Recurrent Learning of Context and Correlation","created":"2017-09-25","cited_by_count":25},{"id":"2207.08677","title":"Label2Label: A Language Modeling Framework for Multi-Attribute Learning","created":"2022-07-18","cited_by_count":23},{"id":"1808.09102","title":"Localization Guided Learning for Pedestrian Attribute Recognition","created":"2018-08-28","cited_by_count":21},{"id":"2204.02611","title":"Cloning Outfits from Real-World Images to 3D Characters for Generalizable Person Re-Identification","created":"2022-04-06","cited_by_count":17},{"id":"2112.00317","title":"Unleashing the Potential of Unsupervised Pre-Training with Intra-Identity Regularization for Person Re-Identification","created":"2021-12-01","cited_by_count":12}],"next_cursor":"100"}