{"list":"other","total":71,"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":"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":"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":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"1610.02391","title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization","created":"2016-10-07","cited_by_count":6733},{"id":"1411.4038","title":"Fully Convolutional Networks for Semantic Segmentation","created":"2014-11-14","cited_by_count":4859},{"id":"1506.02640","title":"You Only Look Once: Unified, Real-Time Object Detection","created":"2015-06-08","cited_by_count":4852},{"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":"1606.00915","title":"DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs","created":"2016-06-02","cited_by_count":3241},{"id":"1512.02325","title":"SSD: Single Shot MultiBox Detector","created":"2015-12-08","cited_by_count":3130},{"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":"2111.02114","title":"LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs","created":"2021-11-03","cited_by_count":1555},{"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":"1609.01775","title":"Performance Measures and a Data Set for Multi-Target, Multi-Camera Tracking","created":"2016-09-06","cited_by_count":692},{"id":"2011.09157","title":"Dense Contrastive Learning for Self-Supervised Visual Pre-Training","created":"2020-11-18","cited_by_count":512},{"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":"2112.12750","title":"SLIP: Self-supervision meets Language-Image Pre-training","created":"2021-12-23","cited_by_count":436},{"id":"2102.04378","title":"TransReID: Transformer-based Object Re-Identification","created":"2021-02-08","cited_by_count":435},{"id":"1903.07071","title":"Bag of Tricks and A Strong Baseline for Deep Person Re-identification","created":"2019-03-17","cited_by_count":430},{"id":"2006.06666","title":"VirTex: Learning Visual Representations from Textual Annotations","created":"2020-06-11","cited_by_count":339},{"id":"1804.01438","title":"Learning Discriminative Features with Multiple Granularities for Person Re-Identification","created":"2018-04-04","cited_by_count":291},{"id":"2006.02713","title":"Self-paced Contrastive Learning with Hybrid Memory for Domain Adaptive Object Re-ID","created":"2020-06-04","cited_by_count":212},{"id":"1702.05729","title":"Person Search with Natural Language Description","created":"2017-02-19","cited_by_count":149},{"id":"1904.02998","title":"Relation-Aware Global Attention for Person Re-identification","created":"2019-04-05","cited_by_count":124},{"id":"2106.04095","title":"Diverse Part Discovery: Occluded Person Re-identification with Part-Aware Transformer","created":"2021-06-08","cited_by_count":120},{"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":"2004.09228","title":"Unsupervised Person Re-identification via Multi-label Classification","created":"2020-04-20","cited_by_count":107},{"id":"2003.08177","title":"High-Order Information Matters: Learning Relation and Topology for Occluded Person Re-Identification","created":"2020-03-18","cited_by_count":106},{"id":"2109.05534","title":"DSSL: Deep Surroundings-person Separation Learning for Text-based Person Retrieval","created":"2021-09-12","cited_by_count":102},{"id":"2012.03753","title":"Unsupervised Pre-training for Person Re-identification","created":"2020-12-07","cited_by_count":95},{"id":"1709.09930","title":"HydraPlus-Net: Attentive Deep Features for Pedestrian Analysis","created":"2017-09-28","cited_by_count":89},{"id":"2103.11568","title":"Cluster Contrast for Unsupervised Person Re-Identification","created":"2021-03-22","cited_by_count":89},{"id":"1812.02162","title":"Dissecting Person Re-identification from the Viewpoint of Viewpoint","created":"2018-12-05","cited_by_count":83},{"id":"1910.12278","title":"Hierarchical Clustering with Hard-batch Triplet Loss for Person Re-identification","created":"2019-10-27","cited_by_count":83},{"id":"2005.07327","title":"ViTAA: Visual-Textual Attributes Alignment in Person Search by Natural Language","created":"2020-05-15","cited_by_count":78},{"id":"2004.00230","title":"Pose-guided Visible Part Matching for Occluded Person ReID","created":"2020-04-01","cited_by_count":70},{"id":"1707.07256","title":"Deeply-Learned Part-Aligned Representations for Person Re-Identification","created":"2017-07-23","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":"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":"2012.09071","title":"Joint Generative and Contrastive Learning for Unsupervised Person Re-identification","created":"2020-12-16","cited_by_count":58},{"id":"1807.03903","title":"Deep Imbalanced Attribute Classification using Visual Attention Aggregation","created":"2018-07-10","cited_by_count":56},{"id":"1905.13143","title":"Semantics-Aligned Representation Learning for Person Re-identification","created":"2019-05-30","cited_by_count":51},{"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":"1811.07130","title":"Batch DropBlock Network for Person Re-identification and Beyond","created":"2018-11-17","cited_by_count":45},{"id":"2106.06133","title":"Refining Pseudo Labels with Clustering Consensus over Generations for Unsupervised Object Re-identification","created":"2021-06-11","cited_by_count":45},{"id":"1707.00798","title":"Deep Representation Learning with Part Loss for Person Re-Identification","created":"2017-07-04","cited_by_count":44},{"id":"2111.12084","title":"Self-Supervised Pre-Training for Transformer-Based Person Re-Identification","created":"2021-11-23","cited_by_count":36},{"id":"1603.07054","title":"A Richly Annotated Dataset for Pedestrian Attribute Recognition","created":"2016-03-23","cited_by_count":33},{"id":"2109.05686","title":"Spatial and Semantic Consistency Regularizations for Pedestrian Attribute Recognition","created":"2021-09-13","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":"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":"2103.01451","title":"Explainable Person Re-Identification with Attribute-guided Metric Distillation","created":"2021-03-02","cited_by_count":24},{"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":"2009.09445","title":"Unsupervised Domain Adaptation for Person Re-Identification through Source-Guided Pseudo-Labeling","created":"2020-09-20","cited_by_count":12},{"id":"1707.06089","title":"Deep View-Sensitive Pedestrian Attribute Inference in an end-to-end Model","created":"2017-07-19","cited_by_count":10}],"next_cursor":null}