{"list":"other","total":83,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"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":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"1709.01507","title":"Squeeze-and-Excitation Networks","created":"2017-09-05","cited_by_count":4789},{"id":"2105.15203","title":"SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers","created":"2021-05-31","cited_by_count":2940},{"id":"2006.16668","title":"GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding","created":"2020-06-30","cited_by_count":1631},{"id":"2012.15840","title":"Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers","created":"2020-12-31","cited_by_count":1369},{"id":"1705.07115","title":"Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics","created":"2017-05-19","cited_by_count":1358},{"id":"1902.09212","title":"Deep High-Resolution Representation Learning for Human Pose Estimation","created":"2019-02-25","cited_by_count":1339},{"id":"2001.06782","title":"Gradient Surgery for Multi-Task Learning","created":"2020-01-19","cited_by_count":1256},{"id":"1805.07836","title":"Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labels","created":"2018-05-20","cited_by_count":997},{"id":"1804.04235","title":"Adafactor: Adaptive Learning Rates with Sublinear Memory Cost","created":"2018-04-11","cited_by_count":905},{"id":"1711.02257","title":"GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks","created":"2017-11-07","cited_by_count":834},{"id":"1810.04650","title":"Multi-Task Learning as Multi-Objective Optimization","created":"2018-10-10","cited_by_count":821},{"id":"2111.11432","title":"Florence: A New Foundation Model for Computer Vision","created":"2021-11-22","cited_by_count":804},{"id":"1703.07737","title":"In Defense of the Triplet Loss for Person Re-Identification","created":"2017-03-22","cited_by_count":786},{"id":"2202.03052","title":"OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework","created":"2022-02-07","cited_by_count":745},{"id":"1803.10704","title":"End-to-End Multi-Task Learning with Attention","created":"2018-03-28","cited_by_count":534},{"id":"2112.01526","title":"MViTv2: Improved Multiscale Vision Transformers for Classification and Detection","created":"2021-12-02","cited_by_count":519},{"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":"1804.06208","title":"Simple Baselines for Human Pose Estimation and Tracking","created":"2018-04-17","cited_by_count":502},{"id":"1611.09813","title":"Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervision","created":"2016-11-29","cited_by_count":494},{"id":"2101.08779","title":"AI Choreographer: Music Conditioned 3D Dance Generation with AIST++","created":"2021-01-21","cited_by_count":485},{"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":"1604.03539","title":"Cross-stitch Networks for Multi-task Learning","created":"2016-04-12","cited_by_count":467},{"id":"2110.14048","title":"Conflict-Averse Gradient Descent for Multi-task Learning","created":"2021-10-26","cited_by_count":459},{"id":"2204.12484","title":"ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation","created":"2022-04-26","cited_by_count":456},{"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":"1907.06987","title":"A Short Note on the Kinetics-700 Human Action Dataset","created":"2019-07-15","cited_by_count":310},{"id":"1804.01438","title":"Learning Discriminative Features with Multiple Granularities for Person Re-Identification","created":"2018-04-04","cited_by_count":291},{"id":"1805.00123","title":"CrowdHuman: A Benchmark for Detecting Human in a Crowd","created":"2018-04-30","cited_by_count":284},{"id":"1705.09368","title":"Pose Guided Person Image Generation","created":"2017-05-25","cited_by_count":251},{"id":"2001.01526","title":"Mutual Mean-Teaching: Pseudo Label Refinery for Unsupervised Domain Adaptation on Person Re-identification","created":"2020-01-06","cited_by_count":215},{"id":"1904.07223","title":"Joint Discriminative and Generative Learning for Person Re-identification","created":"2019-04-15","cited_by_count":213},{"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":"1609.02132","title":"UberNet: Training a `Universal' Convolutional Neural Network for Low-, Mid-, and High-Level Vision using Diverse Datasets and Limited Memory","created":"2016-09-07","cited_by_count":200},{"id":"2211.03375","title":"AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Time","created":"2022-11-07","cited_by_count":200},{"id":"1710.10000","title":"PoseTrack: A Benchmark for Human Pose Estimation and Tracking","created":"2017-10-27","cited_by_count":173},{"id":"1702.05693","title":"CityPersons: A Diverse Dataset for Pedestrian Detection","created":"2017-02-19","cited_by_count":172},{"id":"2110.09408","title":"HRFormer: High-Resolution Transformer for Dense Prediction","created":"2021-10-18","cited_by_count":149},{"id":"1808.00157","title":"Instance-level Human Parsing via Part Grouping Network","created":"2018-08-01","cited_by_count":134},{"id":"2012.14214","title":"TransPose: Keypoint Localization via Transformer","created":"2020-12-28","cited_by_count":126},{"id":"2006.06606","title":"What makes instance discrimination good for transfer learning?","created":"2020-06-11","cited_by_count":111},{"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":"2104.03516","title":"TokenPose: Learning Keypoint Tokens for Human Pose Estimation","created":"2021-04-08","cited_by_count":107},{"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":"2012.03753","title":"Unsupervised Pre-training for Person Re-identification","created":"2020-12-07","cited_by_count":95},{"id":"1611.05377","title":"Fully-adaptive Feature Sharing in Multi-Task Networks with Applications in Person Attribute Classification","created":"2016-11-16","cited_by_count":93},{"id":"2002.02295","title":"Person Re-identification by Contour Sketch under Moderate Clothing Change","created":"2020-02-06","cited_by_count":91},{"id":"1612.07695","title":"MultiNet: Real-time Joint Semantic Reasoning for Autonomous Driving","created":"2016-12-22","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":"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":"2003.09163","title":"Detection in Crowded Scenes: One Proposal, Multiple Predictions","created":"2020-03-20","cited_by_count":59},{"id":"2206.04674","title":"Uni-Perceiver-MoE: Learning Sparse Generalist Models with Conditional MoEs","created":"2022-06-09","cited_by_count":58},{"id":"1905.13143","title":"Semantics-Aligned Representation Learning for Person Re-identification","created":"2019-05-30","cited_by_count":51},{"id":"2105.15076","title":"Large-Scale Spatio-Temporal Person Re-identification: Algorithms and Benchmark","created":"2021-05-31","cited_by_count":47},{"id":"1909.12118","title":"WiderPerson: A Diverse Dataset for Dense Pedestrian Detection in the Wild","created":"2019-09-25","cited_by_count":39},{"id":"2207.07106","title":"Benchmarking Omni-Vision Representation through the Lens of Visual Realms","created":"2022-07-14","cited_by_count":38},{"id":"1808.00661","title":"Adaptive Temporal Encoding Network for Video Instance-level Human Parsing","created":"2018-08-02","cited_by_count":36},{"id":"2112.00496","title":"Revisiting the Transferability of Supervised Pretraining: an MLP Perspective","created":"2021-12-01","cited_by_count":36},{"id":"2012.05649","title":"Concept Generalization in Visual Representation Learning","created":"2020-12-10","cited_by_count":35},{"id":"1807.01394","title":"ModaNet: A Large-Scale Street Fashion Dataset with Polygon Annotations","created":"2018-07-03","cited_by_count":33},{"id":"2111.08687","title":"INTERN: A New Learning Paradigm Towards General Vision","created":"2021-11-16","cited_by_count":33},{"id":"2203.07669","title":"Progressive End-to-End Object Detection in Crowded Scenes","created":"2022-03-15","cited_by_count":31},{"id":"2111.14173","title":"CDGNet: Class Distribution Guided Network for Human Parsing","created":"2021-11-28","cited_by_count":26},{"id":"2203.13815","title":"Versatile Multi-Modal Pre-Training for Human-Centric Perception","created":"2022-03-25","cited_by_count":26},{"id":"2210.11940","title":"JRDB-Pose: A Large-scale Dataset for Multi-Person Pose Estimation and Tracking","created":"2022-10-20","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":"2203.12335","title":"DR.VIC: Decomposition and Reasoning for Video Individual Counting","created":"2022-03-23","cited_by_count":18},{"id":"1908.04992","title":"Memory-Based Neighbourhood Embedding for Visual Recognition","created":"2019-08-14","cited_by_count":16},{"id":"1902.06854","title":"WIDER Face and Pedestrian Challenge 2018: Methods and Results","created":"2019-02-19","cited_by_count":10},{"id":"2105.12355","title":"Multiple Domain Experts Collaborative Learning: Multi-Source Domain Generalization For Person Re-Identification","created":"2021-05-26","cited_by_count":9},{"id":"2203.08764","title":"X-Learner: Learning Cross Sources and Tasks for Universal Visual Representation","created":"2022-03-16","cited_by_count":6}],"next_cursor":null}