{"list":"other","total":52,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"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":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"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":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"2210.08402","title":"LAION-5B: An open large-scale dataset for training next generation image-text models","created":"2022-10-16","cited_by_count":4152},{"id":"2201.03545","title":"A ConvNet for the 2020s","created":"2022-01-10","cited_by_count":3579},{"id":"1811.12231","title":"ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness","created":"2018-11-29","cited_by_count":1432},{"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":"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":"1604.01850","title":"Joint Detection and Identification Feature Learning for Person Search","created":"2016-04-07","cited_by_count":190},{"id":"2303.11681","title":"DiffuMask: Synthesizing Images with Pixel-level Annotations for Semantic Segmentation Using Diffusion Models","created":"2023-03-21","cited_by_count":162},{"id":"1604.02531","title":"Person Re-identification in the Wild","created":"2016-04-09","cited_by_count":157},{"id":"2308.12469","title":"Diffuse, Attend, and Segment: Unsupervised Zero-Shot Segmentation using Stable Diffusion","created":"2023-08-23","cited_by_count":131},{"id":"2309.14303","title":"Dataset Diffusion: Diffusion-based Synthetic Dataset Generation for Pixel-Level Semantic Segmentation","created":"2023-09-25","cited_by_count":112},{"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":"1709.08325","title":"Pose-driven Deep Convolutional Model for Person Re-identification","created":"2017-09-25","cited_by_count":86},{"id":"2301.05221","title":"Open-vocabulary Object Segmentation with Diffusion Models","created":"2023-01-12","cited_by_count":82},{"id":"2309.16779","title":"Intriguing properties of generative classifiers","created":"2023-09-28","cited_by_count":52},{"id":"1807.08107","title":"Person Search via A Mask-Guided Two-Stream CNN Model","created":"2018-07-21","cited_by_count":44},{"id":"2103.11617","title":"Anchor-Free Person Search","created":"2021-03-22","cited_by_count":42},{"id":"1909.08580","title":"Re-ID Driven Localization Refinement for Person Search","created":"2019-09-18","cited_by_count":41},{"id":"1905.01203","title":"Query-guided End-to-End Person Search","created":"2019-05-03","cited_by_count":40},{"id":"1910.12003","title":"Learning Disentangled Representation for Robust Person Re-identification","created":"2019-10-26","cited_by_count":40},{"id":"2103.10148","title":"Sequential End-to-end Network for Efficient Person Search","created":"2021-03-18","cited_by_count":38},{"id":"1910.06160","title":"Mask-Guided Attention Network for Occluded Pedestrian Detection","created":"2019-10-14","cited_by_count":36},{"id":"2311.17921","title":"Do text-free diffusion models learn discriminative visual representations?","created":"2023-11-29","cited_by_count":33},{"id":"2203.09642","title":"Cascade Transformers for End-to-End Person Search","created":"2022-03-17","cited_by_count":31},{"id":"2004.09329","title":"Robust Partial Matching for Person Search in the Wild","created":"2020-04-20","cited_by_count":30},{"id":"2010.00456","title":"From Handcrafted to Deep Features for Pedestrian Detection: A Survey","created":"2020-10-01","cited_by_count":30},{"id":"1705.05552","title":"IAN: The Individual Aggregation Network for Person Search","created":"2017-05-16","cited_by_count":29},{"id":"2303.12343","title":"LD-ZNet: A Latent Diffusion Approach for Text-Based Image Segmentation","created":"2023-03-22","cited_by_count":29},{"id":"2204.03340","title":"PSTR: End-to-End One-Step Person Search With Transformers","created":"2022-04-07","cited_by_count":26},{"id":"2201.08029","title":"Domain Generalization via Frequency-domain-based Feature Disentanglement and Interaction","created":"2022-01-20","cited_by_count":21},{"id":"2307.09756","title":"Generative Prompt Model for Weakly Supervised Object Localization","created":"2023-07-19","cited_by_count":20},{"id":"2102.10795","title":"Decoupled and Memory-Reinforced Networks: Towards Effective Feature Learning for One-Step Person Search","created":"2021-02-22","cited_by_count":19},{"id":"2207.10320","title":"OIMNet++: Prototypical Normalization and Localization-aware Learning for Person Search","created":"2022-07-21","cited_by_count":12},{"id":"2403.18791","title":"Object Pose Estimation via the Aggregation of Diffusion Features","created":"2024-03-27","cited_by_count":12},{"id":"2210.12903","title":"Gallery Filter Network for Person Search","created":"2022-10-24","cited_by_count":8},{"id":"2405.02834","title":"Scene-Adaptive Person Search via Bilateral Modulations","created":"2024-05-05","cited_by_count":2}],"next_cursor":null}