{"list":"other","total":80,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"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":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"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":"2011.13456","title":"Score-Based Generative Modeling through Stochastic Differential Equations","created":"2020-11-26","cited_by_count":9122},{"id":"2105.05233","title":"Diffusion Models Beat GANs on Image Synthesis","created":"2021-05-11","cited_by_count":8255},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"id":"2207.12598","title":"Classifier-Free Diffusion Guidance","created":"2022-07-26","cited_by_count":5847},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"2210.02303","title":"Imagen Video: High Definition Video Generation with Diffusion Models","created":"2022-10-05","cited_by_count":1778},{"id":"2209.14792","title":"Make-A-Video: Text-to-Video Generation without Text-Video Data","created":"2022-09-29","cited_by_count":1742},{"id":"1908.07919","title":"Deep High-Resolution Representation Learning for Visual Recognition","created":"2019-08-20","cited_by_count":1420},{"id":"2009.09761","title":"DiffWave: A Versatile Diffusion Model for Audio Synthesis","created":"2020-09-21","cited_by_count":1354},{"id":"1708.04896","title":"Random Erasing Data Augmentation","created":"2017-08-16","cited_by_count":1239},{"id":"2111.09883","title":"Swin Transformer V2: Scaling Up Capacity and Resolution","created":"2021-11-18","cited_by_count":1228},{"id":"2106.15282","title":"Cascaded Diffusion Models for High Fidelity Image Generation","created":"2021-05-30","cited_by_count":1163},{"id":"1703.07737","title":"In Defense of the Triplet Loss for Person Re-Identification","created":"2017-03-22","cited_by_count":786},{"id":"2311.17117","title":"Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation","created":"2023-11-28","cited_by_count":688},{"id":"2001.04193","title":"Deep Learning for Person Re-identification: A Survey and Outlook","created":"2020-01-13","cited_by_count":549},{"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":"2105.06337","title":"Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speech","created":"2021-05-13","cited_by_count":447},{"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":"2211.09788","title":"DiffusionDet: Diffusion Model for Object Detection","created":"2022-11-17","cited_by_count":354},{"id":"2311.16498","title":"MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model","created":"2023-11-27","cited_by_count":330},{"id":"2309.15818","title":"Show-1: Marrying Pixel and Latent Diffusion Models for Text-to-Video Generation","created":"2023-09-27","cited_by_count":302},{"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":"2112.00390","title":"SegDiff: Image Segmentation with Diffusion Probabilistic Models","created":"2021-12-01","cited_by_count":280},{"id":"2403.14781","title":"Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidance","created":"2024-03-21","cited_by_count":272},{"id":"2203.04306","title":"Diffusion Models for Medical Anomaly Detection","created":"2022-03-08","cited_by_count":232},{"id":"1904.07223","title":"Joint Discriminative and Generative Learning for Person Re-identification","created":"2019-04-15","cited_by_count":213},{"id":"2303.06555","title":"One Transformer Fits All Distributions in Multi-Modal Diffusion at Scale","created":"2023-03-12","cited_by_count":187},{"id":"2211.13977","title":"CLIP-ReID: Exploiting Vision-Language Model for Image Re-Identification without Concrete Text Labels","created":"2022-11-25","cited_by_count":181},{"id":"2006.02631","title":"FastReID: A Pytorch Toolbox for General Instance Re-identification","created":"2020-06-04","cited_by_count":166},{"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":"2201.00308","title":"DiffuseVAE: Efficient, Controllable and High-Fidelity Generation from Low-Dimensional Latents","created":"2022-01-02","cited_by_count":104},{"id":"2210.06366","title":"A Generalist Framework for Panoptic Segmentation of Images and Videos","created":"2022-10-12","cited_by_count":99},{"id":"2206.03461","title":"Fast Unsupervised Brain Anomaly Detection and Segmentation with Diffusion Models","created":"2022-06-07","cited_by_count":97},{"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":"2205.02151","title":"Dual Cross-Attention Learning for Fine-Grained Visual Categorization and Object Re-Identification","created":"2022-05-04","cited_by_count":78},{"id":"1910.06827","title":"Learning Generalisable Omni-Scale Representations for Person Re-Identification","created":"2019-10-15","cited_by_count":74},{"id":"2203.02910","title":"Exploring Dual-task Correlation for Pose Guided Person Image Generation","created":"2022-03-06","cited_by_count":68},{"id":"1907.08427","title":"VRSTC: Occlusion-Free Video Person Re-Identification","created":"2019-07-19","cited_by_count":53},{"id":"1903.09776","title":"Auto-ReID: Searching for a Part-aware ConvNet for Person Re-Identification","created":"2019-03-23","cited_by_count":51},{"id":"2104.00921","title":"AAformer: Auto-Aligned Transformer for Person Re-Identification","created":"2021-04-02","cited_by_count":48},{"id":"2402.18078","title":"Coarse-to-Fine Latent Diffusion for Pose-Guided Person Image Synthesis","created":"2024-02-28","cited_by_count":48},{"id":"2112.08740","title":"Feature Erasing and Diffusion Network for Occluded Person Re-Identification","created":"2021-12-16","cited_by_count":42},{"id":"2212.00226","title":"Learning Progressive Modality-shared Transformers for Effective Visible-Infrared Person Re-identification","created":"2022-12-01","cited_by_count":40},{"id":"1908.05024","title":"Person Re-identification in Aerial Imagery","created":"2019-08-14","cited_by_count":36},{"id":"2403.10254","title":"Magic Tokens: Select Diverse Tokens for Multi-modal Object Re-Identification","created":"2024-03-15","cited_by_count":35},{"id":"2312.09612","title":"TOP-ReID: Multi-spectral Object Re-Identification with Token Permutation","created":"2023-12-15","cited_by_count":32},{"id":"2412.10650","title":"DeMo: Decoupled Feature-Based Mixture of Experts for Multi-Modal Object Re-Identification","created":"2024-12-14","cited_by_count":29},{"id":"2503.10324","title":"IDEA: Inverted Text with Cooperative Deformable Aggregation for Multi-modal Object Re-Identification","created":"2025-03-13","cited_by_count":28},{"id":"2403.14513","title":"View-decoupled Transformer for Person Re-identification under Aerial-ground Camera Network","created":"2024-03-21","cited_by_count":23},{"id":"1910.05549","title":"Stripe-based and Attribute-aware Network: A Two-Branch Deep Model for Vehicle Re-identification","created":"2019-10-12","cited_by_count":22},{"id":"1805.08805","title":"Resource Aware Person Re-identification across Multiple Resolutions","created":"2018-05-22","cited_by_count":21},{"id":"1901.01015","title":"Vehicle Re-Identification: an Efficient Baseline Using Triplet Embedding","created":"2019-01-04","cited_by_count":21},{"id":"2401.02634","title":"AG-ReID.v2: Bridging Aerial and Ground Views for Person Re-identification","created":"2024-01-05","cited_by_count":20},{"id":"2412.10707","title":"MambaPro: Multi-Modal Object Re-Identification with Mamba Aggregation and Synergistic Prompt","created":"2024-12-14","cited_by_count":20},{"id":"1612.01345","title":"Human-In-The-Loop Person Re-Identification","created":"2016-12-05","cited_by_count":19},{"id":"1703.09474","title":"Robust Depth-based Person Re-identification","created":"2017-03-28","cited_by_count":19},{"id":"2303.08597","title":"Aerial-Ground Person Re-ID","created":"2023-03-15","cited_by_count":19},{"id":"1611.07212","title":"Recurrent Attention Models for Depth-Based Person Identification","created":"2016-11-22","cited_by_count":18},{"id":"2408.07500","title":"Cross-Platform Video Person ReID: A New Benchmark Dataset and Adaptation Approach","created":"2024-08-14","cited_by_count":17},{"id":"2503.06965","title":"SeCap: Self-Calibrating and Adaptive Prompts for Cross-view Person Re-Identification in Aerial-Ground Networks","created":"2025-03-10","cited_by_count":16},{"id":"2202.13121","title":"Person Re-identification: A Retrospective on Domain Specific Open Challenges and Future Trends","created":"2022-02-26","cited_by_count":15},{"id":"2503.08121","title":"AG-VPReID: A Challenging Large-Scale Benchmark for Aerial-Ground Video-based Person Re-Identification","created":"2025-03-11","cited_by_count":13},{"id":"2310.17218","title":"Prototypical Contrastive Learning-based CLIP Fine-tuning for Object Re-identification","created":"2023-10-26","cited_by_count":11},{"id":"2308.12712","title":"Ground-to-Aerial Person Search: Benchmark Dataset and Approach","created":"2023-08-24","cited_by_count":9},{"id":"2412.17239","title":"Unity is Strength: Unifying Convolutional and Transformeral Features for Better Person Re-Identification","created":"2024-12-23","cited_by_count":8},{"id":"2503.23722","title":"LATex: Leveraging Attribute-based Text Knowledge for Aerial-Ground Person Re-Identification","created":"2025-03-31","cited_by_count":8},{"id":"2312.07971","title":"LMD: Faster Image Reconstruction with Latent Masking Diffusion","created":"2023-12-13","cited_by_count":7},{"id":"1804.03547","title":"A real-time and unsupervised face Re-Identification system for Human-Robot Interaction","created":"2018-04-10","cited_by_count":6},{"id":"2406.12316","title":"Enhancing Visible-Infrared Person Re-identification with Modality- and Instance-aware Visual Prompt Learning","created":"2024-06-18","cited_by_count":6},{"id":"2406.16042","title":"Pose-dIVE: Pose-Diversified Augmentation with Diffusion Model for Person Re-Identification","created":"2024-06-23","cited_by_count":6},{"id":"2503.17096","title":"Multi-modal Multi-platform Person Re-Identification: Benchmark and Method","created":"2025-03-21","cited_by_count":6}],"next_cursor":null}