{"list":"other","total":66,"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":"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":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"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":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1506.02640","title":"You Only Look Once: Unified, Real-Time Object Detection","created":"2015-06-08","cited_by_count":4852},{"id":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418},{"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":"1503.03832","title":"FaceNet: A Unified Embedding for Face Recognition and Clustering","created":"2015-03-12","cited_by_count":2849},{"id":"2112.01527","title":"Masked-attention Mask Transformer for Universal Image Segmentation","created":"2021-12-02","cited_by_count":2351},{"id":"1606.04797","title":"V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation","created":"2016-06-15","cited_by_count":2292},{"id":"2109.01134","title":"Learning to Prompt for Vision-Language Models","created":"2021-09-02","cited_by_count":2281},{"id":"2203.05557","title":"Conditional Prompt Learning for Vision-Language Models","created":"2022-03-10","cited_by_count":1433},{"id":"1708.04896","title":"Random Erasing Data Augmentation","created":"2017-08-16","cited_by_count":1239},{"id":"1608.00272","title":"Modeling Context in Referring Expressions","created":"2016-07-31","cited_by_count":1063},{"id":"2306.15195","title":"Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic","created":"2023-06-27","cited_by_count":906},{"id":"2311.03079","title":"CogVLM: Visual Expert for Pretrained Language Models","created":"2023-11-06","cited_by_count":708},{"id":"2210.03117","title":"MaPLe: Multi-modal Prompt Learning","created":"2022-10-06","cited_by_count":687},{"id":"2310.07704","title":"Ferret: Refer and Ground Anything Anywhere at Any Granularity","created":"2023-10-11","cited_by_count":509},{"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":"1903.07071","title":"Bag of Tricks and A Strong Baseline for Deep Person Re-identification","created":"2019-03-17","cited_by_count":430},{"id":"1511.03416","title":"Visual7W: Grounded Question Answering in Images","created":"2015-11-11","cited_by_count":318},{"id":"2303.13283","title":"Visual-Language Prompt Tuning with Knowledge-guided Context Optimization","created":"2023-03-23","cited_by_count":308},{"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":"1608.00525","title":"Modeling Context Between Objects for Referring Expression Understanding","created":"2016-08-01","cited_by_count":251},{"id":"1802.08122","title":"Harmonious Attention Network for Person Re-Identification","created":"2018-02-22","cited_by_count":211},{"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":"2005.11037","title":"Style Normalization and Restitution for Generalizable Person Re-identification","created":"2020-05-22","cited_by_count":136},{"id":"2312.02949","title":"LLaVA-Grounding: Grounded Visual Chat with Large Multimodal Models","created":"2023-12-05","cited_by_count":113},{"id":"2012.00417","title":"Learning to Generalize Unseen Domains via Memory-based Multi-Source Meta-Learning for Person Re-Identification","created":"2020-12-01","cited_by_count":110},{"id":"2404.07973","title":"Ferret-v2: An Improved Baseline for Referring and Grounding with Large Language Models","created":"2024-04-11","cited_by_count":97},{"id":"2103.11568","title":"Cluster Contrast for Unsupervised Person Re-Identification","created":"2021-03-22","cited_by_count":89},{"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":"2011.14670","title":"Meta Batch-Instance Normalization for Generalizable Person Re-Identification","created":"2020-11-30","cited_by_count":77},{"id":"2105.09156","title":"Generalizable Person Re-identification with Relevance-aware Mixture of Experts","created":"2021-05-19","cited_by_count":77},{"id":"2012.10674","title":"Camera-aware Proxies for Unsupervised Person Re-Identification","created":"2020-12-19","cited_by_count":59},{"id":"2412.20206","title":"Toward Visual Grounding: A Survey","created":"2024-12-28","cited_by_count":52},{"id":"1803.09937","title":"Dual Attention Matching Network for Context-Aware Feature Sequence based Person Re-Identification","created":"2018-03-27","cited_by_count":50},{"id":"2104.00921","title":"AAformer: Auto-Aligned Transformer for Person Re-Identification","created":"2021-04-02","cited_by_count":48},{"id":"2104.01546","title":"Graph Sampling Based Deep Metric Learning for Generalizable Person Re-Identification","created":"2021-04-04","cited_by_count":37},{"id":"2308.03322","title":"Part-Aware Transformer for Generalizable Person Re-identification","created":"2023-08-07","cited_by_count":35},{"id":"2501.08292","title":"HALoGEN: Fantastic LLM Hallucinations and Where to Find Them","created":"2025-01-14","cited_by_count":34},{"id":"2105.14432","title":"TransMatcher: Deep Image Matching Through Transformers for Generalizable Person Re-identification","created":"2021-05-30","cited_by_count":32},{"id":"2103.15890","title":"Learning Domain Invariant Representations for Generalizable Person Re-Identification","created":"2021-03-29","cited_by_count":22},{"id":"2109.10498","title":"Less is More: Learning from Synthetic Data with Fine-grained Attributes for Person Re-Identification","created":"2021-09-22","cited_by_count":20},{"id":"2106.03720","title":"Person Re-Identification with a Locally Aware Transformer","created":"2021-06-07","cited_by_count":19},{"id":"2112.08684","title":"Mimic Embedding via Adaptive Aggregation: Learning Generalizable Person Re-identification","created":"2021-12-16","cited_by_count":19},{"id":"2308.08887","title":"Identity-Seeking Self-Supervised Representation Learning for Generalizable Person Re-identification","created":"2023-08-17","cited_by_count":13},{"id":"2409.19648","title":"OrientedFormer: An End-to-End Transformer-Based Oriented Object Detector in Remote Sensing Images","created":"2024-09-29","cited_by_count":10},{"id":"2201.05820","title":"Offline-Online Associated Camera-Aware Proxies for Unsupervised Person Re-identification","created":"2022-01-15","cited_by_count":9},{"id":"2110.11391","title":"DEX: Domain Embedding Expansion for Generalized Person Re-identification","created":"2021-10-21","cited_by_count":8},{"id":"2501.16065","title":"CILP-FGDI: Exploiting Vision-Language Model for Generalizable Person Re-Identification","created":"2025-01-27","cited_by_count":7},{"id":"2502.06619","title":"Unleashing the Potential of Pre-Trained Diffusion Models for Generalizable Person Re-Identification","created":"2025-02-10","cited_by_count":7},{"id":"2211.12280","title":"Transformer Based Multi-Grained Features for Unsupervised Person Re-Identification","created":"2022-11-22","cited_by_count":6},{"id":"2311.17629","title":"RQFormer: Rotated Query Transformer for End-to-End Oriented Object Detection","created":"2023-11-29","cited_by_count":5},{"id":"2410.08456","title":"A Unified Deep Semantic Expansion Framework for Domain-Generalized Person Re-identification","created":"2024-10-11","cited_by_count":3},{"id":"2209.05235","title":"Style Variable and Irrelevant Learning for Generalizable Person Re-identification","created":"2022-09-12","cited_by_count":2},{"id":"2409.09391","title":"Tran-GCN: A Transformer-Enhanced Graph Convolutional Network for Person Re-Identification in Monitoring Videos","created":"2024-09-14","cited_by_count":2}],"next_cursor":null}