{"list":"other","total":65,"rows":[{"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":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"2305.06500","title":"InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning","created":"2023-05-11","cited_by_count":2876},{"id":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863},{"id":"2304.10592","title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","created":"2023-04-20","cited_by_count":2711},{"id":"2107.07651","title":"Align before Fuse: Vision and Language Representation Learning with Momentum Distillation","created":"2021-07-16","cited_by_count":1619},{"id":"2304.14178","title":"mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality","created":"2023-04-27","cited_by_count":1040},{"id":"1511.02283","title":"Generation and Comprehension of Unambiguous Object Descriptions","created":"2015-11-07","cited_by_count":904},{"id":"2308.00692","title":"LISA: Reasoning Segmentation via Large Language Model","created":"2023-08-01","cited_by_count":776},{"id":"2001.04193","title":"Deep Learning for Person Re-identification: A Survey and Outlook","created":"2020-01-13","cited_by_count":549},{"id":"2304.06718","title":"Segment Everything Everywhere All at Once","created":"2023-04-13","cited_by_count":548},{"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":"2311.03356","title":"GLaMM: Pixel Grounding Large Multimodal Model","created":"2023-11-06","cited_by_count":455},{"id":"2102.04378","title":"TransReID: Transformer-based Object Re-Identification","created":"2021-02-08","cited_by_count":435},{"id":"2002.10857","title":"Circle Loss: A Unified Perspective of Pair Similarity Optimization","created":"2020-02-25","cited_by_count":403},{"id":"2306.00968","title":"GRES: Generalized Referring Expression Segmentation","created":"2023-06-01","cited_by_count":254},{"id":"2312.02228","title":"PixelLM: Pixel Reasoning with Large Multimodal Model","created":"2023-12-04","cited_by_count":222},{"id":"2312.06742","title":"Honeybee: Locality-enhanced Projector for Multimodal LLM","created":"2023-12-11","cited_by_count":197},{"id":"1604.01850","title":"Joint Detection and Identification Feature Learning for Person Search","created":"2016-04-07","cited_by_count":190},{"id":"1704.01719","title":"Beyond triplet loss: a deep quadruplet network for person re-identification","created":"2017-04-06","cited_by_count":172},{"id":"1604.02531","title":"Person Re-identification in the Wild","created":"2016-04-09","cited_by_count":157},{"id":"2312.10103","title":"GSVA: Generalized Segmentation via Multimodal Large Language Models","created":"2023-12-15","cited_by_count":154},{"id":"1702.05729","title":"Person Search with Natural Language Description","created":"2017-02-19","cited_by_count":149},{"id":"1711.05535","title":"Dual-Path Convolutional Image-Text Embeddings with Instance Loss","created":"2017-11-15","cited_by_count":145},{"id":"2407.11325","title":"VISA: Reasoning Video Object Segmentation via Large Language Models","created":"2024-07-16","cited_by_count":127},{"id":"2305.14167","title":"DetGPT: Detect What You Need via Reasoning","created":"2023-05-23","cited_by_count":112},{"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":"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":"2311.11860","title":"LION : Empowering Multimodal Large Language Model with Dual-Level Visual Knowledge","created":"2023-11-20","cited_by_count":81},{"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":"1711.10378","title":"A Pose-Sensitive Embedding for Person Re-Identification with Expanded Cross Neighborhood Re-Ranking","created":"2017-11-28","cited_by_count":74},{"id":"2402.16846","title":"GROUNDHOG: Grounding Large Language Models to Holistic Segmentation","created":"2024-02-26","cited_by_count":70},{"id":"2112.02466","title":"Pose-guided Feature Disentangling for Occluded Person Re-identification Based on Transformer","created":"2021-12-05","cited_by_count":68},{"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":"2211.03679","title":"Body Part-Based Representation Learning for Occluded Person Re-Identification","created":"2022-11-07","cited_by_count":64},{"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":"2308.09911","title":"Noisy-Correspondence Learning for Text-to-Image Person Re-identification","created":"2023-08-19","cited_by_count":56},{"id":"2110.10807","title":"Text-Based Person Search with Limited Data","created":"2021-10-20","cited_by_count":54},{"id":"2305.13653","title":"RaSa: Relation and Sensitivity Aware Representation Learning for Text-based Person Search","created":"2023-05-23","cited_by_count":54},{"id":"1907.08427","title":"VRSTC: Occlusion-Free Video Person Re-Identification","created":"2019-07-19","cited_by_count":53},{"id":"1905.13143","title":"Semantics-Aligned Representation Learning for Person Re-identification","created":"2019-05-30","cited_by_count":51},{"id":"2310.00582","title":"Pink: Unveiling the Power of Referential Comprehension for Multi-modal LLMs","created":"2023-10-01","cited_by_count":47},{"id":"2203.16533","title":"Large-Scale Pre-training for Person Re-identification with Noisy Labels","created":"2022-03-30","cited_by_count":41},{"id":"2209.06209","title":"Look Before You Leap: Improving Text-based Person Retrieval by Learning A Consistent Cross-modal Common Manifold","created":"2022-09-13","cited_by_count":38},{"id":"2308.10658","title":"Learning Clothing and Pose Invariant 3D Shape Representation for Long-Term Person Re-Identification","created":"2023-08-21","cited_by_count":34},{"id":"1711.08766","title":"Region-based Quality Estimation Network for Large-scale Person Re-identification","created":"2017-11-23","cited_by_count":33},{"id":"2004.09329","title":"Robust Partial Matching for Person Search in the Wild","created":"2020-04-20","cited_by_count":30},{"id":"2303.18247","title":"Adaptive Sparse Pairwise Loss for Object Re-Identification","created":"2023-03-31","cited_by_count":20},{"id":"1905.10048","title":"Beyond Intra-modality: A Survey of Heterogeneous Person Re-identification","created":"2019-05-24","cited_by_count":19},{"id":"2309.01420","title":"Unified Pre-training with Pseudo Texts for Text-To-Image Person Re-identification","created":"2023-09-04","cited_by_count":19},{"id":"2211.04656","title":"MEVID: Multi-view Extended Videos with Identities for Video Person Re-Identification","created":"2022-11-09","cited_by_count":16},{"id":"2409.13475","title":"PLOT: Text-based Person Search with Part Slot Attention for Corresponding Part Discovery","created":"2024-09-20","cited_by_count":15},{"id":"2311.10605","title":"CA-Jaccard: Camera-aware Jaccard Distance for Person Re-identification","created":"2023-11-17","cited_by_count":8},{"id":"2308.16486","title":"Illumination Distillation Framework for Nighttime Person Re-Identification and A New Benchmark","created":"2023-08-31","cited_by_count":6},{"id":"2112.02500","title":"MovieNet-PS: A Large-Scale Person Search Dataset in the Wild","created":"2021-12-05","cited_by_count":4}],"next_cursor":null}