{"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":"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":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1609.02907","title":"Semi-Supervised Classification with Graph Convolutional Networks","created":"2016-09-09","cited_by_count":11361},{"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":"2101.00190","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","created":"2021-01-01","cited_by_count":3915},{"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":"2304.10592","title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","created":"2023-04-20","cited_by_count":2711},{"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":"2210.03117","title":"MaPLe: Multi-modal Prompt Learning","created":"2022-10-06","cited_by_count":687},{"id":"2009.14119","title":"Asymmetric Loss For Multi-Label Classification","created":"2020-09-29","cited_by_count":381},{"id":"2306.11029","title":"RemoteCLIP: A Vision Language Foundation Model for Remote Sensing","created":"2023-06-19","cited_by_count":363},{"id":"1608.05167","title":"AID: A Benchmark Dataset for Performance Evaluation of Aerial Scene Classification","created":"2016-08-18","cited_by_count":347},{"id":"2205.14865","title":"Prompt-aligned Gradient for Prompt Tuning","created":"2022-05-30","cited_by_count":341},{"id":"2210.07183","title":"Visual Classification via Description from Large Language Models","created":"2022-10-13","cited_by_count":336},{"id":"1904.03582","title":"Multi-Label Image Recognition with Graph Convolutional Networks","created":"2019-04-07","cited_by_count":322},{"id":"1604.04573","title":"CNN-RNN: A Unified Framework for Multi-label Image Classification","created":"2016-04-15","cited_by_count":190},{"id":"2107.10834","title":"Query2Label: A Simple Transformer Way to Multi-Label Classification","created":"2021-07-22","cited_by_count":128},{"id":"2011.14027","title":"General Multi-label Image Classification with Transformers","created":"2020-11-27","cited_by_count":127},{"id":"1908.07325","title":"Learning Semantic-Specific Graph Representation for Multi-Label Image Recognition","created":"2019-08-20","cited_by_count":116},{"id":"2311.16090","title":"Self-correcting LLM-controlled Diffusion Models","created":"2023-11-27","cited_by_count":113},{"id":"2206.09541","title":"DualCoOp: Fast Adaptation to Multi-Label Recognition with Limited Annotations","created":"2022-06-20","cited_by_count":102},{"id":"2403.17804","title":"Improving Text-to-Image Consistency via Automatic Prompt Optimization","created":"2024-03-26","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":"2303.05657","title":"Tag2Text: Guiding Vision-Language Model via Image Tagging","created":"2023-03-10","cited_by_count":86},{"id":"1702.05891","title":"Learning Spatial Regularization with Image-level Supervisions for Multi-label Image Classification","created":"2017-02-20","cited_by_count":85},{"id":"1711.02816","title":"Multi-label Image Recognition by Recurrently Discovering Attentional Regions","created":"2017-11-08","cited_by_count":83},{"id":"2012.02994","title":"Attention-Driven Dynamic Graph Convolutional Network for Multi-Label Image Recognition","created":"2020-12-05","cited_by_count":80},{"id":"1912.07872","title":"Cross-Modality Attention with Semantic Graph Embedding for Multi-Label Classification","created":"2019-12-17","cited_by_count":79},{"id":"2111.12933","title":"ML-Decoder: Scalable and Versatile Classification Head","created":"2021-11-25","cited_by_count":79},{"id":"2210.10276","title":"CLIP-Driven Fine-grained Text-Image Person Re-identification","created":"2022-10-19","cited_by_count":79},{"id":"1911.09243","title":"Multi-Label Classification with Label Graph Superimposing","created":"2019-11-21","cited_by_count":65},{"id":"2010.00243","title":"MLRSNet: A Multi-label High Spatial Resolution Remote Sensing Dataset for Semantic Scene Understanding","created":"2020-10-01","cited_by_count":59},{"id":"2108.02456","title":"Residual Attention: A Simple but Effective Method for Multi-Label Recognition","created":"2021-08-05","cited_by_count":52},{"id":"2211.12739","title":"Texts as Images in Prompt Tuning for Multi-Label Image Recognition","created":"2022-11-23","cited_by_count":51},{"id":"1911.09996","title":"Orderless Recurrent Models for Multi-label Classification","created":"2019-11-22","cited_by_count":46},{"id":"1806.04418","title":"Quaternion Recurrent Neural Networks","created":"2018-06-12","cited_by_count":41},{"id":"2110.04722","title":"Transformer-based Dual Relation Graph for Multi-label Image Recognition","created":"2021-10-10","cited_by_count":41},{"id":"2402.04630","title":"LLMs Meet VLMs: Boost Open Vocabulary Object Detection with Fine-grained Descriptors","created":"2024-02-07","cited_by_count":40},{"id":"2307.16634","title":"CDUL: CLIP-Driven Unsupervised Learning for Multi-Label Image Classification","created":"2023-07-31","cited_by_count":39},{"id":"2403.14333","title":"CFPL-FAS: Class Free Prompt Learning for Generalizable Face Anti-spoofing","created":"2024-03-21","cited_by_count":39},{"id":"2207.01887","title":"Open-Vocabulary Multi-Label Classification via Multi-Modal Knowledge Transfer","created":"2022-07-05","cited_by_count":33},{"id":"2109.05686","title":"Spatial and Semantic Consistency Regularizations for Pedestrian Attribute Recognition","created":"2021-09-13","cited_by_count":32},{"id":"1707.05495","title":"Order-Free RNN with Visual Attention for Multi-Label Classification","created":"2017-07-18","cited_by_count":26},{"id":"2405.02077","title":"MVP-Shot: Multi-Velocity Progressive-Alignment Framework for Few-Shot Action Recognition","created":"2024-05-03","cited_by_count":25},{"id":"2312.10692","title":"Pedestrian Attribute Recognition via CLIP based Prompt Vision-Language Fusion","created":"2023-12-17","cited_by_count":24},{"id":"2308.01890","title":"DualCoOp++: Fast and Effective Adaptation to Multi-Label Recognition with Limited Annotations","created":"2023-08-03","cited_by_count":22},{"id":"2307.09066","title":"PatchCT: Aligning Patch Set and Label Set with Conditional Transport for Multi-Label Image Classification","created":"2023-07-18","cited_by_count":21},{"id":"2111.12172","title":"Multi-label Iterated Learning for Image Classification with Label Ambiguity","created":"2021-11-23","cited_by_count":19},{"id":"2304.07230","title":"PARFormer: Transformer-based Multi-Task Network for Pedestrian Attribute Recognition","created":"2023-04-14","cited_by_count":19},{"id":"2003.01043","title":"Gated Mechanism for Attention Based Multimodal Sentiment Analysis","created":"2020-02-21","cited_by_count":17},{"id":"2312.08878","title":"Domain Prompt Learning with Quaternion Networks","created":"2023-12-12","cited_by_count":17},{"id":"2401.04614","title":"Generic Knowledge Boosted Pre-training For Remote Sensing Images","created":"2024-01-09","cited_by_count":16},{"id":"2104.14762","title":"GM-MLIC: Graph Matching based Multi-Label Image Classification","created":"2021-04-30","cited_by_count":12},{"id":"2308.06453","title":"Multi-Label Knowledge Distillation","created":"2023-08-12","cited_by_count":12},{"id":"2403.02626","title":"Modeling Collaborator: Enabling Subjective Vision Classification With Minimal Human Effort via LLM Tool-Use","created":"2024-03-05","cited_by_count":9},{"id":"1509.00511","title":"Pinterest Board Recommendation for Twitter Users","created":"2015-09-01","cited_by_count":7},{"id":"2104.02846","title":"MultiScene: A Large-scale Dataset and Benchmark for Multi-scene Recognition in Single Aerial Images","created":"2021-04-07","cited_by_count":7},{"id":"2304.11275","title":"Semantic-Aware Graph Matching Mechanism for Multi-Label Image Recognition","created":"2023-04-21","cited_by_count":7},{"id":"2208.09562","title":"Open Vocabulary Multi-Label Classification with Dual-Modal Decoder on Aligned Visual-Textual Features","created":"2022-08-19","cited_by_count":6}],"next_cursor":null}