{"list":"other","total":57,"rows":[{"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":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"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":"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":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"id":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"2303.05499","title":"Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection","created":"2023-03-09","cited_by_count":3332},{"id":"1504.08083","title":"Fast R-CNN","created":"2015-04-30","cited_by_count":2933},{"id":"1602.07332","title":"Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations","created":"2016-02-23","cited_by_count":2656},{"id":"1311.2524","title":"Rich feature hierarchies for accurate object detection and semantic segmentation","created":"2013-11-11","cited_by_count":2162},{"id":"2203.03605","title":"DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection","created":"2022-03-07","cited_by_count":1319},{"id":"1712.00726","title":"Cascade R-CNN: Delving into High Quality Object Detection","created":"2017-12-03","cited_by_count":1276},{"id":"2112.03857","title":"Grounded Language-Image Pre-training","created":"2021-12-07","cited_by_count":1156},{"id":"2303.15389","title":"EVA-CLIP: Improved Training Techniques for CLIP at Scale","created":"2023-03-27","cited_by_count":798},{"id":"2401.12168","title":"SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities","created":"2024-01-22","cited_by_count":706},{"id":"2309.17421","title":"The Dawn of LMMs: Preliminary Explorations with GPT-4V(ision)","created":"2023-09-29","cited_by_count":681},{"id":"2201.12329","title":"DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETR","created":"2022-01-28","cited_by_count":573},{"id":"2210.04150","title":"Open-Vocabulary Semantic Segmentation with Mask-adapted CLIP","created":"2022-10-09","cited_by_count":565},{"id":"2304.06718","title":"Segment Everything Everywhere All at Once","created":"2023-04-13","cited_by_count":548},{"id":"2401.17270","title":"YOLO-World: Real-Time Open-Vocabulary Object Detection","created":"2024-01-30","cited_by_count":503},{"id":"2108.06152","title":"Conditional DETR for Fast Training Convergence","created":"2021-08-13","cited_by_count":424},{"id":"1904.12584","title":"The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Sentences From Natural Supervision","created":"2019-04-26","cited_by_count":372},{"id":"1810.02338","title":"Neural-Symbolic VQA: Disentangling Reasoning from Vision and Language Understanding","created":"2018-10-04","cited_by_count":304},{"id":"2212.05598","title":"Recurrent Vision Transformers for Object Detection with Event Cameras","created":"2022-12-11","cited_by_count":159},{"id":"1905.06088","title":"Neural-Symbolic Computing: An Effective Methodology for Principled Integration of Machine Learning and Reasoning","created":"2019-05-15","cited_by_count":151},{"id":"2207.13080","title":"DETRs with Hybrid Matching","created":"2022-07-26","cited_by_count":150},{"id":"2112.01513","title":"OW-DETR: Open-world Detection Transformer","created":"2021-12-02","cited_by_count":129},{"id":"1812.01855","title":"Explainable and Explicit Visual Reasoning over Scene Graphs","created":"2018-12-05","cited_by_count":103},{"id":"2001.02314","title":"Bridging Knowledge Graphs to Generate Scene Graphs","created":"2020-01-07","cited_by_count":86},{"id":"2008.12328","title":"A Background-Agnostic Framework with Adversarial Training for Abnormal Event Detection in Video","created":"2020-08-27","cited_by_count":86},{"id":"2402.16846","title":"GROUNDHOG: Grounding Large Language Models to Holistic Segmentation","created":"2024-02-26","cited_by_count":70},{"id":"2312.02153","title":"Aligning and Prompting Everything All at Once for Universal Visual Perception","created":"2023-12-04","cited_by_count":60},{"id":"2212.01424","title":"PROB: Probabilistic Objectness for Open World Object Detection","created":"2022-12-02","cited_by_count":57},{"id":"2404.00906","title":"From Pixels to Graphs: Open-Vocabulary Scene Graph Generation with Vision-Language Models","created":"2024-04-01","cited_by_count":43},{"id":"2303.05047","title":"Diversity-Measurable Anomaly Detection","created":"2023-03-09","cited_by_count":41},{"id":"2308.04047","title":"SODFormer: Streaming Object Detection with Transformer Using Events and Frames","created":"2023-08-08","cited_by_count":39},{"id":"2112.01698","title":"Learning to Detect Every Thing in an Open World","created":"2021-12-03","cited_by_count":37},{"id":"2210.17041","title":"GPS: Genetic Prompt Search for Efficient Few-shot Learning","created":"2022-10-31","cited_by_count":37},{"id":"2306.12041","title":"Self-Distilled Masked Auto-Encoders are Efficient Video Anomaly Detectors","created":"2023-06-21","cited_by_count":37},{"id":"2404.10193","title":"Consistency and Uncertainty: Identifying Unreliable Responses From Black-Box Vision-Language Models for Selective Visual Question Answering","created":"2024-04-16","cited_by_count":32},{"id":"2205.01297","title":"RU-Net: Regularized Unrolling Network for Scene Graph Generation","created":"2022-05-03","cited_by_count":28},{"id":"2311.09817","title":"Neural-Logic Human-Object Interaction Detection","created":"2023-11-16","cited_by_count":25},{"id":"2208.11602","title":"Motion Robust High-Speed Light-Weighted Object Detection With Event Camera","created":"2022-08-24","cited_by_count":23},{"id":"2303.09919","title":"Dual Memory Aggregation Network for Event-Based Object Detection with Learnable Representation","created":"2023-03-17","cited_by_count":16},{"id":"2106.08613","title":"FastAno: Fast Anomaly Detection via Spatio-temporal Patch Transformation","created":"2021-06-16","cited_by_count":15},{"id":"2311.11904","title":"LLMs as Visual Explainers: Advancing Image Classification with Evolving Visual Descriptions","created":"2023-11-20","cited_by_count":11},{"id":"2410.00447","title":"Scene Graph Disentanglement and Composition for Generalizable Complex Image Generation","created":"2024-10-01","cited_by_count":11},{"id":"2311.08364","title":"Plum: Prompt Learning using Metaheuristic","created":"2023-11-14","cited_by_count":8},{"id":"2303.02635","title":"VTQA: Visual Text Question Answering via Entity Alignment and Cross-Media Reasoning","created":"2023-03-05","cited_by_count":7},{"id":"2309.07403","title":"Flexible Visual Recognition by Evidential Modeling of Confusion and Ignorance","created":"2023-09-14","cited_by_count":6},{"id":"2304.09789","title":"Automatic Interaction and Activity Recognition from Videos of Human Manual Demonstrations with Application to Anomaly Detection","created":"2023-04-19","cited_by_count":3}],"next_cursor":null}