{"list":"other","total":54,"rows":[{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"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":"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":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"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":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"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":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418},{"id":"2012.09841","title":"Taming Transformers for High-Resolution Image Synthesis","created":"2020-12-17","cited_by_count":3253},{"id":"2303.16199","title":"LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention","created":"2023-03-28","cited_by_count":781},{"id":"2308.00692","title":"LISA: Reasoning Segmentation via Large Language Model","created":"2023-08-01","cited_by_count":776},{"id":"1707.03237","title":"Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentations","created":"2017-07-11","cited_by_count":620},{"id":"2311.03356","title":"GLaMM: Pixel Grounding Large Multimodal Model","created":"2023-11-06","cited_by_count":455},{"id":"2306.01567","title":"Segment Anything in High Quality","created":"2023-06-02","cited_by_count":376},{"id":"2312.02228","title":"PixelLM: Pixel Reasoning with Large Multimodal Model","created":"2023-12-04","cited_by_count":222},{"id":"2312.00863","title":"EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything","created":"2023-12-01","cited_by_count":188},{"id":"2312.10103","title":"GSVA: Generalized Segmentation via Multimodal Large Language Models","created":"2023-12-15","cited_by_count":154},{"id":"2406.19389","title":"OMG-LLaVA: Bridging Image-level, Object-level, Pixel-level Reasoning and Understanding","created":"2024-06-27","cited_by_count":127},{"id":"2407.11325","title":"VISA: Reasoning Video Object Segmentation via Large Language Models","created":"2024-07-16","cited_by_count":127},{"id":"1509.01329","title":"Semantic Amodal Segmentation","created":"2015-09-04","cited_by_count":103},{"id":"2403.14598","title":"PSALM: Pixelwise SegmentAtion with Large Multi-Modal Model","created":"2024-03-21","cited_by_count":101},{"id":"2004.02788","title":"Self-Supervised Scene De-occlusion","created":"2020-04-06","cited_by_count":96},{"id":"1604.08202","title":"Amodal Instance Segmentation","created":"2016-04-27","cited_by_count":63},{"id":"1804.08864","title":"Learning to See the Invisible: End-to-End Trainable Amodal Instance Segmentation","created":"2018-04-24","cited_by_count":62},{"id":"1703.10239","title":"SeGAN: Segmenting and Generating the Invisible","created":"2017-03-29","cited_by_count":60},{"id":"2404.08767","title":"LLM-Seg: Bridging Image Segmentation and Large Language Model Reasoning","created":"2024-04-12","cited_by_count":52},{"id":"2312.17247","title":"Amodal Ground Truth and Completion in the Wild","created":"2023-12-28","cited_by_count":45},{"id":"2012.05598","title":"Amodal Segmentation Based on Visible Region Segmentation and Shape Prior","created":"2020-12-10","cited_by_count":43},{"id":"2109.11103","title":"Unseen Object Amodal Instance Segmentation via Hierarchical Occlusion Modeling","created":"2021-09-23","cited_by_count":43},{"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":"2202.11542","title":"Amodal Panoptic Segmentation","created":"2022-02-23","cited_by_count":38},{"id":"2312.15540","title":"Amodal Completion via Progressive Mixed Context Diffusion","created":"2023-12-24","cited_by_count":38},{"id":"1901.00600","title":"A Remote Sensing Image Dataset for Cloud Removal","created":"2019-01-03","cited_by_count":29},{"id":"2010.13175","title":"Amodal Segmentation through Out-of-Task and Out-of-Distribution Generalization with a Bayesian Model","created":"2020-10-25","cited_by_count":29},{"id":"2308.16825","title":"Coarse-to-Fine Amodal Segmentation with Shape Prior","created":"2023-08-31","cited_by_count":29},{"id":"1908.09521","title":"Object-Driven Multi-Layer Scene Decomposition From a Single Image","created":"2019-08-26","cited_by_count":26},{"id":"1707.02432","title":"Deep Semantic Segmentation for Automated Driving: Taxonomy, Roadmap and Challenges","created":"2017-07-08","cited_by_count":24},{"id":"2104.05367","title":"Visiting the Invisible: Layer-by-Layer Completed Scene Decomposition","created":"2021-04-12","cited_by_count":23},{"id":"2108.09897","title":"A Weakly Supervised Amodal Segmenter with Boundary Uncertainty Estimation","created":"2021-08-23","cited_by_count":21},{"id":"2309.00844","title":"Domain Generalization via Balancing Training Difficulty and Model Capability","created":"2023-09-02","cited_by_count":20},{"id":"2205.04028","title":"Learning 6-DoF Object Poses to Grasp Category-level Objects by Language Instructions","created":"2022-05-09","cited_by_count":19},{"id":"2411.13019","title":"Open-World Amodal Appearance Completion","created":"2024-11-20","cited_by_count":19},{"id":"1905.12898","title":"Learning Semantics-aware Distance Map with Semantics Layering Network for Amodal Instance Segmentation","created":"2019-05-30","cited_by_count":16},{"id":"2405.07696","title":"MonoMAE: Enhancing Monocular 3D Detection through Depth-Aware Masked Autoencoders","created":"2024-05-13","cited_by_count":16},{"id":"2309.06547","title":"AmodalSynthDrive: A Synthetic Amodal Perception Dataset for Autonomous Driving","created":"2023-09-12","cited_by_count":14},{"id":"2308.13236","title":"Black-box Unsupervised Domain Adaptation with Bi-directional Atkinson-Shiffrin Memory","created":"2023-08-25","cited_by_count":11},{"id":"2311.07090","title":"CLiF-VQA: Enhancing Video Quality Assessment by Incorporating High-Level Semantic Information related to Human Feelings","created":"2023-11-13","cited_by_count":11},{"id":"2402.19144","title":"Weakly Supervised Monocular 3D Detection with a Single-View Image","created":"2024-02-29","cited_by_count":10},{"id":"2401.01642","title":"BLADE: Box-Level Supervised Amodal Segmentation through Directed Expansion","created":"2024-01-03","cited_by_count":9},{"id":"2411.13927","title":"Multimodal 3D Reasoning Segmentation with Complex Scenes","created":"2024-11-21","cited_by_count":8},{"id":"2405.16094","title":"PLUG: Revisiting Amodal Segmentation with Foundation Model and Hierarchical Focus","created":"2024-05-25","cited_by_count":4}],"next_cursor":null}