{"list":"other","total":64,"rows":[{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"id":"1702.04405","title":"ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes","created":"2017-02-14","cited_by_count":3117},{"id":"2103.13413","title":"Vision Transformers for Dense Prediction","created":"2021-03-24","cited_by_count":1803},{"id":"2312.14132","title":"DUSt3R: Geometric 3D Vision Made Easy","created":"2023-12-21","cited_by_count":1567},{"id":"2503.11651","title":"VGGT: Visual Geometry Grounded Transformer","created":"2025-03-14","cited_by_count":1539},{"id":"1907.01341","title":"Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer","created":"2019-07-02","cited_by_count":1495},{"id":"2406.09414","title":"Depth Anything V2","created":"2024-06-13","cited_by_count":1422},{"id":"2401.10891","title":"Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data","created":"2024-01-19","cited_by_count":1360},{"id":"1406.2283","title":"Depth Map Prediction from a Single Image using a Multi-Scale Deep Network","created":"2014-06-09","cited_by_count":1274},{"id":"1609.03677","title":"Unsupervised Monocular Depth Estimation with Left-Right Consistency","created":"2016-09-13","cited_by_count":820},{"id":"1610.08401","title":"Universal adversarial perturbations","created":"2016-10-26","cited_by_count":784},{"id":"1704.07813","title":"Unsupervised Learning of Depth and Ego-Motion from Video","created":"2017-04-25","cited_by_count":782},{"id":"1412.1897","title":"Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images","created":"2014-12-05","cited_by_count":776},{"id":"2311.16922","title":"Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decoding","created":"2023-11-28","cited_by_count":688},{"id":"2012.13255","title":"Intrinsic Dimensionality Explains the Effectiveness of Language Model Fine-Tuning","created":"2020-12-22","cited_by_count":671},{"id":"2302.12288","title":"ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth","created":"2023-02-23","cited_by_count":657},{"id":"2003.14338","title":"TartanAir: A Dataset to Push the Limits of Visual SLAM","created":"2020-03-31","cited_by_count":506},{"id":"2311.17911","title":"OPERA: Alleviating Hallucination in Multi-Modal Large Language Models via Over-Trust Penalty and Retrospection-Allocation","created":"2023-11-29","cited_by_count":478},{"id":"1905.02693","title":"3D Packing for Self-Supervised Monocular Depth Estimation","created":"2019-05-06","cited_by_count":439},{"id":"2410.02073","title":"Depth Pro: Sharp Monocular Metric Depth in Less Than a Second","created":"2024-10-02","cited_by_count":404},{"id":"2307.10984","title":"Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image","created":"2023-07-20","cited_by_count":365},{"id":"2109.07547","title":"RAFT-Stereo: Multilevel Recurrent Field Transforms for Stereo Matching","created":"2021-09-15","cited_by_count":353},{"id":"2312.02145","title":"Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation","created":"2023-12-04","cited_by_count":327},{"id":"1908.10553","title":"Unsupervised Scale-consistent Depth and Ego-motion Learning from Monocular Video","created":"2019-08-28","cited_by_count":244},{"id":"2303.06615","title":"Iterative Geometry Encoding Volume for Stereo Matching","created":"2023-03-12","cited_by_count":190},{"id":"1604.03901","title":"Single-Image Depth Perception in the Wild","created":"2016-04-13","cited_by_count":180},{"id":"2303.00601","title":"Multimodal Industrial Anomaly Detection via Hybrid Fusion","created":"2023-03-01","cited_by_count":139},{"id":"2210.07829","title":"Asymmetric Student-Teacher Networks for Industrial Anomaly Detection","created":"2022-10-14","cited_by_count":117},{"id":"2403.00486","title":"Selective-Stereo: Adaptive Frequency Information Selection for Stereo Matching","created":"2024-03-01","cited_by_count":99},{"id":"2311.07362","title":"Volcano: Mitigating Multimodal Hallucination through Self-Feedback Guided Revision","created":"2023-11-13","cited_by_count":98},{"id":"2203.05550","title":"Back to the Feature: Classical 3D Features are (Almost) All You Need for 3D Anomaly Detection","created":"2022-03-10","cited_by_count":93},{"id":"2001.03152","title":"Don't Judge an Object by Its Context: Learning to Overcome Contextual Bias","created":"2020-01-09","cited_by_count":91},{"id":"2309.13226","title":"Real3D-AD: A Dataset of Point Cloud Anomaly Detection","created":"2023-09-23","cited_by_count":87},{"id":"2310.05338","title":"Negative Object Presence Evaluation (NOPE) to Measure Object Hallucination in Vision-Language Models","created":"2023-10-09","cited_by_count":80},{"id":"2303.13194","title":"Complementary Pseudo Multimodal Feature for Point Cloud Anomaly Detection","created":"2023-03-23","cited_by_count":75},{"id":"2311.14897","title":"Towards Scalable 3D Anomaly Detection and Localization: A Benchmark via 3D Anomaly Synthesis and A Self-Supervised Learning Network","created":"2023-11-25","cited_by_count":67},{"id":"2202.11660","title":"Anomaly Detection in 3D Point Clouds using Deep Geometric Descriptors","created":"2022-02-23","cited_by_count":66},{"id":"2207.01203","title":"Towards Robust Referring Video Object Segmentation with Cyclic Relational Consensus","created":"2022-07-04","cited_by_count":50},{"id":"2404.06842","title":"MoCha-Stereo: Motif Channel Attention Network for Stereo Matching","created":"2024-04-10","cited_by_count":48},{"id":"2412.04472","title":"Stereo Anywhere: Robust Zero-Shot Deep Stereo Matching Even Where Either Stereo or Mono Fail","created":"2024-12-05","cited_by_count":47},{"id":"2407.10862","title":"R3D-AD: Reconstruction via Diffusion for 3D Anomaly Detection","created":"2024-07-15","cited_by_count":45},{"id":"2307.13925","title":"EasyNet: An Easy Network for 3D Industrial Anomaly Detection","created":"2023-07-26","cited_by_count":43},{"id":"2006.08602","title":"Targeted Adversarial Perturbations for Monocular Depth Prediction","created":"2020-06-12","cited_by_count":40},{"id":"2307.15052","title":"Learning Depth Estimation for Transparent and Mirror Surfaces","created":"2023-07-27","cited_by_count":34},{"id":"2301.08245","title":"Booster: a Benchmark for Depth from Images of Specular and Transparent Surfaces","created":"2023-01-19","cited_by_count":33},{"id":"2311.01117","title":"Cheating Depth: Enhancing 3D Surface Anomaly Detection via Depth Simulation","created":"2023-11-02","cited_by_count":33},{"id":"2403.17301","title":"Physical 3D Adversarial Attacks against Monocular Depth Estimation in Autonomous Driving","created":"2024-03-26","cited_by_count":32},{"id":"2403.17009","title":"Is Your LiDAR Placement Optimized for 3D Scene Understanding?","created":"2024-03-25","cited_by_count":26},{"id":"2412.14592","title":"Multi-Sensor Object Anomaly Detection: Unifying Appearance, Geometry, and Internal Properties","created":"2024-12-19","cited_by_count":26},{"id":"2310.00132","title":"QDFormer: Towards Robust Audiovisual Segmentation in Complex Environments with Quantization-based Semantic Decomposition","created":"2023-09-29","cited_by_count":20},{"id":"2403.11083","title":"Customizing Visual-Language Foundation Models for Multi-modal Anomaly Detection and Reasoning","created":"2024-03-17","cited_by_count":20},{"id":"2106.02523","title":"Hallucination In Object Detection -- A Study In Visual Part Verification","created":"2021-06-04","cited_by_count":16},{"id":"2401.03145","title":"Self-supervised Feature Adaptation for 3D Industrial Anomaly Detection","created":"2024-01-06","cited_by_count":16},{"id":"2509.12474","title":"Image Tokenizer Needs Post-Training","created":"2025-09-15","cited_by_count":12},{"id":"2503.08354","title":"Robust Latent Matters: Boosting Image Generation with Sampling Error Synthesis","created":"2025-03-11","cited_by_count":10},{"id":"2505.24431","title":"Bridging 3D Anomaly Localization and Repair via High-Quality Continuous Geometric Representation","created":"2025-05-30","cited_by_count":9},{"id":"2403.04924","title":"$\\text{R}^2$-Bench: Benchmarking the Robustness of Referring Perception Models under Perturbations","created":"2024-03-07","cited_by_count":6},{"id":"2501.14319","title":"Scalable Benchmarking and Robust Learning for Noise-Free Ego-Motion and 3D Reconstruction from Noisy Video","created":"2025-01-24","cited_by_count":6},{"id":"2207.05580","title":"Online Video Instance Segmentation via Robust Context Fusion","created":"2022-07-12","cited_by_count":5},{"id":"2411.14053","title":"Stereo Anything: Unifying Zero-shot Stereo Matching with Large-Scale Mixed Data","created":"2024-11-21","cited_by_count":5},{"id":"2112.05533","title":"Error Diagnosis of Deep Monocular Depth Estimation Models","created":"2021-11-15","cited_by_count":4},{"id":"2505.13061","title":"3D Visual Illusion Depth Estimation","created":"2025-05-19","cited_by_count":3},{"id":"2503.06014","title":"Towards Ambiguity-Free Spatial Foundation Model: Rethinking and Decoupling Depth Ambiguity","created":"2025-03-08","cited_by_count":2}],"next_cursor":null}