{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/object/papers/51","list_of":"/task/object","task":"Object","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":51,"pages_in_order":107,"rows_per_page":100,"rows":[5001,5100],"of":10696,"counts":{"archive_papers_tagged":10696,"with_a_code_link":3979,"where_syntology_ran_a_sample":1043,"not_listed_spam_title":0,"listed":10696,"listed_where_code_ran":1043,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":919,"every_run_a_failure_of_syntologys_instrument":124,"listed_with_a_run_with_no_instrument_failure":919,"listed_every_run_a_failure_of_syntologys_instrument":124,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/object","prev":"/task/object/papers/50","next":"/task/object/papers/52","papers":[{"url":null,"slug":"generating-human-motion-in-3d-scenes-from","title":"Generating Human Motion in 3D Scenes from Text Descriptions","date":"2024-05-13","arxiv_id":"2405.07784","repositories_listed":0,"syntology":null},{"url":null,"slug":"monomae-enhancing-monocular-3d-detection","title":"MonoMAE: Enhancing Monocular 3D Detection through Depth-Aware Masked Autoencoders","date":"2024-05-13","arxiv_id":"2405.07696","repositories_listed":0,"syntology":null},{"url":null,"slug":"ottc-object-time-to-contact-for-motion","title":"oTTC: Object Time-to-Contact for Motion Estimation in Autonomous Driving","date":"2024-05-13","arxiv_id":"2405.07698","repositories_listed":0,"syntology":null},{"url":null,"slug":"maml-mot-multiple-object-tracking-based-on","title":"MAML MOT: Multiple Object Tracking based on Meta-Learning","date":"2024-05-12","arxiv_id":"2405.07272","repositories_listed":0,"syntology":null},{"url":null,"slug":"point-resampling-and-ray-transformation-aid","title":"Point Resampling and Ray Transformation Aid to Editable NeRF Models","date":"2024-05-12","arxiv_id":"2405.07306","repositories_listed":0,"syntology":null},{"url":null,"slug":"ecar-edge-assisted-collaborative-augmented","title":"eCAR: edge-assisted Collaborative Augmented Reality Framework","date":"2024-05-11","arxiv_id":"2405.06872","repositories_listed":0,"syntology":null},{"url":null,"slug":"manifoundation-model-for-general-purpose","title":"ManiFoundation Model for General-Purpose Robotic Manipulation of Contact Synthesis with Arbitrary Objects and Robots","date":"2024-05-11","arxiv_id":"2405.06964","repositories_listed":0,"syntology":null},{"url":null,"slug":"common-corruptions-for-enhancing-and","title":"Common Corruptions for Enhancing and Evaluating Robustness in Air-to-Air Visual Object Detection","date":"2024-05-10","arxiv_id":"2405.06765","repositories_listed":0,"syntology":null},{"url":null,"slug":"ensuring-uav-safety-a-vision-only-and-real","title":"Ensuring UAV Safety: A Vision-only and Real-time Framework for Collision Avoidance Through Object Detection, Tracking, and Distance Estimation","date":"2024-05-10","arxiv_id":"2405.06749","repositories_listed":0,"syntology":null},{"url":null,"slug":"event-based-structure-from-orbit","title":"Event-based Structure-from-Orbit","date":"2024-05-10","arxiv_id":"2405.06216","repositories_listed":0,"syntology":null},{"url":null,"slug":"graphrelate3d-context-dependent-3d-object","title":"GraphRelate3D: Context-Dependent 3D Object Detection with Inter-Object Relationship Graphs","date":"2024-05-10","arxiv_id":"2405.06782","repositories_listed":0,"syntology":null},{"url":null,"slug":"how-to-augment-for-atmospheric-turbulence","title":"How to Augment for Atmospheric Turbulence Effects on Thermal Adapted Object Detection Models?","date":"2024-05-10","arxiv_id":"2405.06383","repositories_listed":0,"syntology":null},{"url":null,"slug":"residual-nerf-learning-residual-nerfs-for","title":"Residual-NeRF: Learning Residual NeRFs for Transparent Object Manipulation","date":"2024-05-10","arxiv_id":"2405.06181","repositories_listed":0,"syntology":null},{"url":null,"slug":"asgrasp-generalizable-transparent-object","title":"ASGrasp: Generalizable Transparent Object Reconstruction and 6-DoF Grasp Detection from RGB-D Active Stereo Camera","date":"2024-05-09","arxiv_id":"2405.05648","repositories_listed":0,"syntology":null},{"url":null,"slug":"composable-part-based-manipulation","title":"Composable Part-Based Manipulation","date":"2024-05-09","arxiv_id":"2405.05876","repositories_listed":0,"syntology":null},{"url":null,"slug":"depth-awakens-a-depth-perceptual-attention","title":"Depth Awakens: A Depth-perceptual Attention Fusion Network for RGB-D Camouflaged Object Detection","date":"2024-05-09","arxiv_id":"2405.05614","repositories_listed":0,"syntology":null},{"url":null,"slug":"draggaussian-enabling-drag-style-manipulation","title":"DragGaussian: Enabling Drag-style Manipulation on 3D Gaussian Representation","date":"2024-05-09","arxiv_id":"2405.05800","repositories_listed":0,"syntology":null},{"url":null,"slug":"free-moving-object-reconstruction-and-pose","title":"Free-Moving Object Reconstruction and Pose Estimation with Virtual Camera","date":"2024-05-09","arxiv_id":"2405.05858","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-object-detection-model-uses-combined","title":"The object detection model uses combined extraction with KNN and RF classification","date":"2024-05-09","arxiv_id":"2405.05551","repositories_listed":0,"syntology":null},{"url":null,"slug":"loc-zson-language-driven-object-centric-zero","title":"LOC-ZSON: Language-driven Object-Centric Zero-Shot Object Retrieval and Navigation","date":"2024-05-08","arxiv_id":"2405.05363","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-novel-wide-area-multiobject-detection","title":"A Novel Wide-Area Multiobject Detection System with High-Probability Region Searching","date":"2024-05-07","arxiv_id":"2405.04589","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-event-based-object-detection-in","title":"Deep Event-based Object Detection in Autonomous Driving: A Survey","date":"2024-05-07","arxiv_id":"2405.03995","repositories_listed":0,"syntology":null},{"url":null,"slug":"edit-your-motion-space-time-diffusion","title":"Edit-Your-Motion: Space-Time Diffusion Decoupling Learning for Video Motion Editing","date":"2024-05-07","arxiv_id":"2405.04496","repositories_listed":0,"syntology":null},{"url":null,"slug":"space-time-reinforcement-network-for-video","title":"Space-time Reinforcement Network for Video Object Segmentation","date":"2024-05-07","arxiv_id":"2405.04042","repositories_listed":0,"syntology":null},{"url":null,"slug":"badfusion-2d-oriented-backdoor-attacks","title":"BadFusion: 2D-Oriented Backdoor Attacks against 3D Object Detection","date":"2024-05-06","arxiv_id":"2405.03884","repositories_listed":0,"syntology":null},{"url":null,"slug":"collecting-consistently-high-quality-object","title":"Collecting Consistently High Quality Object Tracks with Minimal Human Involvement by Using Self-Supervised Learning to Detect Tracker Errors","date":"2024-05-06","arxiv_id":"2405.03643","repositories_listed":0,"syntology":null},{"url":null,"slug":"infrared-polarization-imaging-based-non","title":"Infrared Polarization Imaging-based Non-destructive Thermography Inspection","date":"2024-05-06","arxiv_id":"2405.03126","repositories_listed":0,"syntology":null},{"url":null,"slug":"low-light-object-detection","title":"Low-light Object Detection","date":"2024-05-06","arxiv_id":"2405.03519","repositories_listed":0,"syntology":null},{"url":null,"slug":"modality-prompts-for-arbitrary-modality","title":"Modality Prompts for Arbitrary Modality Salient Object Detection","date":"2024-05-06","arxiv_id":"2405.03351","repositories_listed":0,"syntology":null},{"url":null,"slug":"spatial-and-surface-correspondence-field-for","title":"Spatial and Surface Correspondence Field for Interaction Transfer","date":"2024-05-06","arxiv_id":"2405.03221","repositories_listed":0,"syntology":null},{"url":null,"slug":"ssyncoa-self-synchronizing-object-aligned","title":"SSyncOA: Self-synchronizing Object-aligned Watermarking to Resist Cropping-paste Attacks","date":"2024-05-06","arxiv_id":"2405.03458","repositories_listed":0,"syntology":null},{"url":null,"slug":"adaptive-guidance-learning-for-camouflaged","title":"Adaptive Guidance Learning for Camouflaged Object Detection","date":"2024-05-05","arxiv_id":"2405.02824","repositories_listed":0,"syntology":null},{"url":null,"slug":"pvtransformer-point-to-voxel-transformer-for","title":"PVTransformer: Point-to-Voxel Transformer for Scalable 3D Object Detection","date":"2024-05-05","arxiv_id":"2405.02811","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-object-states-from-actions-via-large","title":"Learning Multiple Object States from Actions via Large Language Models","date":"2024-05-02","arxiv_id":"2405.01090","repositories_listed":0,"syntology":null},{"url":null,"slug":"sparse-multi-view-hand-object-reconstruction","title":"Sparse multi-view hand-object reconstruction for unseen environments","date":"2024-05-02","arxiv_id":"2405.01353","repositories_listed":0,"syntology":null},{"url":null,"slug":"depth-priors-in-removal-neural-radiance","title":"Depth Priors in Removal Neural Radiance Fields","date":"2024-05-01","arxiv_id":"2405.00630","repositories_listed":0,"syntology":null},{"url":null,"slug":"obtaining-favorable-layouts-for-multiple","title":"Obtaining Favorable Layouts for Multiple Object Generation","date":"2024-05-01","arxiv_id":"2405.00791","repositories_listed":0,"syntology":null},{"url":null,"slug":"physical-backdoor-towards-temperature-based","title":"Physical Backdoor: Towards Temperature-based Backdoor Attacks in the Physical World","date":"2024-04-30","arxiv_id":"2404.19417","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-end-to-end-semi-supervised-table-1","title":"Towards End-to-End Semi-Supervised Table Detection with Semantic Aligned Matching Transformer","date":"2024-04-30","arxiv_id":"2405.00187","repositories_listed":0,"syntology":null},{"url":null,"slug":"distributed-stochastic-optimization-of-a","title":"Distributed Stochastic Optimization of a Neural Representation Network for Time-Space Tomography Reconstruction","date":"2024-04-29","arxiv_id":"2404.19075","repositories_listed":0,"syntology":null},{"url":null,"slug":"object-registration-in-neural-fields","title":"Object Registration in Neural Fields","date":"2024-04-29","arxiv_id":"2404.18381","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-dynamics-prediction-with-object","title":"Unsupervised Dynamics Prediction with Object-Centric Kinematics","date":"2024-04-29","arxiv_id":"2404.18423","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-hybrid-approach-for-document-layout","title":"A Hybrid Approach for Document Layout Analysis in Document images","date":"2024-04-27","arxiv_id":"2404.17888","repositories_listed":0,"syntology":null},{"url":null,"slug":"boostrad-enhancing-object-detection-by","title":"BoostRad: Enhancing Object Detection by Boosting Radar Reflections","date":"2024-04-27","arxiv_id":"2404.17861","repositories_listed":0,"syntology":null},{"url":null,"slug":"cobra-confidence-score-based-on-shape","title":"COBRA -- COnfidence score Based on shape Regression Analysis for method-independent quality assessment of object pose estimation from single images","date":"2024-04-25","arxiv_id":"2404.16471","repositories_listed":0,"syntology":null},{"url":null,"slug":"cross-domain-spatial-matching-for-camera-and","title":"Cross-Domain Spatial Matching for Camera and Radar Sensor Data Fusion in Autonomous Vehicle Perception System","date":"2024-04-25","arxiv_id":"2404.16548","repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-assembler-learning-to-generate-fine","title":"Neural Assembler: Learning to Generate Fine-Grained Robotic Assembly Instructions from Multi-View Images","date":"2024-04-25","arxiv_id":"2404.16423","repositories_listed":0,"syntology":null},{"url":null,"slug":"single-view-scene-point-cloud-human-grasp","title":"Single-View Scene Point Cloud Human Grasp Generation","date":"2024-04-24","arxiv_id":"2404.15815","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-models-for-multi-view-3d-object","title":"Deep Models for Multi-View 3D Object Recognition: A Review","date":"2024-04-23","arxiv_id":"2404.15224","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-prompt-following-with-visual","title":"Enhancing Prompt Following with Visual Control Through Training-Free Mask-Guided Diffusion","date":"2024-04-23","arxiv_id":"2404.14768","repositories_listed":0,"syntology":null},{"url":null,"slug":"glod-composing-global-contexts-and-local","title":"GLoD: Composing Global Contexts and Local Details in Image Generation","date":"2024-04-23","arxiv_id":"2404.15447","repositories_listed":0,"syntology":null},{"url":null,"slug":"other-tokens-matter-exploring-global-and","title":"Other Tokens Matter: Exploring Global and Local Features of Vision Transformers for Object Re-Identification","date":"2024-04-23","arxiv_id":"2404.14985","repositories_listed":0,"syntology":null},{"url":null,"slug":"source-free-domain-adaptation-for-video","title":"Source-free Domain Adaptation for Video Object Detection Under Adverse Image Conditions","date":"2024-04-23","arxiv_id":"2404.15252","repositories_listed":0,"syntology":null},{"url":null,"slug":"360vots-visual-object-tracking-and","title":"360VOTS: Visual Object Tracking and Segmentation in Omnidirectional Videos","date":"2024-04-22","arxiv_id":"2404.13953","repositories_listed":0,"syntology":null},{"url":null,"slug":"geodiffuser-geometry-based-image-editing-with","title":"GeoDiffuser: Geometry-Based Image Editing with Diffusion Models","date":"2024-04-22","arxiv_id":"2404.14403","repositories_listed":0,"syntology":null},{"url":null,"slug":"ltos-layout-controllable-text-object","title":"LTOS: Layout-controllable Text-Object Synthesis via Adaptive Cross-attention Fusions","date":"2024-04-21","arxiv_id":"2404.13579","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-framework-of-a-design-process-language","title":"The Framework of a Design Process Language","date":"2024-04-21","arxiv_id":"2404.13721","repositories_listed":0,"syntology":null},{"url":null,"slug":"composing-pre-trained-object-centric","title":"Composing Pre-Trained Object-Centric Representations for Robotics From \"What\" and \"Where\" Foundation Models","date":"2024-04-20","arxiv_id":"2404.13474","repositories_listed":0,"syntology":null},{"url":null,"slug":"fisheyedetnet-object-detection-on-fisheye","title":"FisheyeDetNet: 360° Surround view Fisheye Camera based Object Detection System for Autonomous Driving","date":"2024-04-20","arxiv_id":"2404.13443","repositories_listed":0,"syntology":null},{"url":null,"slug":"ecor-explainable-clip-for-object-recognition","title":"ECOR: Explainable CLIP for Object Recognition","date":"2024-04-19","arxiv_id":"2404.12839","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-interactive-semantic-alignment-for","title":"Exploring Interactive Semantic Alignment for Efficient HOI Detection with Vision-language Model","date":"2024-04-19","arxiv_id":"2404.12678","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-object-semantic-similarity-with-self","title":"Learning Object Semantic Similarity with Self-Supervision","date":"2024-04-19","arxiv_id":"2405.05143","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-board-classification-of-underwater-images","title":"On-board classification of underwater images using hybrid classical-quantum CNN based method","date":"2024-04-19","arxiv_id":"2404.13130","repositories_listed":0,"syntology":null},{"url":null,"slug":"physdreamer-physics-based-interaction-with-3d","title":"PhysDreamer: Physics-Based Interaction with 3D Objects via Video Generation","date":"2024-04-19","arxiv_id":"2404.13026","repositories_listed":0,"syntology":null},{"url":null,"slug":"customizing-text-to-image-diffusion-with","title":"Customizing Text-to-Image Diffusion with Object Viewpoint Control","date":"2024-04-18","arxiv_id":"2404.12333","repositories_listed":0,"syntology":null},{"url":null,"slug":"g-hop-generative-hand-object-prior-for","title":"G-HOP: Generative Hand-Object Prior for Interaction Reconstruction and Grasp Synthesis","date":"2024-04-18","arxiv_id":"2404.12383","repositories_listed":0,"syntology":null},{"url":null,"slug":"inverse-neural-rendering-for-explainable","title":"Inverse Neural Rendering for Explainable Multi-Object Tracking","date":"2024-04-18","arxiv_id":"2404.12359","repositories_listed":0,"syntology":null},{"url":null,"slug":"simultaneous-detection-and-interaction","title":"Simultaneous Detection and Interaction Reasoning for Object-Centric Action Recognition","date":"2024-04-18","arxiv_id":"2404.11903","repositories_listed":0,"syntology":null},{"url":null,"slug":"detector-collapse-backdooring-object","title":"Detector Collapse: Physical-World Backdooring Object Detection to Catastrophic Overload or Blindness in Autonomous Driving","date":"2024-04-17","arxiv_id":"2404.11357","repositories_listed":0,"syntology":null},{"url":null,"slug":"equivariant-spatio-temporal-self-supervision","title":"Equivariant Spatio-Temporal Self-Supervision for LiDAR Object Detection","date":"2024-04-17","arxiv_id":"2404.11737","repositories_listed":0,"syntology":null},{"url":null,"slug":"georef-geometric-alignment-across-shape","title":"GeoReF: Geometric Alignment Across Shape Variation for Category-level Object Pose Refinement","date":"2024-04-17","arxiv_id":"2404.11139","repositories_listed":0,"syntology":null},{"url":null,"slug":"how-to-deal-with-glare-for-improved","title":"How to deal with glare for improved perception of Autonomous Vehicles","date":"2024-04-17","arxiv_id":"2404.10992","repositories_listed":0,"syntology":null},{"url":null,"slug":"intrinsicanything-learning-diffusion-priors","title":"IntrinsicAnything: Learning Diffusion Priors for Inverse Rendering Under Unknown Illumination","date":"2024-04-17","arxiv_id":"2404.11593","repositories_listed":0,"syntology":null},{"url":null,"slug":"multimodal-3d-object-detection-on-unseen","title":"Multimodal 3D Object Detection on Unseen Domains","date":"2024-04-17","arxiv_id":"2404.11764","repositories_listed":0,"syntology":null},{"url":null,"slug":"object-remover-performance-evaluation-methods","title":"Object Remover Performance Evaluation Methods using Class-wise Object Removal Images","date":"2024-04-17","arxiv_id":"2404.11104","repositories_listed":0,"syntology":null},{"url":null,"slug":"generating-human-interaction-motions-in","title":"Generating Human Interaction Motions in Scenes with Text Control","date":"2024-04-16","arxiv_id":"2404.10685","repositories_listed":0,"syntology":null},{"url":null,"slug":"osr-vit-a-simple-and-modular-framework-for","title":"OSR-ViT: A Simple and Modular Framework for Open-Set Object Detection and Discovery","date":"2024-04-16","arxiv_id":"2404.10865","repositories_listed":0,"syntology":null},{"url":null,"slug":"hoi-ref-hand-object-interaction-referral-in","title":"HOI-Ref: Hand-Object Interaction Referral in Egocentric Vision","date":"2024-04-15","arxiv_id":"2404.09933","repositories_listed":0,"syntology":null},{"url":null,"slug":"improved-object-based-style-transfer-with","title":"Improved Object-Based Style Transfer with Single Deep Network","date":"2024-04-15","arxiv_id":"2404.09461","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-weakly-supervised-object-2","title":"Improving Weakly-Supervised Object Localization Using Adversarial Erasing and Pseudo Label","date":"2024-04-15","arxiv_id":"2404.09475","repositories_listed":0,"syntology":null},{"url":null,"slug":"vfmm3d-releasing-the-potential-of-image-by","title":"VFMM3D: Releasing the Potential of Image by Vision Foundation Model for Monocular 3D Object Detection","date":"2024-04-15","arxiv_id":"2404.09431","repositories_listed":0,"syntology":null},{"url":null,"slug":"coreset-selection-for-object-detection","title":"Coreset Selection for Object Detection","date":"2024-04-14","arxiv_id":"2404.09161","repositories_listed":0,"syntology":null},{"url":"/paper/detclipv3-towards-versatile-generative-open","slug":"detclipv3-towards-versatile-generative-open","title":"DetCLIPv3: Towards Versatile Generative Open-vocabulary Object Detection","date":"2024-04-14","arxiv_id":"2404.09216","repositories_listed":0,"syntology":null},{"url":null,"slug":"fusion-mamba-for-cross-modality-object","title":"Fusion-Mamba for Cross-modality Object Detection","date":"2024-04-14","arxiv_id":"2404.09146","repositories_listed":0,"syntology":null},{"url":null,"slug":"loopanimate-loopable-salient-object-animation","title":"LoopAnimate: Loopable Salient Object Animation","date":"2024-04-14","arxiv_id":"2404.09172","repositories_listed":0,"syntology":null},{"url":null,"slug":"bg-yolo-a-bidirectional-guided-method-for","title":"BG-YOLO: A Bidirectional-Guided Method for Underwater Object Detection","date":"2024-04-13","arxiv_id":"2404.08979","repositories_listed":0,"syntology":null},{"url":null,"slug":"adapting-the-segment-anything-model-during","title":"Adapting the Segment Anything Model During Usage in Novel Situations","date":"2024-04-12","arxiv_id":"2404.08421","repositories_listed":0,"syntology":null},{"url":null,"slug":"tdanet-target-directed-attention-network-for","title":"TDANet: Target-Directed Attention Network For Object-Goal Visual Navigation With Zero-Shot Ability","date":"2024-04-12","arxiv_id":"2404.08353","repositories_listed":0,"syntology":null},{"url":null,"slug":"run-time-monitoring-of-3d-object-detection-in","title":"Run-time Monitoring of 3D Object Detection in Automated Driving Systems Using Early Layer Neural Activation Patterns","date":"2024-04-11","arxiv_id":"2404.07685","repositories_listed":0,"syntology":null},{"url":null,"slug":"simplifying-two-stage-detectors-for-on-device","title":"Simplifying Two-Stage Detectors for On-Device Inference in Remote Sensing","date":"2024-04-11","arxiv_id":"2404.07405","repositories_listed":0,"syntology":null},{"url":null,"slug":"identification-of-fine-grained-systematic","title":"Identification of Fine-grained Systematic Errors via Controlled Scene Generation","date":"2024-04-10","arxiv_id":"2404.07045","repositories_listed":0,"syntology":null},{"url":null,"slug":"o2v-mapping-online-open-vocabulary-mapping","title":"O2V-Mapping: Online Open-Vocabulary Mapping with Neural Implicit Representation","date":"2024-04-10","arxiv_id":"2404.06836","repositories_listed":0,"syntology":null},{"url":null,"slug":"object-conditioned-energy-based-attention-map","title":"Object-Conditioned Energy-Based Attention Map Alignment in Text-to-Image Diffusion Models","date":"2024-04-10","arxiv_id":"2404.07389","repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-defect-detection-in-sewer-network","title":"Automatic Defect Detection in Sewer Network Using Deep Learning Based Object Detector","date":"2024-04-09","arxiv_id":"2404.06219","repositories_listed":0,"syntology":null},{"url":null,"slug":"counting-objects-in-a-robotic-hand","title":"Counting Objects in a Robotic Hand","date":"2024-04-09","arxiv_id":"2404.06631","repositories_listed":0,"syntology":null},{"url":null,"slug":"label-efficient-3d-object-detection-for-road","title":"Label-Efficient 3D Object Detection For Road-Side Units","date":"2024-04-09","arxiv_id":"2404.06256","repositories_listed":0,"syntology":null},{"url":null,"slug":"object-dynamics-modeling-with-hierarchical","title":"Object Dynamics Modeling with Hierarchical Point Cloud-based Representations","date":"2024-04-09","arxiv_id":"2404.06044","repositories_listed":0,"syntology":null},{"url":null,"slug":"reconstructing-hand-held-objects-in-3d","title":"Reconstructing Hand-Held Objects in 3D from Images and Videos","date":"2024-04-09","arxiv_id":"2404.06507","repositories_listed":0,"syntology":null},{"url":null,"slug":"spatial-temporal-multi-level-association-for","title":"Spatial-Temporal Multi-level Association for Video Object Segmentation","date":"2024-04-09","arxiv_id":"2404.06265","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-a-category-level-object-pose","title":"Learning a Category-level Object Pose Estimator without Pose Annotations","date":"2024-04-08","arxiv_id":"2404.05626","repositories_listed":0,"syntology":null}],"record_sha256":"b67358361b1f0978a7f72370353d4cfe1ae0487bd88f882050477c2fa1814408","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}