{"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/52","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":52,"pages_in_order":107,"rows_per_page":100,"rows":[5101,5200],"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/51","next":"/task/object/papers/53","papers":[{"url":null,"slug":"mose-boosting-vision-based-roadside-3d-object","title":"MOSE: Boosting Vision-based Roadside 3D Object Detection with Scene Cues","date":"2024-04-08","arxiv_id":"2404.05280","repositories_listed":0,"syntology":null},{"url":null,"slug":"swapanything-enabling-arbitrary-object","title":"SwapAnything: Enabling Arbitrary Object Swapping in Personalized Visual Editing","date":"2024-04-08","arxiv_id":"2404.05717","repositories_listed":0,"syntology":null},{"url":null,"slug":"few-shot-object-detection-research-advances","title":"Few-Shot Object Detection: Research Advances and Challenges","date":"2024-04-07","arxiv_id":"2404.04799","repositories_listed":0,"syntology":null},{"url":null,"slug":"genearl-a-training-free-generative-framework","title":"GenEARL: A Training-Free Generative Framework for Multimodal Event Argument Role Labeling","date":"2024-04-07","arxiv_id":"2404.04763","repositories_listed":0,"syntology":null},{"url":null,"slug":"hyperbolic-learning-with-synthetic-captions","title":"Hyperbolic Learning with Synthetic Captions for Open-World Detection","date":"2024-04-07","arxiv_id":"2404.05016","repositories_listed":0,"syntology":null},{"url":null,"slug":"glcm-based-feature-combination-for-extraction","title":"GLCM-Based Feature Combination for Extraction Model Optimization in Object Detection Using Machine Learning","date":"2024-04-06","arxiv_id":"2404.04578","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-detection-in-aerial-images-by","title":"Context-Aware Aerial Object Detection: Leveraging Inter-Object and Background Relationships","date":"2024-04-05","arxiv_id":"2404.04140","repositories_listed":0,"syntology":null},{"url":"/paper/learning-correlation-structures-for-vision","slug":"learning-correlation-structures-for-vision","title":"Learning Correlation Structures for Vision Transformers","date":"2024-04-05","arxiv_id":"2404.03924","repositories_listed":0,"syntology":null},{"url":null,"slug":"biovl-qr-egocentric-biochemical-video-and","title":"BioVL-QR: Egocentric Biochemical Vision-and-Language Dataset Using Micro QR Codes","date":"2024-04-04","arxiv_id":"2404.03161","repositories_listed":0,"syntology":null},{"url":null,"slug":"ow-viscap-open-world-video-instance","title":"OW-VISCapTor: Abstractors for Open-World Video Instance Segmentation and Captioning","date":"2024-04-04","arxiv_id":"2404.03657","repositories_listed":0,"syntology":null},{"url":null,"slug":"preafford-universal-affordance-based-pre","title":"PreAfford: Universal Affordance-Based Pre-Grasping for Diverse Objects and Environments","date":"2024-04-04","arxiv_id":"2404.03634","repositories_listed":0,"syntology":null},{"url":null,"slug":"semgrasp-semantic-grasp-generation-via","title":"SemGrasp: Semantic Grasp Generation via Language Aligned Discretization","date":"2024-04-04","arxiv_id":"2404.03590","repositories_listed":0,"syntology":null},{"url":null,"slug":"you-only-scan-once-a-dynamic-scene","title":"You Only Scan Once: A Dynamic Scene Reconstruction Pipeline for 6-DoF Robotic Grasping of Novel Objects","date":"2024-04-04","arxiv_id":"2404.03462","repositories_listed":0,"syntology":null},{"url":null,"slug":"adjusting-interpretable-dimensions-in","title":"Adjusting Interpretable Dimensions in Embedding Space with Human Judgments","date":"2024-04-03","arxiv_id":"2404.02619","repositories_listed":0,"syntology":null},{"url":null,"slug":"aloha-a-new-measure-for-hallucination-in","title":"ALOHa: A New Measure for Hallucination in Captioning Models","date":"2024-04-03","arxiv_id":"2404.02904","repositories_listed":0,"syntology":null},{"url":null,"slug":"i-design-personalized-llm-interior-designer","title":"I-Design: Personalized LLM Interior Designer","date":"2024-04-03","arxiv_id":"2404.02838","repositories_listed":0,"syntology":null},{"url":null,"slug":"independently-keypoint-learning-for-small","title":"Independently Keypoint Learning for Small Object Semantic Correspondence","date":"2024-04-03","arxiv_id":"2404.02678","repositories_listed":0,"syntology":null},{"url":null,"slug":"gears-local-geometry-aware-hand-object","title":"GEARS: Local Geometry-aware Hand-object Interaction Synthesis","date":"2024-04-02","arxiv_id":"2404.01758","repositories_listed":0,"syntology":null},{"url":null,"slug":"lr-fpn-enhancing-remote-sensing-object","title":"LR-FPN: Enhancing Remote Sensing Object Detection with Location Refined Feature Pyramid Network","date":"2024-04-02","arxiv_id":"2404.01614","repositories_listed":0,"syntology":null},{"url":null,"slug":"segment-any-3d-object-with-language","title":"Segment Any 3D Object with Language","date":"2024-04-02","arxiv_id":"2404.02157","repositories_listed":0,"syntology":null},{"url":"/paper/sparse-semi-detr-sparse-learnable-queries-for","slug":"sparse-semi-detr-sparse-learnable-queries-for","title":"Sparse Semi-DETR: Sparse Learnable Queries for Semi-Supervised Object Detection","date":"2024-04-02","arxiv_id":"2404.01819","repositories_listed":0,"syntology":null},{"url":null,"slug":"task-integration-distillation-for-object","title":"Task Integration Distillation for Object Detectors","date":"2024-04-02","arxiv_id":"2404.01699","repositories_listed":0,"syntology":null},{"url":null,"slug":"uncertainty-aware-active-learning-of-nerf","title":"Uncertainty-aware Active Learning of NeRF-based Object Models for Robot Manipulators using Visual and Re-orientation Actions","date":"2024-04-02","arxiv_id":"2404.01812","repositories_listed":0,"syntology":null},{"url":null,"slug":"contacthandover-contact-guided-robot-to-human","title":"ContactHandover: Contact-Guided Robot-to-Human Object Handover","date":"2024-04-01","arxiv_id":"2404.01402","repositories_listed":0,"syntology":null},{"url":null,"slug":"detect2interact-localizing-object-key-field","title":"Detect2Interact: Localizing Object Key Field in Visual Question Answering (VQA) with LLMs","date":"2024-04-01","arxiv_id":"2404.01151","repositories_listed":0,"syntology":null},{"url":null,"slug":"investigating-robustness-of-open-vocabulary","title":"Open-Vocabulary Object Detectors: Robustness Challenges under Distribution Shifts","date":"2024-04-01","arxiv_id":"2405.14874","repositories_listed":0,"syntology":null},{"url":null,"slug":"object-conditioned-bag-of-instances-for-few","title":"Object-conditioned Bag of Instances for Few-Shot Personalized Instance Recognition","date":"2024-04-01","arxiv_id":"2404.01397","repositories_listed":0,"syntology":null},{"url":null,"slug":"sugar-pre-training-3d-visual-representations","title":"SUGAR: Pre-training 3D Visual Representations for Robotics","date":"2024-04-01","arxiv_id":"2404.01491","repositories_listed":0,"syntology":null},{"url":null,"slug":"what-is-point-supervision-worth-in-video","title":"What is Point Supervision Worth in Video Instance Segmentation?","date":"2024-04-01","arxiv_id":"2404.01990","repositories_listed":0,"syntology":null},{"url":null,"slug":"object-level-copy-move-forgery-image","title":"Object-level Copy-Move Forgery Image Detection based on Inconsistency Mining","date":"2024-03-31","arxiv_id":"2404.00611","repositories_listed":0,"syntology":null},{"url":null,"slug":"constrained-layout-generation-with-factor","title":"Constrained Layout Generation with Factor Graphs","date":"2024-03-30","arxiv_id":"2404.00385","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-unseen-environments-with-robots","title":"Cognitive Planning for Object Goal Navigation using Generative AI Models","date":"2024-03-30","arxiv_id":"2404.00318","repositories_listed":0,"syntology":null},{"url":null,"slug":"hoi-m3-capture-multiple-humans-and-objects","title":"HOI-M3:Capture Multiple Humans and Objects Interaction within Contextual Environment","date":"2024-03-30","arxiv_id":"2404.00299","repositories_listed":0,"syntology":null},{"url":null,"slug":"ploc-a-new-evaluation-criterion-based-on","title":"PLoc: A New Evaluation Criterion Based on Physical Location for Autonomous Driving Datasets","date":"2024-03-29","arxiv_id":"2403.19893","repositories_listed":0,"syntology":null},{"url":null,"slug":"algorithmic-ways-of-seeing-using-object","title":"Algorithmic Ways of Seeing: Using Object Detection to Facilitate Art Exploration","date":"2024-03-28","arxiv_id":"2403.19174","repositories_listed":0,"syntology":null},{"url":null,"slug":"graspxl-generating-grasping-motions-for","title":"GraspXL: Generating Grasping Motions for Diverse Objects at Scale","date":"2024-03-28","arxiv_id":"2403.19649","repositories_listed":0,"syntology":null},{"url":null,"slug":"oakink2-a-dataset-of-bimanual-hands-object","title":"OAKINK2: A Dataset of Bimanual Hands-Object Manipulation in Complex Task Completion","date":"2024-03-28","arxiv_id":"2403.19417","repositories_listed":0,"syntology":null},{"url":null,"slug":"riemann-near-real-time-se-3-equivariant-robot","title":"RiEMann: Near Real-Time SE(3)-Equivariant Robot Manipulation without Point Cloud Segmentation","date":"2024-03-28","arxiv_id":"2403.19460","repositories_listed":0,"syntology":null},{"url":null,"slug":"bam-box-abstraction-monitors-for-real-time","title":"BAM: Box Abstraction Monitors for Real-time OoD Detection in Object Detection","date":"2024-03-27","arxiv_id":"2403.18373","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-multiple-object-tracking-accuracy","title":"Enhancing Multiple Object Tracking Accuracy via Quantum Annealing","date":"2024-03-27","arxiv_id":"2403.18908","repositories_listed":0,"syntology":null},{"url":null,"slug":"flexedit-flexible-and-controllable-diffusion","title":"FlexEdit: Flexible and Controllable Diffusion-based Object-centric Image Editing","date":"2024-03-27","arxiv_id":"2403.18605","repositories_listed":0,"syntology":null},{"url":null,"slug":"objectdrop-bootstrapping-counterfactuals-for","title":"ObjectDrop: Bootstrapping Counterfactuals for Photorealistic Object Removal and Insertion","date":"2024-03-27","arxiv_id":"2403.18818","repositories_listed":0,"syntology":null},{"url":null,"slug":"online-embedding-multi-scale-clip-features","title":"Online Embedding Multi-Scale CLIP Features into 3D Maps","date":"2024-03-27","arxiv_id":"2403.18178","repositories_listed":0,"syntology":null},{"url":null,"slug":"diffh2o-diffusion-based-synthesis-of-hand","title":"DiffH2O: Diffusion-Based Synthesis of Hand-Object Interactions from Textual Descriptions","date":"2024-03-26","arxiv_id":"2403.17827","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-dynamic-transformer-for-efficient","title":"Exploring Dynamic Transformer for Efficient Object Tracking","date":"2024-03-26","arxiv_id":"2403.17651","repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchical-open-vocabulary-3d-scene-graphs","title":"Hierarchical Open-Vocabulary 3D Scene Graphs for Language-Grounded Robot Navigation","date":"2024-03-26","arxiv_id":"2403.17846","repositories_listed":0,"syntology":null},{"url":null,"slug":"spectralwaste-dataset-multimodal-data-for","title":"SpectralWaste Dataset: Multimodal Data for Waste Sorting Automation","date":"2024-03-26","arxiv_id":"2403.18033","repositories_listed":0,"syntology":null},{"url":null,"slug":"co-occurring-of-object-detection-and","title":"Co-Occurring of Object Detection and Identification towards unlabeled object discovery","date":"2024-03-25","arxiv_id":"2403.17223","repositories_listed":0,"syntology":null},{"url":null,"slug":"comp4d-llm-guided-compositional-4d-scene","title":"Comp4D: LLM-Guided Compositional 4D Scene Generation","date":"2024-03-25","arxiv_id":"2403.16993","repositories_listed":0,"syntology":null},{"url":null,"slug":"dora-3d-visual-grounding-with-order-aware","title":"Data-Efficient 3D Visual Grounding via Order-Aware Referring","date":"2024-03-25","arxiv_id":"2403.16539","repositories_listed":0,"syntology":null},{"url":null,"slug":"v2x-pc-vehicle-to-everything-collaborative","title":"V2X-PC: Vehicle-to-everything Collaborative Perception via Point Cluster","date":"2024-03-25","arxiv_id":"2403.16635","repositories_listed":0,"syntology":null},{"url":null,"slug":"fusion-of-active-and-passive-measurements-for","title":"Fusion of Active and Passive Measurements for Robust and Scalable Positioning","date":"2024-03-24","arxiv_id":"2403.16150","repositories_listed":0,"syntology":null},{"url":null,"slug":"gaze-guided-hand-object-interaction-synthesis","title":"Gaze-guided Hand-Object Interaction Synthesis: Dataset and Method","date":"2024-03-24","arxiv_id":"2403.16169","repositories_listed":0,"syntology":null},{"url":null,"slug":"inverse-rendering-of-glossy-objects-via-the","title":"Inverse Rendering of Glossy Objects via the Neural Plenoptic Function and Radiance Fields","date":"2024-03-24","arxiv_id":"2403.16224","repositories_listed":0,"syntology":null},{"url":null,"slug":"realtime-robust-shape-estimation-of","title":"Realtime Robust Shape Estimation of Deformable Linear Object","date":"2024-03-24","arxiv_id":"2403.16146","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-two-stream-foveation-based-active","title":"Towards Two-Stream Foveation-based Active Vision Learning","date":"2024-03-24","arxiv_id":"2403.15977","repositories_listed":0,"syntology":null},{"url":null,"slug":"inpainting-driven-mask-optimization-for","title":"Inpainting-Driven Mask Optimization for Object Removal","date":"2024-03-23","arxiv_id":"2403.15849","repositories_listed":0,"syntology":null},{"url":null,"slug":"temporal-spatial-object-relations-modeling","title":"Temporal-Spatial Object Relations Modeling for Vision-and-Language Navigation","date":"2024-03-23","arxiv_id":"2403.15691","repositories_listed":0,"syntology":null},{"url":null,"slug":"pseudotouch-efficiently-imaging-the-surface","title":"PseudoTouch: Efficiently Imaging the Surface Feel of Objects for Robotic Manipulation","date":"2024-03-22","arxiv_id":"2403.15107","repositories_listed":0,"syntology":null},{"url":null,"slug":"reasoning-enhanced-object-centric-learning","title":"Reasoning-Enhanced Object-Centric Learning for Videos","date":"2024-03-22","arxiv_id":"2403.15245","repositories_listed":0,"syntology":null},{"url":null,"slug":"survey-on-modeling-of-articulated-objects","title":"Survey on Modeling of Human-made Articulated Objects","date":"2024-03-22","arxiv_id":"2403.14937","repositories_listed":0,"syntology":null},{"url":null,"slug":"3d-object-detection-from-point-cloud-via","title":"3D Object Detection from Point Cloud via Voting Step Diffusion","date":"2024-03-21","arxiv_id":"2403.14133","repositories_listed":0,"syntology":null},{"url":null,"slug":"external-knowledge-enhanced-3d-scene","title":"External Knowledge Enhanced 3D Scene Generation from Sketch","date":"2024-03-21","arxiv_id":"2403.14121","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-large-language-model-based-room","title":"Leveraging Large Language Model-based Room-Object Relationships Knowledge for Enhancing Multimodal-Input Object Goal Navigation","date":"2024-03-21","arxiv_id":"2403.14163","repositories_listed":0,"syntology":null},{"url":null,"slug":"object-centric-domain-randomization-for-3d","title":"Robust 3D Shape Reconstruction in Zero-Shot from a Single Image in the Wild","date":"2024-03-21","arxiv_id":"2403.14539","repositories_listed":0,"syntology":null},{"url":null,"slug":"scene-graph-vit-end-to-end-open-vocabulary","title":"Scene-Graph ViT: End-to-End Open-Vocabulary Visual Relationship Detection","date":"2024-03-21","arxiv_id":"2403.14270","repositories_listed":0,"syntology":null},{"url":null,"slug":"visibility-aware-keypoint-localization-for","title":"VAPO: Visibility-Aware Keypoint Localization for Efficient 6DoF Object Pose Estimation","date":"2024-03-21","arxiv_id":"2403.14559","repositories_listed":0,"syntology":null},{"url":null,"slug":"zero-shot-multi-object-shape-completion","title":"Zero-Shot Multi-Object Scene Completion","date":"2024-03-21","arxiv_id":"2403.14628","repositories_listed":0,"syntology":null},{"url":null,"slug":"ec-iou-orienting-safety-for-object-detectors","title":"EC-IoU: Orienting Safety for Object Detectors via Ego-Centric Intersection-over-Union","date":"2024-03-20","arxiv_id":"2403.15474","repositories_listed":0,"syntology":null},{"url":null,"slug":"ecosense-energy-efficient-intelligent-sensing","title":"EcoSense: Energy-Efficient Intelligent Sensing for In-Shore Ship Detection through Edge-Cloud Collaboration","date":"2024-03-20","arxiv_id":"2403.14027","repositories_listed":0,"syntology":null},{"url":null,"slug":"few-shot-oriented-object-detection-with","title":"Few-shot Oriented Object Detection with Memorable Contrastive Learning in Remote Sensing Images","date":"2024-03-20","arxiv_id":"2403.13375","repositories_listed":0,"syntology":null},{"url":null,"slug":"3d-semantic-mapnet-building-maps-for-multi","title":"3D Semantic MapNet: Building Maps for Multi-Object Re-Identification in 3D","date":"2024-03-19","arxiv_id":"2403.13190","repositories_listed":0,"syntology":null},{"url":null,"slug":"comboverse-compositional-3d-assets-creation","title":"ComboVerse: Compositional 3D Assets Creation Using Spatially-Aware Diffusion Guidance","date":"2024-03-19","arxiv_id":"2403.12409","repositories_listed":0,"syntology":null},{"url":null,"slug":"ov9d-open-vocabulary-category-level-9d-object","title":"OV9D: Open-Vocabulary Category-Level 9D Object Pose and Size Estimation","date":"2024-03-19","arxiv_id":"2403.12396","repositories_listed":0,"syntology":null},{"url":null,"slug":"sc-diff-3d-shape-completion-with-latent","title":"SC-Diff: 3D Shape Completion with Latent Diffusion Models","date":"2024-03-19","arxiv_id":"2403.12470","repositories_listed":0,"syntology":null},{"url":null,"slug":"circle-representation-for-medical-instance","title":"Circle Representation for Medical Instance Object Segmentation","date":"2024-03-18","arxiv_id":"2403.11507","repositories_listed":0,"syntology":null},{"url":null,"slug":"flexcap-generating-rich-localized-and","title":"FlexCap: Describe Anything in Images in Controllable Detail","date":"2024-03-18","arxiv_id":"2403.12026","repositories_listed":0,"syntology":null},{"url":null,"slug":"genflow-generalizable-recurrent-flow-for-6d","title":"GenFlow: Generalizable Recurrent Flow for 6D Pose Refinement of Novel Objects","date":"2024-03-18","arxiv_id":"2403.11510","repositories_listed":0,"syntology":null},{"url":null,"slug":"hoidiffusion-generating-realistic-3d-hand","title":"HOIDiffusion: Generating Realistic 3D Hand-Object Interaction Data","date":"2024-03-18","arxiv_id":"2403.12011","repositories_listed":0,"syntology":null},{"url":null,"slug":"object-segmentation-assisted-inter-prediction","title":"Object Segmentation-Assisted Inter Prediction for Versatile Video Coding","date":"2024-03-18","arxiv_id":"2403.11694","repositories_listed":0,"syntology":null},{"url":null,"slug":"pedestrian-tracking-with-monocular-camera","title":"Pedestrian Tracking with Monocular Camera using Unconstrained 3D Motion Model","date":"2024-03-18","arxiv_id":"2403.11978","repositories_listed":0,"syntology":null},{"url":null,"slug":"prototipo-de-un-contador-bidireccional","title":"Prototipo de un Contador Bidireccional Automático de Personas basado en sensores de visión 3D","date":"2024-03-18","arxiv_id":"2403.12310","repositories_listed":0,"syntology":null},{"url":null,"slug":"r3ds-reality-linked-3d-scenes-for-panoramic","title":"R3DS: Reality-linked 3D Scenes for Panoramic Scene Understanding","date":"2024-03-18","arxiv_id":"2403.12301","repositories_listed":0,"syntology":null},{"url":null,"slug":"creating-seamless-3d-maps-using-radiance","title":"Creating Seamless 3D Maps Using Radiance Fields","date":"2024-03-17","arxiv_id":"2403.11364","repositories_listed":0,"syntology":null},{"url":null,"slug":"force-dataset-and-method-for-intuitive","title":"FORCE: Physics-aware Human-object Interaction","date":"2024-03-17","arxiv_id":"2403.11237","repositories_listed":0,"syntology":null},{"url":null,"slug":"gra-detecting-oriented-objects-through-group","title":"GRA: Detecting Oriented Objects through Group-wise Rotating and Attention","date":"2024-03-17","arxiv_id":"2403.11127","repositories_listed":0,"syntology":null},{"url":null,"slug":"thor-text-to-human-object-interaction","title":"THOR: Text to Human-Object Interaction Diffusion via Relation Intervention","date":"2024-03-17","arxiv_id":"2403.11208","repositories_listed":0,"syntology":null},{"url":null,"slug":"segment-any-object-model-saom-real-to","title":"Segment Any Object Model (SAOM): Real-to-Simulation Fine-Tuning Strategy for Multi-Class Multi-Instance Segmentation","date":"2024-03-16","arxiv_id":"2403.10780","repositories_listed":0,"syntology":null},{"url":null,"slug":"view-centric-multi-object-tracking-with","title":"View-Centric Multi-Object Tracking with Homographic Matching in Moving UAV","date":"2024-03-16","arxiv_id":"2403.10830","repositories_listed":0,"syntology":null},{"url":null,"slug":"grasp-anything-combining-teacher-augmented","title":"Grasp Anything: Combining Teacher-Augmented Policy Gradient Learning with Instance Segmentation to Grasp Arbitrary Objects","date":"2024-03-15","arxiv_id":"2403.10187","repositories_listed":0,"syntology":null},{"url":null,"slug":"gs-pose-cascaded-framework-for-generalizable","title":"GS-Pose: Generalizable Segmentation-based 6D Object Pose Estimation with 3D Gaussian Splatting","date":"2024-03-15","arxiv_id":"2403.10683","repositories_listed":0,"syntology":null},{"url":null,"slug":"imprint-generative-object-compositing-by","title":"IMPRINT: Generative Object Compositing by Learning Identity-Preserving Representation","date":"2024-03-15","arxiv_id":"2403.10701","repositories_listed":0,"syntology":null},{"url":null,"slug":"latent-object-characteristics-recognition","title":"Latent Object Characteristics Recognition with Visual to Haptic-Audio Cross-modal Transfer Learning","date":"2024-03-15","arxiv_id":"2403.10689","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-physical-dynamics-for-object-centric","title":"Learning Physical Dynamics for Object-centric Visual Prediction","date":"2024-03-15","arxiv_id":"2403.10079","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-distant-3d-object-detection-using","title":"Improving Distant 3D Object Detection Using 2D Box Supervision","date":"2024-03-14","arxiv_id":"2403.09230","repositories_listed":0,"syntology":null},{"url":"/paper/onetracker-unifying-visual-object-tracking","slug":"onetracker-unifying-visual-object-tracking","title":"OneTracker: Unifying Visual Object Tracking with Foundation Models and Efficient Tuning","date":"2024-03-14","arxiv_id":"2403.09634","repositories_listed":0,"syntology":null},{"url":null,"slug":"poifusion-multi-modal-3d-object-detection-via","title":"PoIFusion: Multi-Modal 3D Object Detection via Fusion at Points of Interest","date":"2024-03-14","arxiv_id":"2403.09212","repositories_listed":0,"syntology":null},{"url":null,"slug":"reconstruction-and-simulation-of-elastic","title":"Reconstruction and Simulation of Elastic Objects with Spring-Mass 3D Gaussians","date":"2024-03-14","arxiv_id":"2403.09434","repositories_listed":0,"syntology":null},{"url":null,"slug":"rethinking-referring-object-removal","title":"Rethinking Referring Object Removal","date":"2024-03-14","arxiv_id":"2403.09128","repositories_listed":0,"syntology":null},{"url":null,"slug":"right-place-right-time-towards-objectnav-for","title":"Right Place, Right Time! Dynamizing Topological Graphs for Embodied Navigation","date":"2024-03-14","arxiv_id":"2403.09905","repositories_listed":0,"syntology":null}],"record_sha256":"e564634c5b752445eb90eb15cf33396a34b3788ddd7c0c0beadeac521a662a35","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}