{"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/43","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":43,"pages_in_order":107,"rows_per_page":100,"rows":[4201,4300],"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/42","next":"/task/object/papers/44","papers":[{"url":null,"slug":"any6d-model-free-6d-pose-estimation-of-novel","title":"Any6D: Model-free 6D Pose Estimation of Novel Objects","date":"2025-03-24","arxiv_id":"2503.18673","repositories_listed":0,"syntology":null},{"url":null,"slug":"human-object-interaction-with-vision-language","title":"Human-Object Interaction with Vision-Language Model Guided Relative Movement Dynamics","date":"2025-03-24","arxiv_id":"2503.18349","repositories_listed":0,"syntology":null},{"url":null,"slug":"online-3d-scene-reconstruction-using-neural","title":"Online 3D Scene Reconstruction Using Neural Object Priors","date":"2025-03-24","arxiv_id":"2503.18897","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-image-like-diffusion-method-for-human","title":"An Image-like Diffusion Method for Human-Object Interaction Detection","date":"2025-03-23","arxiv_id":"2503.18134","repositories_listed":0,"syntology":null},{"url":null,"slug":"decorum-a-language-based-approach-for-style","title":"Decorum: A Language-Based Approach For Style-Conditioned Synthesis of Indoor 3D Scenes","date":"2025-03-23","arxiv_id":"2503.18155","repositories_listed":0,"syntology":null},{"url":null,"slug":"omnimattezero-training-free-real-time","title":"OmnimatteZero: Training-free Real-time Omnimatte with Pre-trained Video Diffusion Models","date":"2025-03-23","arxiv_id":"2503.18033","repositories_listed":0,"syntology":null},{"url":null,"slug":"shapley-scarf-markets-with-objective","title":"Shapley-Scarf Markets with Objective Indifferences","date":"2025-03-23","arxiv_id":"2503.18144","repositories_listed":0,"syntology":null},{"url":null,"slug":"co-op-correspondence-based-novel-object-pose","title":"Co-op: Correspondence-based Novel Object Pose Estimation","date":"2025-03-22","arxiv_id":"2503.17731","repositories_listed":0,"syntology":null},{"url":null,"slug":"mamat-3d-mamba-based-atmospheric-turbulence","title":"MAMAT: 3D Mamba-Based Atmospheric Turbulence Removal and its Object Detection Capability","date":"2025-03-22","arxiv_id":"2503.17700","repositories_listed":0,"syntology":null},{"url":null,"slug":"refcut-interactive-segmentation-with","title":"RefCut: Interactive Segmentation with Reference Guidance","date":"2025-03-22","arxiv_id":"2503.17820","repositories_listed":0,"syntology":null},{"url":null,"slug":"excap3d-expressive-3d-scene-understanding-via","title":"ExCap3D: Expressive 3D Scene Understanding via Object Captioning with Varying Detail","date":"2025-03-21","arxiv_id":"2503.17044","repositories_listed":0,"syntology":null},{"url":null,"slug":"re-hold-video-hand-object-interaction","title":"Re-HOLD: Video Hand Object Interaction Reenactment via adaptive Layout-instructed Diffusion Model","date":"2025-03-21","arxiv_id":"2503.16942","repositories_listed":0,"syntology":null},{"url":null,"slug":"which2comm-an-efficient-collaborative","title":"Which2comm: An Efficient Collaborative Perception Framework for 3D Object Detection","date":"2025-03-21","arxiv_id":"2503.17175","repositories_listed":0,"syntology":null},{"url":null,"slug":"graplus-graph-based-placement-using-semantics","title":"GraPLUS: Graph-based Placement Using Semantics for Image Composition","date":"2025-03-20","arxiv_id":"2503.15761","repositories_listed":0,"syntology":null},{"url":null,"slug":"magicmotion-controllable-video-generation","title":"MagicMotion: Controllable Video Generation with Dense-to-Sparse Trajectory Guidance","date":"2025-03-20","arxiv_id":"2503.16421","repositories_listed":0,"syntology":null},{"url":null,"slug":"fine-grained-open-vocabulary-object-detection","title":"Fine-Grained Open-Vocabulary Object Detection with Fined-Grained Prompts: Task, Dataset and Benchmark","date":"2025-03-19","arxiv_id":"2503.14862","repositories_listed":0,"syntology":null},{"url":null,"slug":"intelligent-spatial-perception-by-building","title":"Intelligent Spatial Perception by Building Hierarchical 3D Scene Graphs for Indoor Scenarios with the Help of LLMs","date":"2025-03-19","arxiv_id":"2503.15091","repositories_listed":0,"syntology":null},{"url":null,"slug":"test-time-backdoor-detection-for-object","title":"Test-Time Backdoor Detection for Object Detection Models","date":"2025-03-19","arxiv_id":"2503.15293","repositories_listed":0,"syntology":null},{"url":null,"slug":"variational-message-passing-based-multiobject","title":"Variational Message Passing-based Multiobject Tracking for MIMO-Radars using Raw Sensor Signals","date":"2025-03-19","arxiv_id":"2503.15246","repositories_listed":0,"syntology":null},{"url":null,"slug":"volumetric-reconstruction-from-partial-views","title":"Volumetric Reconstruction From Partial Views for Task-Oriented Grasping","date":"2025-03-19","arxiv_id":"2503.15167","repositories_listed":0,"syntology":null},{"url":null,"slug":"xmod-cross-modal-distillation-for-2d-3d-multi","title":"xMOD: Cross-Modal Distillation for 2D/3D Multi-Object Discovery from 2D motion","date":"2025-03-19","arxiv_id":"2503.15022","repositories_listed":0,"syntology":null},{"url":null,"slug":"frustumfusionnets-a-three-dimensional-object","title":"FrustumFusionNets: A Three-Dimensional Object Detection Network Based on Tractor Road Scene","date":"2025-03-18","arxiv_id":"2503.13951","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-shape-independent-transformation-via","title":"Learning Shape-Independent Transformation via Spherical Representations for Category-Level Object Pose Estimation","date":"2025-03-18","arxiv_id":"2503.13926","repositories_listed":0,"syntology":null},{"url":"/paper/psa-ssl-pose-and-size-aware-self-supervised","slug":"psa-ssl-pose-and-size-aware-self-supervised","title":"PSA-SSL: Pose and Size-aware Self-Supervised Learning on LiDAR Point Clouds","date":"2025-03-18","arxiv_id":"2503.13914","repositories_listed":0,"syntology":{"n":10,"n_ran":9,"n_constructed":0,"n_ran_checked":7,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":2,"n_no_contract":5,"n_pointer_only":4,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 2 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/psa-ssl-pose-and-size-aware-self-supervised#ran","syntology_url":"https://syntology.ai/paper/2503.13914","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.13914"}},"official":null}},{"url":null,"slug":"flex-a-framework-for-learning-robot-agnostic","title":"FLEX: A Framework for Learning Robot-Agnostic Force-based Skills Involving Sustained Contact Object Manipulation","date":"2025-03-17","arxiv_id":"2503.13418","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-motion-information-for-better-self","title":"Leveraging Motion Information for Better Self-Supervised Video Correspondence Learning","date":"2025-03-15","arxiv_id":"2503.12026","repositories_listed":0,"syntology":null},{"url":null,"slug":"cognitive-disentanglement-for-referring-multi","title":"Cognitive Disentanglement for Referring Multi-Object Tracking","date":"2025-03-14","arxiv_id":"2503.11496","repositories_listed":0,"syntology":null},{"url":null,"slug":"disentangled-object-centric-image","title":"Disentangled Object-Centric Image Representation for Robotic Manipulation","date":"2025-03-14","arxiv_id":"2503.11565","repositories_listed":0,"syntology":null},{"url":null,"slug":"mtv-inpaint-multi-task-long-video-inpainting","title":"MTV-Inpaint: Multi-Task Long Video Inpainting","date":"2025-03-14","arxiv_id":"2503.11412","repositories_listed":0,"syntology":null},{"url":null,"slug":"taste-rob-advancing-video-generation-of-task","title":"TASTE-Rob: Advancing Video Generation of Task-Oriented Hand-Object Interaction for Generalizable Robotic Manipulation","date":"2025-03-14","arxiv_id":"2503.11423","repositories_listed":0,"syntology":null},{"url":null,"slug":"3d-extended-object-tracking-based-on-extruded","title":"3D Extended Object Tracking based on Extruded B-Spline Side View Profiles","date":"2025-03-13","arxiv_id":"2503.10730","repositories_listed":0,"syntology":null},{"url":"/paper/6d-object-pose-tracking-in-internet-videos","slug":"6d-object-pose-tracking-in-internet-videos","title":"6D Object Pose Tracking in Internet Videos for Robotic Manipulation","date":"2025-03-13","arxiv_id":"2503.10307","repositories_listed":0,"syntology":null},{"url":null,"slug":"auto-associative-memories-for-direct","title":"Auto-Associative Memories for Direct Signalling of Visual Angle During Object Approaches","date":"2025-03-13","arxiv_id":"2503.10896","repositories_listed":0,"syntology":null},{"url":null,"slug":"dreaminsert-zero-shot-image-to-video-object","title":"DreamInsert: Zero-Shot Image-to-Video Object Insertion from A Single Image","date":"2025-03-13","arxiv_id":"2503.10342","repositories_listed":0,"syntology":null},{"url":null,"slug":"kuda-keypoints-to-unify-dynamics-learning-and","title":"KUDA: Keypoints to Unify Dynamics Learning and Visual Prompting for Open-Vocabulary Robotic Manipulation","date":"2025-03-13","arxiv_id":"2503.10546","repositories_listed":0,"syntology":null},{"url":null,"slug":"ocpm-2-extending-the-process-mining","title":"OCPM$^2$: Extending the Process Mining Methodology for Object-Centric Event Data Extraction","date":"2025-03-13","arxiv_id":"2503.10735","repositories_listed":0,"syntology":null},{"url":null,"slug":"roodi-reconstructing-occluded-objects-with","title":"ROODI: Reconstructing Occluded Objects with Denoising Inpainters","date":"2025-03-13","arxiv_id":"2503.10256","repositories_listed":0,"syntology":null},{"url":null,"slug":"semantic-supervised-spatial-temporal-fusion","title":"Semantic-Supervised Spatial-Temporal Fusion for LiDAR-based 3D Object Detection","date":"2025-03-13","arxiv_id":"2503.10579","repositories_listed":0,"syntology":null},{"url":null,"slug":"2handedafforder-learning-precise-actionable","title":"2HandedAfforder: Learning Precise Actionable Bimanual Affordances from Human Videos","date":"2025-03-12","arxiv_id":"2503.09320","repositories_listed":0,"syntology":null},{"url":null,"slug":"gaspacho-gaussian-splatting-for-controllable","title":"GASPACHO: Gaussian Splatting for Controllable Humans and Objects","date":"2025-03-12","arxiv_id":"2503.09342","repositories_listed":0,"syntology":null},{"url":null,"slug":"interactedit-zero-shot-editing-of-human","title":"InteractEdit: Zero-Shot Editing of Human-Object Interactions in Images","date":"2025-03-12","arxiv_id":"2503.09130","repositories_listed":0,"syntology":null},{"url":null,"slug":"object-aware-dino-oh-a-dino-enhancing-self","title":"Object-Aware DINO (Oh-A-Dino): Enhancing Self-Supervised Representations for Multi-Object Instance Retrieval","date":"2025-03-12","arxiv_id":"2503.09867","repositories_listed":0,"syntology":null},{"url":null,"slug":"tetragrip-sensor-driven-multi-suction","title":"TetraGrip: Sensor-Driven Multi-Suction Reactive Object Manipulation in Cluttered Scenes","date":"2025-03-12","arxiv_id":"2503.08978","repositories_listed":0,"syntology":null},{"url":null,"slug":"bring-remote-sensing-object-detect-into","title":"Bring Remote Sensing Object Detect Into Nature Language Model: Using SFT Method","date":"2025-03-11","arxiv_id":"2503.08144","repositories_listed":0,"syntology":null},{"url":null,"slug":"embodied-crowd-counting","title":"Embodied Crowd Counting","date":"2025-03-11","arxiv_id":"2503.08367","repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchical-contact-rich-trajectory","title":"Hierarchical Contact-Rich Trajectory Optimization for Multi-Modal Manipulation using Tight Convex Relaxations","date":"2025-03-11","arxiv_id":"2503.07963","repositories_listed":0,"syntology":null},{"url":null,"slug":"objectmover-generative-object-movement-with","title":"ObjectMover: Generative Object Movement with Video Prior","date":"2025-03-11","arxiv_id":"2503.08037","repositories_listed":0,"syntology":null},{"url":null,"slug":"omnipaint-mastering-object-oriented-editing","title":"OmniPaint: Mastering Object-Oriented Editing via Disentangled Insertion-Removal Inpainting","date":"2025-03-11","arxiv_id":"2503.08677","repositories_listed":0,"syntology":null},{"url":null,"slug":"seeing-what-s-not-there-spurious-correlation","title":"Seeing What's Not There: Spurious Correlation in Multimodal LLMs","date":"2025-03-11","arxiv_id":"2503.08884","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-light-perspective-for-3d-object-detection","title":"A Light Perspective for 3D Object Detection","date":"2025-03-10","arxiv_id":"2503.07133","repositories_listed":0,"syntology":null},{"url":null,"slug":"aligning-instance-semantic-sparse","title":"Aligning Instance-Semantic Sparse Representation towards Unsupervised Object Segmentation and Shape Abstraction with Repeatable Primitives","date":"2025-03-10","arxiv_id":"2503.06947","repositories_listed":0,"syntology":null},{"url":null,"slug":"eazy-eliminating-hallucinations-in-lvlms-by","title":"EAZY: Eliminating Hallucinations in LVLMs by Zeroing out Hallucinatory Image Tokens","date":"2025-03-10","arxiv_id":"2503.07772","repositories_listed":0,"syntology":null},{"url":null,"slug":"erase-diffusion-empowering-object-removal","title":"Erase Diffusion: Empowering Object Removal Through Calibrating Diffusion Pathways","date":"2025-03-10","arxiv_id":"2503.07026","repositories_listed":0,"syntology":null},{"url":null,"slug":"find-your-needle-small-object-image-retrieval","title":"Find your Needle: Small Object Image Retrieval via Multi-Object Attention Optimization","date":"2025-03-10","arxiv_id":"2503.07038","repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchical-cross-modal-alignment-for-open","title":"Hierarchical Cross-Modal Alignment for Open-Vocabulary 3D Object Detection","date":"2025-03-10","arxiv_id":"2503.07593","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-language-model-guided-progressive","title":"Large Language Model Guided Progressive Feature Alignment for Multimodal UAV Object Detection","date":"2025-03-10","arxiv_id":"2503.06948","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-modal-3d-mesh-reconstruction-from","title":"Multi-Modal 3D Mesh Reconstruction from Images and Text","date":"2025-03-10","arxiv_id":"2503.07190","repositories_listed":0,"syntology":null},{"url":null,"slug":"recovering-partially-corrupted-major-objects","title":"Recovering Partially Corrupted Major Objects through Tri-modality Based Image Completion","date":"2025-03-10","arxiv_id":"2503.07047","repositories_listed":0,"syntology":null},{"url":null,"slug":"axispose-model-free-matching-free-single-shot","title":"AxisPose: Model-Free Matching-Free Single-Shot 6D Object Pose Estimation via Axis Generation","date":"2025-03-09","arxiv_id":"2503.06660","repositories_listed":0,"syntology":null},{"url":null,"slug":"d3dr-lighting-aware-object-insertion-in","title":"D3DR: Lighting-Aware Object Insertion in Gaussian Splatting","date":"2025-03-09","arxiv_id":"2503.06740","repositories_listed":0,"syntology":null},{"url":"/paper/ov-scan-semantically-consistent-alignment-for","slug":"ov-scan-semantically-consistent-alignment-for","title":"OV-SCAN: Semantically Consistent Alignment for Novel Object Discovery in Open-Vocabulary 3D Object Detection","date":"2025-03-09","arxiv_id":"2503.06435","repositories_listed":0,"syntology":{"n":8,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/ov-scan-semantically-consistent-alignment-for#ran","syntology_url":"https://syntology.ai/paper/2503.06435","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.06435"}},"official":null}},{"url":null,"slug":"accurate-and-efficient-two-stage-gun","title":"Accurate and Efficient Two-Stage Gun Detection in Video","date":"2025-03-08","arxiv_id":"2503.06317","repositories_listed":0,"syntology":null},{"url":null,"slug":"object-centric-world-model-for-language","title":"Object-Centric World Model for Language-Guided Manipulation","date":"2025-03-08","arxiv_id":"2503.06170","repositories_listed":0,"syntology":null},{"url":null,"slug":"openrsd-towards-open-prompts-for-object","title":"OpenRSD: Towards Open-prompts for Object Detection in Remote Sensing Images","date":"2025-03-08","arxiv_id":"2503.06146","repositories_listed":0,"syntology":null},{"url":null,"slug":"2d-object-detection-a-survey","title":"2D Object Detection: A Survey","date":"2025-03-07","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"decoupledgaussian-object-scene-decoupling-for","title":"DecoupledGaussian: Object-Scene Decoupling for Physics-Based Interaction","date":"2025-03-07","arxiv_id":"2503.05484","repositories_listed":0,"syntology":null},{"url":null,"slug":"oscar-object-status-and-contextual-awareness","title":"OSCAR: Object Status and Contextual Awareness for Recipes to Support Non-Visual Cooking","date":"2025-03-07","arxiv_id":"2503.05962","repositories_listed":0,"syntology":null},{"url":null,"slug":"energy-guided-optimization-for-personalized","title":"Energy-Guided Optimization for Personalized Image Editing with Pretrained Text-to-Image Diffusion Models","date":"2025-03-06","arxiv_id":"2503.04215","repositories_listed":0,"syntology":null},{"url":null,"slug":"fine-tuning-florence2-for-enhanced-object","title":"Fine-Tuning Florence2 for Enhanced Object Detection in Un-constructed Environments: Vision-Language Model Approach","date":"2025-03-06","arxiv_id":"2503.04918","repositories_listed":0,"syntology":null},{"url":null,"slug":"high-precision-transformer-based-visual","title":"High-Precision Transformer-Based Visual Servoing for Humanoid Robots in Aligning Tiny Objects","date":"2025-03-06","arxiv_id":"2503.04862","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-object-placement-programs-for-indoor","title":"Learning Object Placement Programs for Indoor Scene Synthesis with Iterative Self Training","date":"2025-03-06","arxiv_id":"2503.04496","repositories_listed":0,"syntology":null},{"url":null,"slug":"shaken-not-stirred-a-novel-dataset-for-visual","title":"Shaken, Not Stirred: A Novel Dataset for Visual Understanding of Glasses in Human-Robot Bartending Tasks","date":"2025-03-06","arxiv_id":"2503.04308","repositories_listed":0,"syntology":null},{"url":null,"slug":"teach-yolo-to-remember-a-self-distillation","title":"Teach YOLO to Remember: A Self-Distillation Approach for Continual Object Detection","date":"2025-03-06","arxiv_id":"2503.04688","repositories_listed":0,"syntology":null},{"url":null,"slug":"active-6d-pose-estimation-for-textureless","title":"Active 6D Pose Estimation for Textureless Objects using Multi-View RGB Frames","date":"2025-03-05","arxiv_id":"2503.03726","repositories_listed":0,"syntology":null},{"url":null,"slug":"afford-x-generalizable-and-slim-affordance","title":"Afford-X: Generalizable and Slim Affordance Reasoning for Task-oriented Manipulation","date":"2025-03-05","arxiv_id":"2503.03556","repositories_listed":0,"syntology":null},{"url":null,"slug":"bevmosnet-multimodal-fusion-for-bev-moving","title":"BEVMOSNet: Multimodal Fusion for BEV Moving Object Segmentation","date":"2025-03-05","arxiv_id":"2503.03280","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-visual-discrimination-and-reasoning","title":"Towards Visual Discrimination and Reasoning of Real-World Physical Dynamics: Physics-Grounded Anomaly Detection","date":"2025-03-05","arxiv_id":"2503.03562","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-dataset-free-approach-for-self-supervised","title":"A dataset-free approach for self-supervised learning of 3D reflectional symmetries","date":"2025-03-04","arxiv_id":"2503.02660","repositories_listed":0,"syntology":null},{"url":null,"slug":"monolite3d-lightweight-3d-object-properties","title":"MonoLite3D: Lightweight 3D Object Properties Estimation","date":"2025-03-04","arxiv_id":"2503.02201","repositories_listed":0,"syntology":null},{"url":null,"slug":"2503-01068","title":"Language-Guided Object Search in Agricultural Environments","date":"2025-03-03","arxiv_id":"2503.01068","repositories_listed":0,"syntology":null},{"url":null,"slug":"airroom-objects-matter-in-room","title":"AirRoom: Objects Matter in Room Reidentification","date":"2025-03-03","arxiv_id":"2503.01130","repositories_listed":0,"syntology":null},{"url":null,"slug":"category-level-meta-learned-nerf-priors-for","title":"Category-level Meta-learned NeRF Priors for Efficient Object Mapping","date":"2025-03-03","arxiv_id":"2503.01582","repositories_listed":0,"syntology":null},{"url":null,"slug":"clipgrader-leveraging-vision-language-models","title":"ClipGrader: Leveraging Vision-Language Models for Robust Label Quality Assessment in Object Detection","date":"2025-03-03","arxiv_id":"2503.02897","repositories_listed":0,"syntology":null},{"url":null,"slug":"object-aware-video-matting-with-cross-frame","title":"Object-Aware Video Matting with Cross-Frame Guidance","date":"2025-03-03","arxiv_id":"2503.01262","repositories_listed":0,"syntology":null},{"url":null,"slug":"videohandles-editing-3d-object-compositions","title":"VideoHandles: Editing 3D Object Compositions in Videos Using Video Generative Priors","date":"2025-03-03","arxiv_id":"2503.01107","repositories_listed":0,"syntology":null},{"url":null,"slug":"eigenactor-variant-body-object-interaction","title":"EigenActor: Variant Body-Object Interaction Generation Evolved from Invariant Action Basis Reasoning","date":"2025-03-01","arxiv_id":"2503.00382","repositories_listed":0,"syntology":null},{"url":null,"slug":"taming-large-multimodal-agents-for-ultra-low","title":"Taming Large Multimodal Agents for Ultra-low Bitrate Semantically Disentangled Image Compression","date":"2025-03-01","arxiv_id":"2503.00399","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-deep-neural-networks-through","title":"Enhancing deep neural networks through complex-valued representations and Kuramoto synchronization dynamics","date":"2025-02-28","arxiv_id":"2502.21077","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-semantic-3d-hand-object-interaction","title":"Towards Semantic 3D Hand-Object Interaction Generation via Functional Text Guidance","date":"2025-02-28","arxiv_id":"2502.20805","repositories_listed":0,"syntology":null},{"url":null,"slug":"analyzing-clip-s-performance-limitations-in","title":"Analyzing CLIP's Performance Limitations in Multi-Object Scenarios: A Controlled High-Resolution Study","date":"2025-02-27","arxiv_id":"2502.19828","repositories_listed":0,"syntology":null},{"url":null,"slug":"bevdiffuser-plug-and-play-diffusion-model-for","title":"BEVDiffuser: Plug-and-Play Diffusion Model for BEV Denoising with Ground-Truth Guidance","date":"2025-02-27","arxiv_id":"2502.19694","repositories_listed":0,"syntology":null},{"url":null,"slug":"mitracker-multi-view-integration-for-visual","title":"MITracker: Multi-View Integration for Visual Object Tracking","date":"2025-02-27","arxiv_id":"2502.20111","repositories_listed":0,"syntology":null},{"url":null,"slug":"qort-former-query-optimized-real-time","title":"QORT-Former: Query-optimized Real-time Transformer for Understanding Two Hands Manipulating Objects","date":"2025-02-27","arxiv_id":"2502.19769","repositories_listed":0,"syntology":null},{"url":null,"slug":"coopdetr-a-unified-cooperative-perception","title":"CoopDETR: A Unified Cooperative Perception Framework for 3D Detection via Object Query","date":"2025-02-26","arxiv_id":"2502.19313","repositories_listed":0,"syntology":null},{"url":null,"slug":"dictionary-based-framework-for-interpretable","title":"Dictionary-based Framework for Interpretable and Consistent Object Parsing","date":"2025-02-26","arxiv_id":"2502.19540","repositories_listed":0,"syntology":null},{"url":null,"slug":"objectvla-end-to-end-open-world-object","title":"ObjectVLA: End-to-End Open-World Object Manipulation Without Demonstration","date":"2025-02-26","arxiv_id":"2502.19250","repositories_listed":0,"syntology":null},{"url":null,"slug":"spectral-enhanced-transformers-leveraging","title":"Spectral-Enhanced Transformers: Leveraging Large-Scale Pretrained Models for Hyperspectral Object Tracking","date":"2025-02-26","arxiv_id":"2502.18748","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-distributional-treatment-of-real2sim2real","title":"A Distributional Treatment of Real2Sim2Real for Object-Centric Agent Adaptation in Vision-Driven Deformable Linear Object Manipulation","date":"2025-02-25","arxiv_id":"2502.18615","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-reusability-of-learned-skills-for","title":"Enhancing Reusability of Learned Skills for Robot Manipulation via Gaze and Bottleneck","date":"2025-02-25","arxiv_id":"2502.18121","repositories_listed":0,"syntology":null},{"url":null,"slug":"fetchbot-object-fetching-in-cluttered-shelves","title":"FetchBot: Object Fetching in Cluttered Shelves via Zero-Shot Sim2Real","date":"2025-02-25","arxiv_id":"2502.17894","repositories_listed":0,"syntology":null}],"record_sha256":"1ade49d4c0d53c266f66176974c3fda7029393651af0845fc764b7d3fda60e07","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}