{"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/47","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":47,"pages_in_order":107,"rows_per_page":100,"rows":[4601,4700],"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/46","next":"/task/object/papers/48","papers":[{"url":null,"slug":"radar-and-camera-fusion-for-object-detection","title":"Radar and Camera Fusion for Object Detection and Tracking: A Comprehensive Survey","date":"2024-10-24","arxiv_id":"2410.19872","repositories_listed":0,"syntology":null},{"url":null,"slug":"zero-shot-object-navigation-with-vision","title":"Zero-shot Object Navigation with Vision-Language Models Reasoning","date":"2024-10-24","arxiv_id":"2410.18570","repositories_listed":0,"syntology":null},{"url":null,"slug":"yolo-vehicle-pro-a-cloud-edge-collaborative","title":"YOLO-Vehicle-Pro: A Cloud-Edge Collaborative Framework for Object Detection in Autonomous Driving under Adverse Weather Conditions","date":"2024-10-23","arxiv_id":"2410.17734","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-real-zero-shot-camouflaged-object","title":"Towards Real Zero-Shot Camouflaged Object Segmentation without Camouflaged Annotations","date":"2024-10-22","arxiv_id":"2410.16953","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-learning-and-machine-learning-object","title":"Deep Learning and Machine Learning -- Object Detection and Semantic Segmentation: From Theory to Applications","date":"2024-10-21","arxiv_id":"2410.15584","repositories_listed":0,"syntology":null},{"url":null,"slug":"few-shot-target-driven-instance-detection","title":"Few-shot target-driven instance detection based on open-vocabulary object detection models","date":"2024-10-21","arxiv_id":"2410.16028","repositories_listed":0,"syntology":null},{"url":null,"slug":"joint-top-down-and-bottom-up-frameworks-for","title":"Joint Top-Down and Bottom-Up Frameworks for 3D Visual Grounding","date":"2024-10-21","arxiv_id":"2410.15615","repositories_listed":0,"syntology":null},{"url":null,"slug":"object-centric-temporal-consistency-via","title":"Object-Centric Temporal Consistency via Conditional Autoregressive Inductive Biases","date":"2024-10-21","arxiv_id":"2410.15728","repositories_listed":0,"syntology":null},{"url":null,"slug":"online-pseudo-label-unified-object-detection","title":"Online Pseudo-Label Unified Object Detection for Multiple Datasets Training","date":"2024-10-21","arxiv_id":"2410.15569","repositories_listed":0,"syntology":null},{"url":null,"slug":"singapo-single-image-controlled-generation-of","title":"SINGAPO: Single Image Controlled Generation of Articulated Parts in Objects","date":"2024-10-21","arxiv_id":"2410.16499","repositories_listed":0,"syntology":null},{"url":null,"slug":"grs-generating-robotic-simulation-tasks-from","title":"GRS: Generating Robotic Simulation Tasks from Real-World Images","date":"2024-10-20","arxiv_id":"2410.15536","repositories_listed":0,"syntology":null},{"url":null,"slug":"social-media-management-system-project-report-1","title":"SOCIAL MEDIA MANAGEMENT SYSTEM PROJECT REPORT","date":"2024-10-20","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"interpretable-end-to-end-neurosymbolic","title":"Interpretable end-to-end Neurosymbolic Reinforcement Learning agents","date":"2024-10-18","arxiv_id":"2410.14371","repositories_listed":0,"syntology":null},{"url":null,"slug":"skill-generalization-with-verbs","title":"Skill Generalization with Verbs","date":"2024-10-18","arxiv_id":"2410.14118","repositories_listed":0,"syntology":null},{"url":null,"slug":"accelerating-object-detection-with-yolov4-for","title":"Accelerating Object Detection with YOLOv4 for Real-Time Applications","date":"2024-10-17","arxiv_id":"2410.16320","repositories_listed":0,"syntology":null},{"url":null,"slug":"generative-location-modeling-for-spatially","title":"Generative Location Modeling for Spatially Aware Object Insertion","date":"2024-10-17","arxiv_id":"2410.13564","repositories_listed":0,"syntology":null},{"url":null,"slug":"graspdiffusion-synthesizing-realistic-whole","title":"GraspDiffusion: Synthesizing Realistic Whole-body Hand-Object Interaction","date":"2024-10-17","arxiv_id":"2410.13911","repositories_listed":0,"syntology":null},{"url":null,"slug":"object-pose-estimation-using-implicit","title":"Object Pose Estimation Using Implicit Representation For Transparent Objects","date":"2024-10-17","arxiv_id":"2410.13465","repositories_listed":0,"syntology":null},{"url":null,"slug":"spatiotemporal-object-detection-for-improved","title":"Spatiotemporal Object Detection for Improved Aerial Vehicle Detection in Traffic Monitoring","date":"2024-10-17","arxiv_id":"2410.13616","repositories_listed":0,"syntology":null},{"url":null,"slug":"cocoon-robust-multi-modal-perception-with","title":"Cocoon: Robust Multi-Modal Perception with Uncertainty-Aware Sensor Fusion","date":"2024-10-16","arxiv_id":"2410.12592","repositories_listed":0,"syntology":null},{"url":null,"slug":"hiding-in-plain-sight-hips-attack-on-clip-for","title":"Hiding-in-Plain-Sight (HiPS) Attack on CLIP for Targetted Object Removal from Images","date":"2024-10-16","arxiv_id":"2410.13010","repositories_listed":0,"syntology":null},{"url":null,"slug":"mambabev-an-efficient-3d-detection-model-with","title":"MambaBEV: An efficient 3D detection model with Mamba2","date":"2024-10-16","arxiv_id":"2410.12673","repositories_listed":0,"syntology":null},{"url":null,"slug":"optimizing-yolov5s-object-detection-through","title":"Optimizing YOLOv5s Object Detection through Knowledge Distillation algorithm","date":"2024-10-16","arxiv_id":"2410.12259","repositories_listed":0,"syntology":null},{"url":null,"slug":"stable-object-placement-planning-from-contact","title":"Stable Object Placement Planning From Contact Point Robustness","date":"2024-10-16","arxiv_id":"2410.12483","repositories_listed":0,"syntology":null},{"url":null,"slug":"jigsaw-imagining-complete-shape-priors-for","title":"Jigsaw++: Imagining Complete Shape Priors for Object Reassembly","date":"2024-10-15","arxiv_id":"2410.11816","repositories_listed":0,"syntology":null},{"url":null,"slug":"sgedit-bridging-llm-with-text2image","title":"SGEdit: Bridging LLM with Text2Image Generative Model for Scene Graph-based Image Editing","date":"2024-10-15","arxiv_id":"2410.11815","repositories_listed":0,"syntology":null},{"url":null,"slug":"data-driven-approaches-for-modelling-target","title":"Data-Driven Approaches for Modelling Target Behaviour","date":"2024-10-14","arxiv_id":"2410.10538","repositories_listed":0,"syntology":null},{"url":null,"slug":"dintr-tracking-via-diffusion-based","title":"DINTR: Tracking via Diffusion-based Interpolation","date":"2024-10-14","arxiv_id":"2410.10053","repositories_listed":0,"syntology":null},{"url":null,"slug":"uav3d-a-large-scale-3d-perception-benchmark","title":"UAV3D: A Large-scale 3D Perception Benchmark for Unmanned Aerial Vehicles","date":"2024-10-14","arxiv_id":"2410.11125","repositories_listed":0,"syntology":null},{"url":null,"slug":"block-to-scene-pre-training-for-point-cloud","title":"Block-to-Scene Pre-training for Point Cloud Hybrid-Domain Masked Autoencoders","date":"2024-10-13","arxiv_id":"2410.09886","repositories_listed":0,"syntology":null},{"url":null,"slug":"videosam-open-world-video-segmentation","title":"VideoSAM: Open-World Video Segmentation","date":"2024-10-11","arxiv_id":"2410.08781","repositories_listed":0,"syntology":null},{"url":null,"slug":"vovtrack-exploring-the-potentiality-in-videos","title":"VOVTrack: Exploring the Potentiality in Videos for Open-Vocabulary Object Tracking","date":"2024-10-11","arxiv_id":"2410.08529","repositories_listed":0,"syntology":null},{"url":null,"slug":"fusionsense-bridging-common-sense-vision-and","title":"FusionSense: Bridging Common Sense, Vision, and Touch for Robust Sparse-View Reconstruction","date":"2024-10-10","arxiv_id":"2410.08282","repositories_listed":0,"syntology":null},{"url":null,"slug":"heightformer-a-semantic-alignment-monocular","title":"HeightFormer: A Semantic Alignment Monocular 3D Object Detection Method from Roadside Perspective","date":"2024-10-10","arxiv_id":"2410.07758","repositories_listed":0,"syntology":null},{"url":null,"slug":"regiongrasp-a-novel-task-for-contact-region","title":"RegionGrasp: A Novel Task for Contact Region Controllable Hand Grasp Generation","date":"2024-10-10","arxiv_id":"2410.07995","repositories_listed":0,"syntology":null},{"url":null,"slug":"sg-nav-online-3d-scene-graph-prompting-for","title":"SG-Nav: Online 3D Scene Graph Prompting for LLM-based Zero-shot Object Navigation","date":"2024-10-10","arxiv_id":"2410.08189","repositories_listed":0,"syntology":null},{"url":null,"slug":"avatargo-zero-shot-4d-human-object","title":"AvatarGO: Zero-shot 4D Human-Object Interaction Generation and Animation","date":"2024-10-09","arxiv_id":"2410.07164","repositories_listed":0,"syntology":null},{"url":null,"slug":"progressive-multi-modal-fusion-for-robust-3d","title":"Progressive Multi-Modal Fusion for Robust 3D Object Detection","date":"2024-10-09","arxiv_id":"2410.07475","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-supervised-learning-for-real-world","title":"Self-Supervised Learning for Real-World Object Detection: a Survey","date":"2024-10-09","arxiv_id":"2410.07442","repositories_listed":0,"syntology":null},{"url":null,"slug":"structured-spatial-reasoning-with-open","title":"Structured Spatial Reasoning with Open Vocabulary Object Detectors","date":"2024-10-09","arxiv_id":"2410.07394","repositories_listed":0,"syntology":null},{"url":null,"slug":"adver-city-open-source-multi-modal-dataset","title":"Adver-City: Open-Source Multi-Modal Dataset for Collaborative Perception Under Adverse Weather Conditions","date":"2024-10-08","arxiv_id":"2410.06380","repositories_listed":0,"syntology":null},{"url":null,"slug":"first-experimental-study-of-multiple","title":"First experimental study of multiple orientation muon tomography, with image optimization in sparse data environments","date":"2024-10-08","arxiv_id":"2410.07264","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-gaussian-data-augmentation-in","title":"Learning Gaussian Data Augmentation in Feature Space for One-shot Object Detection in Manga","date":"2024-10-08","arxiv_id":"2410.05935","repositories_listed":0,"syntology":null},{"url":null,"slug":"training-free-open-ended-object-detection-and","title":"Training-Free Open-Ended Object Detection and Segmentation via Attention as Prompts","date":"2024-10-08","arxiv_id":"2410.05963","repositories_listed":0,"syntology":null},{"url":"/paper/improving-object-detection-via-local-global","slug":"improving-object-detection-via-local-global","title":"Improving Object Detection via Local-global Contrastive Learning","date":"2024-10-07","arxiv_id":"2410.05058","repositories_listed":0,"syntology":null},{"url":null,"slug":"next-state-prediction-gives-rise-to-entangled","title":"Next state prediction gives rise to entangled, yet compositional representations of objects","date":"2024-10-07","arxiv_id":"2410.04940","repositories_listed":0,"syntology":null},{"url":null,"slug":"deformable-nerf-using-recursively-subdivided","title":"Deformable NeRF using Recursively Subdivided Tetrahedra","date":"2024-10-06","arxiv_id":"2410.04402","repositories_listed":0,"syntology":null},{"url":null,"slug":"streetsurfgs-scalable-urban-street-surface","title":"StreetSurfGS: Scalable Urban Street Surface Reconstruction with Planar-based Gaussian Splatting","date":"2024-10-06","arxiv_id":"2410.04354","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-object-properties-using-robot","title":"Learning Object Properties Using Robot Proprioception via Differentiable Robot-Object Interaction","date":"2024-10-04","arxiv_id":"2410.03920","repositories_listed":0,"syntology":null},{"url":null,"slug":"task-decoupled-image-inpainting-framework-for","title":"Task-Decoupled Image Inpainting Framework for Class-specific Object Remover","date":"2024-10-03","arxiv_id":"2410.02894","repositories_listed":0,"syntology":null},{"url":null,"slug":"arpov-expanding-visualization-of-object","title":"ARPOV: Expanding Visualization of Object Detection in AR with Panoramic Mosaic Stitching","date":"2024-10-01","arxiv_id":"2410.01055","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-we-remove-the-ground-obstacle-aware-point","title":"Can We Remove the Ground? Obstacle-aware Point Cloud Compression for Remote Object Detection","date":"2024-10-01","arxiv_id":"2410.00582","repositories_listed":0,"syntology":null},{"url":null,"slug":"simplified-priors-for-object-centric-learning","title":"Simplified priors for Object-Centric Learning","date":"2024-10-01","arxiv_id":"2410.00728","repositories_listed":0,"syntology":null},{"url":null,"slug":"dressrecon-freeform-4d-human-reconstruction","title":"DressRecon: Freeform 4D Human Reconstruction from Monocular Video","date":"2024-09-30","arxiv_id":"2409.20563","repositories_listed":0,"syntology":null},{"url":null,"slug":"geartrack-automating-6d-pose-estimation","title":"SuperPose: Improved 6D Pose Estimation with Robust Tracking and Mask-Free Initialization","date":"2024-09-30","arxiv_id":"2409.19986","repositories_listed":0,"syntology":null},{"url":null,"slug":"applying-the-lower-biased-teacher-model-in","title":"Applying the Lower-Biased Teacher Model in Semi-Supervised Object Detection","date":"2024-09-29","arxiv_id":"2409.19703","repositories_listed":0,"syntology":null},{"url":null,"slug":"fcop-focal-length-estimation-from-category","title":"fCOP: Focal Length Estimation from Category-level Object Priors","date":"2024-09-29","arxiv_id":"2409.19641","repositories_listed":0,"syntology":null},{"url":null,"slug":"1st-place-solution-to-the-8th-hands-workshop","title":"1st Place Solution to the 8th HANDS Workshop Challenge -- ARCTIC Track: 3DGS-based Bimanual Category-agnostic Interaction Reconstruction","date":"2024-09-28","arxiv_id":"2409.19215","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-overview-of-multi-object-estimation-via","title":"An Overview of Multi-Object Estimation via Labeled Random Finite Set","date":"2024-09-27","arxiv_id":"2409.18531","repositories_listed":0,"syntology":null},{"url":"/paper/caff-dino-multi-spectral-object-detection","slug":"caff-dino-multi-spectral-object-detection","title":"CAFF-DINO: Multi-spectral object detection transformers with cross-attention features fusion","date":"2024-09-27","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"query-matching-for-spatio-temporal-action","title":"Query matching for spatio-temporal action detection with query-based object detector","date":"2024-09-27","arxiv_id":"2409.18408","repositories_listed":0,"syntology":null},{"url":null,"slug":"search3d-hierarchical-open-vocabulary-3d","title":"Search3D: Hierarchical Open-Vocabulary 3D Segmentation","date":"2024-09-27","arxiv_id":"2409.18431","repositories_listed":0,"syntology":null},{"url":null,"slug":"you-only-speak-once-to-see","title":"You Only Speak Once to See","date":"2024-09-27","arxiv_id":"2409.18372","repositories_listed":0,"syntology":null},{"url":null,"slug":"advancing-object-detection-in-transportation","title":"Advancing Object Detection in Transportation with Multimodal Large Language Models (MLLMs): A Comprehensive Review and Empirical Testing","date":"2024-09-26","arxiv_id":"2409.18286","repositories_listed":0,"syntology":null},{"url":null,"slug":"amodal-instance-segmentation-with-diffusion","title":"Amodal Instance Segmentation with Diffusion Shape Prior Estimation","date":"2024-09-26","arxiv_id":"2409.18256","repositories_listed":0,"syntology":null},{"url":null,"slug":"camot-camera-angle-aware-multi-object","title":"CAMOT: Camera Angle-aware Multi-Object Tracking","date":"2024-09-26","arxiv_id":"2409.17533","repositories_listed":0,"syntology":null},{"url":null,"slug":"general-compression-framework-for-efficient","title":"General Compression Framework for Efficient Transformer Object Tracking","date":"2024-09-26","arxiv_id":"2409.17564","repositories_listed":0,"syntology":null},{"url":null,"slug":"hand-object-reconstruction-via-interaction","title":"Hand-object reconstruction via interaction-aware graph attention mechanism","date":"2024-09-26","arxiv_id":"2409.17629","repositories_listed":0,"syntology":null},{"url":null,"slug":"search-and-detect-training-free-long-tail","title":"Search and Detect: Training-Free Long Tail Object Detection via Web-Image Retrieval","date":"2024-09-26","arxiv_id":"2409.18733","repositories_listed":0,"syntology":null},{"url":null,"slug":"soar-self-supervision-optimized-uav-action","title":"SOAR: Self-supervision Optimized UAV Action Recognition with Efficient Object-Aware Pretraining","date":"2024-09-26","arxiv_id":"2409.18300","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-grasping-movement-intention-estimator-for","title":"A Grasping Movement Intention Estimator for Intuitive Control of Assistive Devices","date":"2024-09-25","arxiv_id":"2409.16692","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-versatile-and-differentiable-hand-object","title":"A Versatile and Differentiable Hand-Object Interaction Representation","date":"2024-09-25","arxiv_id":"2409.16855","repositories_listed":0,"syntology":null},{"url":null,"slug":"go-slam-grounded-object-segmentation-and","title":"Go-SLAM: Grounded Object Segmentation and Localization with Gaussian Splatting SLAM","date":"2024-09-25","arxiv_id":"2409.16944","repositories_listed":0,"syntology":null},{"url":null,"slug":"transient-adversarial-3d-projection-attacks","title":"Transient Adversarial 3D Projection Attacks on Object Detection in Autonomous Driving","date":"2024-09-25","arxiv_id":"2409.17403","repositories_listed":0,"syntology":null},{"url":null,"slug":"articulated-object-manipulation-using-online","title":"Articulated Object Manipulation using Online Axis Estimation with SAM2-Based Tracking","date":"2024-09-24","arxiv_id":"2409.16287","repositories_listed":0,"syntology":null},{"url":null,"slug":"open-world-object-detection-with-instance","title":"OW-Rep: Open World Object Detection with Instance Representation Learning","date":"2024-09-24","arxiv_id":"2409.16073","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-robust-object-detection-identifying","title":"Towards Robust Object Detection: Identifying and Removing Backdoors via Module Inconsistency Analysis","date":"2024-09-24","arxiv_id":"2409.16057","repositories_listed":0,"syntology":null},{"url":null,"slug":"uice-mirnet-guided-image-enhancement-for","title":"UICE-MIRNet guided image enhancement for underwater object detection","date":"2024-09-24","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-bottom-up-approach-to-class-agnostic-image","title":"A Bottom-Up Approach to Class-Agnostic Image Segmentation","date":"2024-09-20","arxiv_id":"2409.13687","repositories_listed":0,"syntology":null},{"url":null,"slug":"formula-supervised-visual-geometric-pre","title":"Formula-Supervised Visual-Geometric Pre-training","date":"2024-09-20","arxiv_id":"2409.13535","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-play-video-games-with-intuitive","title":"Learning to Play Video Games with Intuitive Physics Priors","date":"2024-09-20","arxiv_id":"2409.13886","repositories_listed":0,"syntology":null},{"url":null,"slug":"end-to-end-open-vocabulary-video-visual","title":"End-to-end Open-vocabulary Video Visual Relationship Detection using Multi-modal Prompting","date":"2024-09-19","arxiv_id":"2409.12499","repositories_listed":0,"syntology":null},{"url":null,"slug":"frequency-guided-spatial-adaptation-for","title":"Frequency-Guided Spatial Adaptation for Camouflaged Object Detection","date":"2024-09-19","arxiv_id":"2409.12421","repositories_listed":0,"syntology":null},{"url":null,"slug":"interpretable-action-recognition-on-hard-to","title":"Interpretable Action Recognition on Hard to Classify Actions","date":"2024-09-19","arxiv_id":"2409.13091","repositories_listed":0,"syntology":null},{"url":null,"slug":"deteclap-enhancing-audio-visual","title":"DETECLAP: Enhancing Audio-Visual Representation Learning with Object Information","date":"2024-09-18","arxiv_id":"2409.11729","repositories_listed":0,"syntology":null},{"url":null,"slug":"end-to-end-probabilistic-geometry-guided","title":"End-to-End Probabilistic Geometry-Guided Regression for 6DoF Object Pose Estimation","date":"2024-09-18","arxiv_id":"2409.11819","repositories_listed":0,"syntology":null},{"url":null,"slug":"fast-gdrnpp-improving-the-speed-of-state-of","title":"FAST GDRNPP: Improving the Speed of State-of-the-Art 6D Object Pose Estimation","date":"2024-09-18","arxiv_id":"2409.12720","repositories_listed":0,"syntology":null},{"url":null,"slug":"one-map-to-find-them-all-real-time-open","title":"One Map to Find Them All: Real-time Open-Vocabulary Mapping for Zero-shot Multi-Object Navigation","date":"2024-09-18","arxiv_id":"2409.11764","repositories_listed":0,"syntology":null},{"url":null,"slug":"representing-positional-information-in","title":"Representing Positional Information in Generative World Models for Object Manipulation","date":"2024-09-18","arxiv_id":"2409.12005","repositories_listed":0,"syntology":null},{"url":"/paper/sim-ofe-structure-information-mining-and","slug":"sim-ofe-structure-information-mining-and","title":"SIM-OFE: Structure Information Mining and Object-aware Feature Enhancement for Fine-Grained Visual Categorization","date":"2024-09-18","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"open-set-semantic-uncertainty-aware-metric","title":"Open-Set Semantic Uncertainty Aware Metric-Semantic Graph Matching","date":"2024-09-17","arxiv_id":"2409.11555","repositories_listed":0,"syntology":null},{"url":null,"slug":"trajssl-trajectory-enhanced-semi-supervised","title":"TrajSSL: Trajectory-Enhanced Semi-Supervised 3D Object Detection","date":"2024-09-17","arxiv_id":"2409.10901","repositories_listed":0,"syntology":null},{"url":null,"slug":"lithohod-a-litho-simulator-powered-framework","title":"LithoHoD: A Litho Simulator-Powered Framework for IC Layout Hotspot Detection","date":"2024-09-16","arxiv_id":"2409.10021","repositories_listed":0,"syntology":null},{"url":null,"slug":"point2graph-an-end-to-end-point-cloud-based","title":"Point2Graph: An End-to-end Point Cloud-based 3D Open-Vocabulary Scene Graph for Robot Navigation","date":"2024-09-16","arxiv_id":"2409.10350","repositories_listed":0,"syntology":null},{"url":null,"slug":"realdiff-real-world-3d-shape-completion-using","title":"RealDiff: Real-world 3D Shape Completion using Self-Supervised Diffusion Models","date":"2024-09-16","arxiv_id":"2409.10180","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-weakly-supervised-object-detection","title":"Enhancing Weakly-Supervised Object Detection on Static Images through (Hallucinated) Motion","date":"2024-09-15","arxiv_id":"2409.09616","repositories_listed":0,"syntology":null},{"url":null,"slug":"narf24-estimating-articulated-object","title":"NARF24: Estimating Articulated Object Structure for Implicit Rendering","date":"2024-09-15","arxiv_id":"2409.09829","repositories_listed":0,"syntology":null},{"url":null,"slug":"childplay-hand-a-dataset-of-hand","title":"ChildPlay-Hand: A Dataset of Hand Manipulations in the Wild","date":"2024-09-14","arxiv_id":"2409.09319","repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluating-authenticity-and-quality-of-image","title":"Evaluating authenticity and quality of image captions via sentiment and semantic analyses","date":"2024-09-14","arxiv_id":"2409.09560","repositories_listed":0,"syntology":null},{"url":null,"slug":"interactive-masked-image-modeling-for","title":"Interactive Masked Image Modeling for Multimodal Object Detection in Remote Sensing","date":"2024-09-13","arxiv_id":"2409.08885","repositories_listed":0,"syntology":null}],"record_sha256":"2f2b6aaa4f5001083d931a0afbd965785a4f1cb161000593453ee64ed8fd94e1","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}