{"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-localization/papers/4","list_of":"/task/object-localization","task":"Object Localization","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":4,"pages_in_order":7,"rows_per_page":100,"rows":[301,400],"of":617,"counts":{"archive_papers_tagged":617,"with_a_code_link":282,"where_syntology_ran_a_sample":81,"not_listed_spam_title":0,"listed":617,"listed_where_code_ran":81,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":67,"every_run_a_failure_of_syntologys_instrument":14,"listed_with_a_run_with_no_instrument_failure":67,"listed_every_run_a_failure_of_syntologys_instrument":14,"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-localization","prev":"/task/object-localization/papers/3","next":"/task/object-localization/papers/5","papers":[{"url":null,"slug":"beyond-object-categories-multi-attribute","title":"Beyond Object Categories: Multi-Attribute Reference Understanding for Visual Grounding","date":"2025-03-25","arxiv_id":"2503.19240","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":"dr-splat-directly-referring-3d-gaussian","title":"Dr. Splat: Directly Referring 3D Gaussian Splatting via Direct Language Embedding Registration","date":"2025-02-23","arxiv_id":"2502.16652","repositories_listed":0,"syntology":null},{"url":null,"slug":"momentseeker-a-comprehensive-benchmark-and-a","title":"MomentSeeker: A Task-Oriented Benchmark For Long-Video Moment Retrieval","date":"2025-02-18","arxiv_id":"2502.12558","repositories_listed":0,"syntology":null},{"url":null,"slug":"auto-prompting-sam-for-weakly-supervised","title":"Auto-Prompting SAM for Weakly Supervised Landslide Extraction","date":"2025-01-23","arxiv_id":"2501.13426","repositories_listed":0,"syntology":null},{"url":null,"slug":"auxdepthnet-real-time-monocular-3d-object","title":"AuxDepthNet: Real-Time Monocular 3D Object Detection with Depth-Sensitive Features","date":"2025-01-07","arxiv_id":"2501.03700","repositories_listed":0,"syntology":null},{"url":null,"slug":"neuromorphic-optical-tracking-and-imaging-of","title":"Neuromorphic Optical Tracking and Imaging of Randomly Moving Targets through Strongly Scattering Media","date":"2025-01-07","arxiv_id":"2501.03874","repositories_listed":0,"syntology":null},{"url":null,"slug":"cross-modal-distillation-for-2d-3d-multi","title":"Cross-Modal Distillation for 2D/3D Multi-Object Discovery from 2D Motion","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"demystifying-the-potential-of-chatgpt-4","title":"Demystifying the Potential of ChatGPT-4 Vision for Construction Progress Monitoring","date":"2024-12-20","arxiv_id":"2412.16108","repositories_listed":0,"syntology":null},{"url":null,"slug":"supergseg-open-vocabulary-3d-segmentation","title":"SuperGSeg: Open-Vocabulary 3D Segmentation with Structured Super-Gaussians","date":"2024-12-13","arxiv_id":"2412.10231","repositories_listed":0,"syntology":null},{"url":null,"slug":"3d-spatial-understanding-in-mllms","title":"3D Spatial Understanding in MLLMs: Disambiguation and Evaluation","date":"2024-12-09","arxiv_id":"2412.06613","repositories_listed":0,"syntology":null},{"url":null,"slug":"seeground-see-and-ground-for-zero-shot-open","title":"SeeGround: See and Ground for Zero-Shot Open-Vocabulary 3D Visual Grounding","date":"2024-12-05","arxiv_id":"2412.04383","repositories_listed":0,"syntology":null},{"url":null,"slug":"relocate-a-simple-training-free-baseline-for","title":"RELOCATE: A Simple Training-Free Baseline for Visual Query Localization Using Region-Based Representations","date":"2024-12-02","arxiv_id":"2412.01826","repositories_listed":0,"syntology":null},{"url":"/paper/sparc-sparse-radar-camera-fusion-for-3d","slug":"sparc-sparse-radar-camera-fusion-for-3d","title":"SpaRC: Sparse Radar-Camera Fusion for 3D Object Detection","date":"2024-11-29","arxiv_id":"2411.19860","repositories_listed":0,"syntology":null},{"url":null,"slug":"objectrelator-enabling-cross-view-object","title":"ObjectRelator: Enabling Cross-View Object Relation Understanding in Ego-Centric and Exo-Centric Videos","date":"2024-11-28","arxiv_id":"2411.19083","repositories_listed":0,"syntology":null},{"url":null,"slug":"glofinder-ai-empowered-qupath-plugin-for-wsi","title":"GloFinder: AI-empowered QuPath Plugin for WSI-level Glomerular Detection, Visualization, and Curation","date":"2024-11-27","arxiv_id":"2411.18795","repositories_listed":0,"syntology":null},{"url":null,"slug":"probing-the-mid-level-vision-capabilities-of","title":"Probing the Mid-level Vision Capabilities of Self-Supervised Learning","date":"2024-11-25","arxiv_id":"2411.17474","repositories_listed":0,"syntology":null},{"url":null,"slug":"time-is-on-my-sight-scene-graph-filtering-for","title":"Time is on my sight: scene graph filtering for dynamic environment perception in an LLM-driven robot","date":"2024-11-22","arxiv_id":"2411.15027","repositories_listed":0,"syntology":null},{"url":null,"slug":"fast-splat-fast-ambiguity-free-semantics","title":"FAST-Splat: Fast, Ambiguity-Free Semantics Transfer in Gaussian Splatting","date":"2024-11-20","arxiv_id":"2411.13753","repositories_listed":0,"syntology":null},{"url":null,"slug":"text-guided-zero-shot-object-localization","title":"Text-guided Zero-Shot Object Localization","date":"2024-11-18","arxiv_id":"2411.11357","repositories_listed":0,"syntology":null},{"url":null,"slug":"visual-linguistic-agent-towards-collaborative","title":"Visual-Linguistic Agent: Towards Collaborative Contextual Object Reasoning","date":"2024-11-15","arxiv_id":"2411.10252","repositories_listed":0,"syntology":null},{"url":null,"slug":"ludvig-learning-free-uplifting-of-2d-visual","title":"LUDVIG: Learning-free Uplifting of 2D Visual features to Gaussian Splatting scenes","date":"2024-10-18","arxiv_id":"2410.14462","repositories_listed":0,"syntology":null},{"url":null,"slug":"co-segmentation-without-any-pixel-level","title":"Co-Segmentation without any Pixel-level Supervision with Application to Large-Scale Sketch Classification","date":"2024-10-17","arxiv_id":"2410.13582","repositories_listed":0,"syntology":null},{"url":null,"slug":"optimizing-multi-task-learning-for-accurate","title":"Optimizing Multi-Task Learning for Accurate Spacecraft Pose Estimation","date":"2024-10-16","arxiv_id":"2410.12679","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":null,"slug":"dial-dense-image-text-alignment-for-weakly","title":"DIAL: Dense Image-text ALignment for Weakly Supervised Semantic Segmentation","date":"2024-09-24","arxiv_id":"2409.15801","repositories_listed":0,"syntology":null},{"url":null,"slug":"pmr-net-parallel-multi-resolution-encoder","title":"PMR-Net: Parallel Multi-Resolution Encoder-Decoder Network Framework for Medical Image Segmentation","date":"2024-09-19","arxiv_id":"2409.12678","repositories_listed":0,"syntology":null},{"url":null,"slug":"top-gap-integrating-size-priors-in-cnns-for","title":"Top-GAP: Integrating Size Priors in CNNs for more Interpretability, Robustness, and Bias Mitigation","date":"2024-09-07","arxiv_id":"2409.04819","repositories_listed":0,"syntology":null},{"url":null,"slug":"prediction-accuracy-reliability","title":"Prediction Accuracy & Reliability: Classification and Object Localization under Distribution Shift","date":"2024-09-05","arxiv_id":"2409.03543","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-scale-multi-instance-visual-sound","title":"Multi-scale Multi-instance Visual Sound Localization and Segmentation","date":"2024-08-31","arxiv_id":"2409.00486","repositories_listed":0,"syntology":null},{"url":null,"slug":"lsms-language-guided-scale-aware-medsegmentor","title":"Language-guided Scale-aware MedSegmentor for Lesion Segmentation in Medical Imaging","date":"2024-08-30","arxiv_id":"2408.17347","repositories_listed":0,"syntology":null},{"url":null,"slug":"optimal-weight-scheme-for-fusion-assisted","title":"Optimal Weight Scheme for Fusion-Assisted Cooperative Multi-Monostatic Object Localization in 6G Networks","date":"2024-08-29","arxiv_id":"2408.16464","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-beam-object-localization-for-millimeter","title":"Multi-Beam Object-Localization for Millimeter-Wave ISAC-Aided Connected Autonomous Vehicles","date":"2024-08-26","arxiv_id":"2408.14312","repositories_listed":0,"syntology":null},{"url":null,"slug":"2408-01655","title":"Stimulating Imagination: Towards General-purpose Object Rearrangement","date":"2024-08-03","arxiv_id":"2408.01655","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-fused-recognition-fusing","title":"Categorical Knowledge Fused Recognition: Fusing Hierarchical Knowledge with Image Classification through Aligning and Deep Metric Learning","date":"2024-07-30","arxiv_id":"2407.20600","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-model-generalization-study-in-localizing","title":"A Model Generalization Study in Localizing Indoor Cows with COw LOcalization (COLO) dataset","date":"2024-07-29","arxiv_id":"2407.20372","repositories_listed":0,"syntology":null},{"url":null,"slug":"biv-priv-seg-locating-private-content-in","title":"BIV-Priv-Seg: Locating Private Content in Images Taken by People With Visual Impairments","date":"2024-07-25","arxiv_id":"2407.18243","repositories_listed":0,"syntology":null},{"url":null,"slug":"2408-01433","title":"Evaluating and Enhancing Trustworthiness of LLMs in Perception Tasks","date":"2024-07-18","arxiv_id":"2408.01433","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-activations-for-superpixel","title":"Leveraging Activations for Superpixel Explanations","date":"2024-06-07","arxiv_id":"2406.04933","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":"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":"real-world-instance-specific-image-goal","title":"Real-world Instance-specific Image Goal Navigation: Bridging Domain Gaps via Contrastive Learning","date":"2024-04-15","arxiv_id":"2404.09645","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":"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":"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":"spatio-temporal-bi-directional-cross-frame","title":"Spatio-Temporal Bi-directional Cross-frame Memory for Distractor Filtering Point Cloud Single Object Tracking","date":"2024-03-23","arxiv_id":"2403.15831","repositories_listed":0,"syntology":null},{"url":null,"slug":"point-detr3d-leveraging-imagery-data-with","title":"Point-DETR3D: Leveraging Imagery Data with Spatial Point Prior for Weakly Semi-supervised 3D Object Detection","date":"2024-03-22","arxiv_id":"2403.15317","repositories_listed":0,"syntology":null},{"url":null,"slug":"semantic-gaussians-open-vocabulary-scene","title":"Semantic Gaussians: Open-Vocabulary Scene Understanding with 3D Gaussian Splatting","date":"2024-03-22","arxiv_id":"2403.15624","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":"could-we-generate-cytology-images-from","title":"Could We Generate Cytology Images from Histopathology Images? An Empirical Study","date":"2024-03-16","arxiv_id":"2403.10885","repositories_listed":0,"syntology":null},{"url":null,"slug":"weakly-supervised-monocular-3d-detection-with","title":"Weakly Supervised Monocular 3D Detection with a Single-View Image","date":"2024-02-29","arxiv_id":"2402.19144","repositories_listed":0,"syntology":null},{"url":null,"slug":"retinotopic-mapping-enhances-the-robustness","title":"Foveated Retinotopy Improves Classification and Localization in CNNs","date":"2024-02-23","arxiv_id":"2402.15480","repositories_listed":0,"syntology":null},{"url":null,"slug":"toward-accurate-camera-based-3d-object","title":"Toward Accurate Camera-based 3D Object Detection via Cascade Depth Estimation and Calibration","date":"2024-02-07","arxiv_id":"2402.04883","repositories_listed":0,"syntology":null},{"url":null,"slug":"mssvt-mixed-scale-sparse-voxel-transformer","title":"MsSVT++: Mixed-scale Sparse Voxel Transformer with Center Voting for 3D Object Detection","date":"2024-01-22","arxiv_id":"2401.11718","repositories_listed":0,"syntology":null},{"url":null,"slug":"domain-adaptation-for-large-vocabulary-object","title":"Domain Adaptation for Large-Vocabulary Object Detectors","date":"2024-01-13","arxiv_id":"2401.06969","repositories_listed":0,"syntology":null},{"url":null,"slug":"gta-guided-transfer-of-spatial-attention-from","title":"GTA: Guided Transfer of Spatial Attention from Object-Centric Representations","date":"2024-01-05","arxiv_id":"2401.02656","repositories_listed":0,"syntology":null},{"url":null,"slug":"cyclic-learning-for-binaural-audio-generation","title":"Cyclic Learning for Binaural Audio Generation and Localization","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"fred-towards-a-full-rotation-equivariance-in","title":"FRED: Towards a Full Rotation-Equivariance in Aerial Image Object Detection","date":"2023-12-22","arxiv_id":"2401.06159","repositories_listed":0,"syntology":null},{"url":null,"slug":"weakly-supervised-open-vocabulary-object","title":"Weakly Supervised Open-Vocabulary Object Detection","date":"2023-12-19","arxiv_id":"2312.12437","repositories_listed":0,"syntology":null},{"url":null,"slug":"multiscale-vision-transformer-with-deep","title":"Multiscale Vision Transformer With Deep Clustering-Guided Refinement for Weakly Supervised Object Localization","date":"2023-12-15","arxiv_id":"2312.09584","repositories_listed":0,"syntology":null},{"url":null,"slug":"zero-shot-point-cloud-registration","title":"ZeroReg: Zero-Shot Point Cloud Registration with Foundation Models","date":"2023-12-05","arxiv_id":"2312.03032","repositories_listed":0,"syntology":null},{"url":null,"slug":"sanerf-hq-segment-anything-for-nerf-in-high","title":"SANeRF-HQ: Segment Anything for NeRF in High Quality","date":"2023-12-03","arxiv_id":"2312.01531","repositories_listed":0,"syntology":null},{"url":null,"slug":"seeing-beyond-cancer-multi-institutional","title":"Seeing Beyond Cancer: Multi-Institutional Validation of Object Localization and 3D Semantic Segmentation using Deep Learning for Breast MRI","date":"2023-11-27","arxiv_id":"2311.16213","repositories_listed":0,"syntology":null},{"url":null,"slug":"cooperative-multi-monostatic-sensing-for","title":"Cooperative Multi-Monostatic Sensing for Object Localization in 6G Networks","date":"2023-11-24","arxiv_id":"2311.14591","repositories_listed":0,"syntology":null},{"url":null,"slug":"dua-da-distillation-based-unbiased-alignment","title":"DSD-DA: Distillation-based Source Debiasing for Domain Adaptive Object Detection","date":"2023-11-17","arxiv_id":"2311.10437","repositories_listed":0,"syntology":null},{"url":null,"slug":"object-pose-estimation-annotation-pipeline","title":"Object Pose Estimation Annotation Pipeline for Multi-view Monocular Camera Systems in Industrial Settings","date":"2023-10-23","arxiv_id":"2310.14914","repositories_listed":0,"syntology":null},{"url":null,"slug":"clip-meets-model-zoo-experts-pseudo","title":"CLIP meets Model Zoo Experts: Pseudo-Supervision for Visual Enhancement","date":"2023-10-21","arxiv_id":"2310.14108","repositories_listed":0,"syntology":null},{"url":null,"slug":"memory-efficient-particle-filter-recurrent","title":"Memory-efficient particle filter recurrent neural network for object localization","date":"2023-10-02","arxiv_id":"2310.01595","repositories_listed":0,"syntology":null},{"url":null,"slug":"deepadain-net-deep-adaptive-device-edge","title":"DeepAdaIn-Net: Deep Adaptive Device-Edge Collaborative Inference for Augmented Reality","date":"2023-09-22","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"sempart-self-supervised-multi-resolution","title":"SEMPART: Self-supervised Multi-resolution Partitioning of Image Semantics","date":"2023-09-20","arxiv_id":"2309.10972","repositories_listed":0,"syntology":null},{"url":null,"slug":"hilm-d-towards-high-resolution-understanding","title":"HiLM-D: Towards High-Resolution Understanding in Multimodal Large Language Models for Autonomous Driving","date":"2023-09-11","arxiv_id":"2309.05186","repositories_listed":0,"syntology":null},{"url":null,"slug":"three-ways-to-improve-verbo-visual-fusion-for","title":"Four Ways to Improve Verbo-visual Fusion for Dense 3D Visual Grounding","date":"2023-09-08","arxiv_id":"2309.04561","repositories_listed":0,"syntology":null},{"url":null,"slug":"semantic-constraint-matching-transformer-for","title":"Semantic-Constraint Matching Transformer for Weakly Supervised Object Localization","date":"2023-09-04","arxiv_id":"2309.01331","repositories_listed":0,"syntology":null},{"url":null,"slug":"i3dod-towards-incremental-3d-object-detection","title":"I3DOD: Towards Incremental 3D Object Detection via Prompting","date":"2023-08-24","arxiv_id":"2308.12512","repositories_listed":0,"syntology":null},{"url":null,"slug":"video-owl-vit-temporally-consistent-open","title":"Video OWL-ViT: Temporally-consistent open-world localization in video","date":"2023-08-22","arxiv_id":"2308.11093","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-grounded-visual-spatial-reasoning-in","title":"Towards Grounded Visual Spatial Reasoning in Multi-Modal Vision Language Models","date":"2023-08-18","arxiv_id":"2308.09778","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-next-active-objects-for-context","title":"Leveraging Next-Active Objects for Context-Aware Anticipation in Egocentric Videos","date":"2023-08-16","arxiv_id":"2308.08303","repositories_listed":0,"syntology":null},{"url":null,"slug":"rethinking-the-localization-in-weakly","title":"Rethinking the Localization in Weakly Supervised Object Localization","date":"2023-08-11","arxiv_id":"2308.06161","repositories_listed":0,"syntology":null},{"url":null,"slug":"rapid-training-data-creation-by-synthesizing","title":"Rapid Training Data Creation by Synthesizing Medical Images for Classification and Localization","date":"2023-08-09","arxiv_id":"2308.04687","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-memory-augmented-multi-task-collaborative","title":"A Memory-Augmented Multi-Task Collaborative Framework for Unsupervised Traffic Accident Detection in Driving Videos","date":"2023-07-27","arxiv_id":"2307.14575","repositories_listed":0,"syntology":null},{"url":null,"slug":"mpdiou-a-loss-for-efficient-and-accurate","title":"MPDIoU: A Loss for Efficient and Accurate Bounding Box Regression","date":"2023-07-14","arxiv_id":"2307.07662","repositories_listed":0,"syntology":null},{"url":null,"slug":"open-vocabulary-object-detection-via-scene","title":"Open-Vocabulary Object Detection via Scene Graph Discovery","date":"2023-07-07","arxiv_id":"2307.03339","repositories_listed":0,"syntology":null},{"url":null,"slug":"neurocs-neural-nocs-supervision-for-monocular-1","title":"NeurOCS: Neural NOCS Supervision for Monocular 3D Object Localization","date":"2023-05-28","arxiv_id":"2305.17763","repositories_listed":0,"syntology":null},{"url":null,"slug":"mitigating-biased-activation-in-weakly","title":"Counterfactual Co-occurring Learning for Bias Mitigation in Weakly-supervised Object Localization","date":"2023-05-24","arxiv_id":"2305.15354","repositories_listed":0,"syntology":null},{"url":null,"slug":"probing-the-role-of-positional-information-in-2","title":"Probing the Role of Positional Information in Vision-Language Models","date":"2023-05-17","arxiv_id":"2305.10046","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-systematic-study-on-object-recognition","title":"A Systematic Study on Object Recognition Using Millimeter-wave Radar","date":"2023-05-03","arxiv_id":"2305.02085","repositories_listed":0,"syntology":null},{"url":null,"slug":"av-sam-segment-anything-model-meets-audio","title":"AV-SAM: Segment Anything Model Meets Audio-Visual Localization and Segmentation","date":"2023-05-03","arxiv_id":"2305.01836","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-search-for-and-detect-objects-in","title":"Learning to search for and detect objects in foveal images using deep learning","date":"2023-04-12","arxiv_id":"2304.05741","repositories_listed":0,"syntology":null},{"url":null,"slug":"most-multiple-object-localization-with-self","title":"MOST: Multiple Object localization with Self-supervised Transformers for object discovery","date":"2023-04-11","arxiv_id":"2304.05387","repositories_listed":0,"syntology":null},{"url":null,"slug":"few-shot-geometry-aware-keypoint-localization","title":"Few-shot Geometry-Aware Keypoint Localization","date":"2023-03-30","arxiv_id":"2303.17216","repositories_listed":0,"syntology":null},{"url":null,"slug":"rethinking-ai-explainability-and-plausibility","title":"Why is plausibility surprisingly problematic as an XAI criterion?","date":"2023-03-30","arxiv_id":"2303.17707","repositories_listed":0,"syntology":null},{"url":null,"slug":"diffusionseg-adapting-diffusion-towards","title":"DiffusionSeg: Adapting Diffusion Towards Unsupervised Object Discovery","date":"2023-03-17","arxiv_id":"2303.09813","repositories_listed":0,"syntology":null},{"url":null,"slug":"query-guided-attention-in-vision-transformers","title":"Query-guided Attention in Vision Transformers for Localizing Objects Using a Single Sketch","date":"2023-03-15","arxiv_id":"2303.08784","repositories_listed":0,"syntology":null},{"url":null,"slug":"fingerslam-closed-loop-unknown-object","title":"FingerSLAM: Closed-loop Unknown Object Localization and Reconstruction from Visuo-tactile Feedback","date":"2023-03-14","arxiv_id":"2303.07997","repositories_listed":0,"syntology":null},{"url":null,"slug":"multiparticle-kalman-filter-for-object","title":"Multiparticle Kalman filter for object localization in symmetric environments","date":"2023-03-14","arxiv_id":"2303.07897","repositories_listed":0,"syntology":null},{"url":null,"slug":"joint-ann-snn-co-training-for-object","title":"Joint ANN-SNN Co-training for Object Localization and Image Segmentation","date":"2023-03-10","arxiv_id":"2303.12738","repositories_listed":0,"syntology":null},{"url":null,"slug":"3d-aware-object-localization-using-gaussian","title":"3D-Aware Object Localization using Gaussian Implicit Occupancy Function","date":"2023-03-03","arxiv_id":"2303.02058","repositories_listed":0,"syntology":null},{"url":null,"slug":"confidence-driven-bounding-box-localization","title":"Confidence-driven Bounding Box Localization for Small Object Detection","date":"2023-03-03","arxiv_id":"2303.01803","repositories_listed":0,"syntology":null},{"url":null,"slug":"nu-air-a-neuromorphic-urban-aerial-dataset","title":"NU-AIR -- A Neuromorphic Urban Aerial Dataset for Detection and Localization of Pedestrians and Vehicles","date":"2023-02-18","arxiv_id":"2302.09429","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-application-of-deep-learning-for-sweet","title":"An Application of Deep Learning for Sweet Cherry Phenotyping using YOLO Object Detection","date":"2023-02-13","arxiv_id":"2302.06698","repositories_listed":0,"syntology":null}],"record_sha256":"123b2b4b10ae9f0db05a394f5f0570d538c929aef8ad2298a48b80f3ba04dd4e","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}