{"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/49","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":49,"pages_in_order":107,"rows_per_page":100,"rows":[4801,4900],"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/48","next":"/task/object/papers/50","papers":[{"url":null,"slug":"2408-01746","title":"Domain penalisation for improved Out-of-Distribution Generalisation","date":"2024-08-03","arxiv_id":"2408.01746","repositories_listed":0,"syntology":null},{"url":null,"slug":"2408-01843","title":"Supervised Image Translation from Visible to Infrared Domain for Object Detection","date":"2024-08-03","arxiv_id":"2408.01843","repositories_listed":0,"syntology":null},{"url":null,"slug":"2408-00967","title":"Extracting Object Heights From LiDAR & Aerial Imagery","date":"2024-08-02","arxiv_id":"2408.00967","repositories_listed":0,"syntology":null},{"url":null,"slug":"2408-01137","title":"PGNeXt: High-Resolution Salient Object Detection via Pyramid Grafting Network","date":"2024-08-02","arxiv_id":"2408.01137","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-adaptive-tensor-train-decomposition","title":"An Efficient Real-Time Object Detection Framework on Resource-Constricted Hardware Devices via Software and Hardware Co-design","date":"2024-08-02","arxiv_id":"2408.01534","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-simple-background-augmentation-method-for","title":"A Simple Background Augmentation Method for Object Detection with Diffusion Model","date":"2024-08-01","arxiv_id":"2408.00350","repositories_listed":0,"syntology":null},{"url":null,"slug":"diff3detr-agent-based-diffusion-model-for","title":"Diff3DETR:Agent-based Diffusion Model for Semi-supervised 3D Object Detection","date":"2024-08-01","arxiv_id":"2408.00286","repositories_listed":0,"syntology":null},{"url":null,"slug":"mufasa-multi-view-fusion-and-adaptation","title":"MUFASA: Multi-View Fusion and Adaptation Network with Spatial Awareness for Radar Object Detection","date":"2024-08-01","arxiv_id":"2408.00565","repositories_listed":0,"syntology":null},{"url":null,"slug":"social-media-management-system-project-report","title":"SOCIAL MEDIA MANAGEMENT SYSTEM PROJECT REPORT.","date":"2024-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"2407-21687","title":"Dynamic Object Queries for Transformer-based Incremental Object Detection","date":"2024-07-31","arxiv_id":"2407.21687","repositories_listed":0,"syntology":null},{"url":null,"slug":"ezsr-event-based-zero-shot-recognition","title":"EZSR: Event-based Zero-Shot Recognition","date":"2024-07-31","arxiv_id":"2407.21616","repositories_listed":0,"syntology":null},{"url":null,"slug":"pear-phrase-based-hand-object-interaction","title":"PEAR: Phrase-Based Hand-Object Interaction Anticipation","date":"2024-07-31","arxiv_id":"2407.21510","repositories_listed":0,"syntology":null},{"url":null,"slug":"what-is-yolov5-a-deep-look-into-the-internal","title":"What is YOLOv5: A deep look into the internal features of the popular object detector","date":"2024-07-30","arxiv_id":"2407.20892","repositories_listed":0,"syntology":null},{"url":null,"slug":"mevdt-multi-modal-event-based-vehicle","title":"MEVDT: Multi-Modal Event-Based Vehicle Detection and Tracking Dataset","date":"2024-07-29","arxiv_id":"2407.20446","repositories_listed":0,"syntology":null},{"url":"/paper/clickdiff-click-to-induce-semantic-contact","slug":"clickdiff-click-to-induce-semantic-contact","title":"ClickDiff: Click to Induce Semantic Contact Map for Controllable Grasp Generation with Diffusion Models","date":"2024-07-28","arxiv_id":"2407.19370","repositories_listed":0,"syntology":null},{"url":null,"slug":"progressive-domain-adaptation-for-thermal","title":"Progressive Domain Adaptation for Thermal Infrared Object Tracking","date":"2024-07-28","arxiv_id":"2407.19430","repositories_listed":0,"syntology":null},{"url":null,"slug":"floating-no-more-object-ground-reconstruction","title":"Floating No More: Object-Ground Reconstruction from a Single Image","date":"2024-07-26","arxiv_id":"2407.18914","repositories_listed":0,"syntology":null},{"url":null,"slug":"rapid-object-annotation","title":"Rapid Object Annotation","date":"2024-07-26","arxiv_id":"2407.18682","repositories_listed":0,"syntology":null},{"url":null,"slug":"shic-shape-image-correspondences-with-no","title":"SHIC: Shape-Image Correspondences with no Keypoint Supervision","date":"2024-07-26","arxiv_id":"2407.18907","repositories_listed":0,"syntology":null},{"url":null,"slug":"guided-latent-slot-diffusion-for-object","title":"Guided Latent Slot Diffusion for Object-Centric Learning","date":"2024-07-25","arxiv_id":"2407.17929","repositories_listed":0,"syntology":null},{"url":null,"slug":"xs-vid-an-extremely-small-video-object","title":"XS-VID: An Extremely Small Video Object Detection Dataset","date":"2024-07-25","arxiv_id":"2407.18137","repositories_listed":0,"syntology":null},{"url":null,"slug":"ai-based-density-recognition","title":"AI-based Density Recognition","date":"2024-07-24","arxiv_id":"2407.17064","repositories_listed":0,"syntology":null},{"url":null,"slug":"understanding-impacts-of-electromagnetic","title":"Understanding Impacts of Electromagnetic Signal Injection Attacks on Object Detection","date":"2024-07-23","arxiv_id":"2407.16327","repositories_listed":0,"syntology":null},{"url":null,"slug":"affordance-labeling-and-exploration-a","title":"Affordance Labeling and Exploration: A Manifold-Based Approach","date":"2024-07-22","arxiv_id":"2407.15479","repositories_listed":0,"syntology":null},{"url":null,"slug":"carformer-self-driving-with-learned-object","title":"CarFormer: Self-Driving with Learned Object-Centric Representations","date":"2024-07-22","arxiv_id":"2407.15843","repositories_listed":0,"syntology":null},{"url":null,"slug":"local-occupancy-enhanced-object-grasping-with","title":"Local Occupancy-Enhanced Object Grasping with Multiple Triplanar Projection","date":"2024-07-22","arxiv_id":"2407.15771","repositories_listed":0,"syntology":null},{"url":null,"slug":"ss-sfr-synthetic-scenes-spatial-frequency","title":"SS-SFR: Synthetic Scenes Spatial Frequency Response on Virtual KITTI and Degraded Automotive Simulations for Object Detection","date":"2024-07-22","arxiv_id":"2407.15646","repositories_listed":0,"syntology":null},{"url":null,"slug":"flow-as-the-cross-domain-manipulation","title":"Flow as the Cross-Domain Manipulation Interface","date":"2024-07-21","arxiv_id":"2407.15208","repositories_listed":0,"syntology":null},{"url":null,"slug":"hybrid-phd-pmb-trajectory-smoothing-using","title":"Hybrid PHD-PMB Trajectory Smoothing Using Backward Simulation","date":"2024-07-20","arxiv_id":"2407.14806","repositories_listed":0,"syntology":null},{"url":null,"slug":"rayformer-improving-query-based-multi-camera","title":"RayFormer: Improving Query-Based Multi-Camera 3D Object Detection via Ray-Centric Strategies","date":"2024-07-20","arxiv_id":"2407.14923","repositories_listed":0,"syntology":null},{"url":null,"slug":"emocam-toward-understanding-what-drives-cnn","title":"EmoCAM: Toward Understanding What Drives CNN-based Emotion Recognition","date":"2024-07-19","arxiv_id":"2407.14314","repositories_listed":0,"syntology":null},{"url":null,"slug":"interior-object-geometry-via-fitted-frames","title":"Interior Object Geometry via Fitted Frames","date":"2024-07-19","arxiv_id":"2407.14357","repositories_listed":0,"syntology":null},{"url":null,"slug":"octrack-benchmarking-the-open-corpus-multi","title":"OCTrack: Benchmarking the Open-Corpus Multi-Object Tracking","date":"2024-07-19","arxiv_id":"2407.14047","repositories_listed":0,"syntology":null},{"url":null,"slug":"pd-tpe-parallel-decoder-with-text-guided","title":"PD-APE: A Parallel Decoding Framework with Adaptive Position Encoding for 3D Visual Grounding","date":"2024-07-19","arxiv_id":"2407.14491","repositories_listed":0,"syntology":null},{"url":null,"slug":"dfmsd-dual-feature-masking-stage-wise","title":"DFMSD: Dual Feature Masking Stage-wise Knowledge Distillation for Object Detection","date":"2024-07-18","arxiv_id":"2407.13147","repositories_listed":0,"syntology":null},{"url":null,"slug":"focusdiffuser-perceiving-local-disparities","title":"FocusDiffuser: Perceiving Local Disparities for Camouflaged Object Detection","date":"2024-07-18","arxiv_id":"2407.13133","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-camouflaged-object-detection-from","title":"Learning Camouflaged Object Detection from Noisy Pseudo Label","date":"2024-07-18","arxiv_id":"2407.13157","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-visual-grounding-from-generative","title":"Learning Visual Grounding from Generative Vision and Language Model","date":"2024-07-18","arxiv_id":"2407.14563","repositories_listed":0,"syntology":null},{"url":null,"slug":"data-driven-verification-of-dnns-for-object","title":"Data-driven Verification of DNNs for Object Recognition","date":"2024-07-17","arxiv_id":"2408.00783","repositories_listed":0,"syntology":null},{"url":null,"slug":"himo-a-new-benchmark-for-full-body-human","title":"HIMO: A New Benchmark for Full-Body Human Interacting with Multiple Objects","date":"2024-07-17","arxiv_id":"2407.12371","repositories_listed":0,"syntology":null},{"url":null,"slug":"nl2contact-natural-language-guided-3d-hand","title":"NL2Contact: Natural Language Guided 3D Hand-Object Contact Modeling with Diffusion Model","date":"2024-07-17","arxiv_id":"2407.12727","repositories_listed":0,"syntology":null},{"url":null,"slug":"strawberry-detection-and-counting-based-on","title":"Strawberry detection and counting based on YOLOv7 pruning and information based tracking algorithm","date":"2024-07-17","arxiv_id":"2407.12614","repositories_listed":0,"syntology":null},{"url":"/paper/improving-unsupervised-video-object-1","slug":"improving-unsupervised-video-object-1","title":"Improving Unsupervised Video Object Segmentation via Fake Flow Generation","date":"2024-07-16","arxiv_id":"2407.11714","repositories_listed":0,"syntology":null},{"url":null,"slug":"maskvd-region-masking-for-efficient-video","title":"MaskVD: Region Masking for Efficient Video Object Detection","date":"2024-07-16","arxiv_id":"2407.12067","repositories_listed":0,"syntology":null},{"url":null,"slug":"anticipating-future-object-compositions","title":"Anticipating Future Object Compositions without Forgetting","date":"2024-07-15","arxiv_id":"2407.10723","repositories_listed":0,"syntology":null},{"url":null,"slug":"invi-object-insertion-in-videos-using-off-the","title":"InVi: Object Insertion In Videos Using Off-the-Shelf Diffusion Models","date":"2024-07-15","arxiv_id":"2407.10958","repositories_listed":0,"syntology":null},{"url":null,"slug":"3x2-3d-object-part-segmentation-by-2d","title":"3x2: 3D Object Part Segmentation by 2D Semantic Correspondences","date":"2024-07-12","arxiv_id":"2407.09648","repositories_listed":0,"syntology":null},{"url":null,"slug":"clover-context-aware-long-term-object","title":"CLOVER: Context-aware Long-term Object Viewpoint- and Environment- Invariant Representation Learning","date":"2024-07-12","arxiv_id":"2407.09718","repositories_listed":0,"syntology":null},{"url":null,"slug":"introducing-vada-novel-image-segmentation","title":"Introducing VaDA: Novel Image Segmentation Model for Maritime Object Segmentation Using New Dataset","date":"2024-07-12","arxiv_id":"2407.09005","repositories_listed":0,"syntology":null},{"url":null,"slug":"kgpose-keypoint-graph-driven-end-to-end-multi","title":"KGpose: Keypoint-Graph Driven End-to-End Multi-Object 6D Pose Estimation via Point-Wise Pose Voting","date":"2024-07-12","arxiv_id":"2407.08909","repositories_listed":0,"syntology":null},{"url":null,"slug":"stylesplat-3d-object-style-transfer-with","title":"StyleSplat: 3D Object Style Transfer with Gaussian Splatting","date":"2024-07-12","arxiv_id":"2407.09473","repositories_listed":0,"syntology":null},{"url":null,"slug":"hacman-spatially-grounded-motion-primitives","title":"HACMan++: Spatially-Grounded Motion Primitives for Manipulation","date":"2024-07-11","arxiv_id":"2407.08585","repositories_listed":0,"syntology":null},{"url":null,"slug":"omninocs-a-unified-nocs-dataset-and-model-for","title":"OmniNOCS: A unified NOCS dataset and model for 3D lifting of 2D objects","date":"2024-07-11","arxiv_id":"2407.08711","repositories_listed":0,"syntology":null},{"url":null,"slug":"semi-supervised-object-detection-a-survey-on-1","title":"Semi-Supervised Object Detection: A Survey on Progress from CNN to Transformer","date":"2024-07-11","arxiv_id":"2407.08460","repositories_listed":0,"syntology":null},{"url":"/paper/learning-spatial-semantic-features-for-robust","slug":"learning-spatial-semantic-features-for-robust","title":"Learning Spatial-Semantic Features for Robust Video Object Segmentation","date":"2024-07-10","arxiv_id":"2407.07760","repositories_listed":0,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":5,"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) · 0 unverified","sample_list":"/paper/learning-spatial-semantic-features-for-robust#ran","syntology_url":"https://syntology.ai/paper/2407.07760","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.07760"}},"official":null}},{"url":null,"slug":"lsm-a-comprehensive-metric-for-assessing-the","title":"LSM: A Comprehensive Metric for Assessing the Safety of Lane Detection Systems in Autonomous Driving","date":"2024-07-10","arxiv_id":"2407.07740","repositories_listed":0,"syntology":null},{"url":null,"slug":"vegetable-peeling-a-case-study-in-constrained","title":"Vegetable Peeling: A Case Study in Constrained Dexterous Manipulation","date":"2024-07-10","arxiv_id":"2407.07884","repositories_listed":0,"syntology":null},{"url":null,"slug":"category-level-object-detection-pose","title":"Category-level Object Detection, Pose Estimation and Reconstruction from Stereo Images","date":"2024-07-09","arxiv_id":"2407.06984","repositories_listed":0,"syntology":null},{"url":null,"slug":"rethinking-image-to-video-adaptation-an","title":"Rethinking Image-to-Video Adaptation: An Object-centric Perspective","date":"2024-07-09","arxiv_id":"2407.06871","repositories_listed":0,"syntology":null},{"url":null,"slug":"sketch-guided-scene-image-generation","title":"Sketch-Guided Scene Image Generation","date":"2024-07-09","arxiv_id":"2407.06469","repositories_listed":0,"syntology":null},{"url":null,"slug":"universal-multi-view-black-box-attack-against","title":"Universal Multi-view Black-box Attack against Object Detectors via Layout Optimization","date":"2024-07-09","arxiv_id":"2407.06688","repositories_listed":0,"syntology":null},{"url":null,"slug":"boosting-3d-object-detection-with-semantic","title":"Boosting 3D Object Detection with Semantic-Aware Multi-Branch Framework","date":"2024-07-08","arxiv_id":"2407.05769","repositories_listed":0,"syntology":null},{"url":null,"slug":"context-propagation-from-proposals-for","title":"Context Propagation from Proposals for Semantic Video Object Segmentation","date":"2024-07-08","arxiv_id":"2407.06247","repositories_listed":0,"syntology":null},{"url":null,"slug":"geowatch-for-detecting-heavy-construction-in","title":"GeoWATCH for Detecting Heavy Construction in Heterogeneous Time Series of Satellite Images","date":"2024-07-08","arxiv_id":"2407.06337","repositories_listed":0,"syntology":null},{"url":null,"slug":"submodular-video-object-proposal-selection","title":"Submodular video object proposal selection for semantic object segmentation","date":"2024-07-08","arxiv_id":"2407.05913","repositories_listed":0,"syntology":null},{"url":null,"slug":"targo-benchmarking-target-driven-object","title":"TARGO: Benchmarking Target-driven Object Grasping under Occlusions","date":"2024-07-08","arxiv_id":"2407.06168","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-reflected-object-detection-a","title":"Towards Reflected Object Detection: A Benchmark","date":"2024-07-08","arxiv_id":"2407.05575","repositories_listed":0,"syntology":null},{"url":null,"slug":"addressing-single-object-tracking-in","title":"Addressing single object tracking in satellite imagery through prompt-engineered solutions","date":"2024-07-07","arxiv_id":"2407.05518","repositories_listed":0,"syntology":null},{"url":null,"slug":"unlocking-textual-and-visual-wisdom-open","title":"Unlocking Textual and Visual Wisdom: Open-Vocabulary 3D Object Detection Enhanced by Comprehensive Guidance from Text and Image","date":"2024-07-07","arxiv_id":"2407.05256","repositories_listed":0,"syntology":null},{"url":null,"slug":"object-recognition-in-primates-what-can-early","title":"Object recognition in primates: What can early visual areas contribute?","date":"2024-07-05","arxiv_id":"2407.04816","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-stable-3d-object-detection","title":"Towards Stable 3D Object Detection","date":"2024-07-05","arxiv_id":"2407.04305","repositories_listed":0,"syntology":null},{"url":null,"slug":"beyond-viewpoint-robust-3d-object-recognition","title":"Beyond Viewpoint: Robust 3D Object Recognition under Arbitrary Views through Joint Multi-Part Representation","date":"2024-07-04","arxiv_id":"2407.03842","repositories_listed":0,"syntology":null},{"url":null,"slug":"fipgnet-pyramid-grafting-network-with-feature","title":"FIPGNet:Pyramid grafting network with feature interaction strategies","date":"2024-07-04","arxiv_id":"2407.04085","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-solution-for-the-gaiic2024-rgb-tir-object","title":"The Solution for the GAIIC2024 RGB-TIR object detection Challenge","date":"2024-07-04","arxiv_id":"2407.03872","repositories_listed":0,"syntology":null},{"url":null,"slug":"cyclic-refiner-object-aware-temporal","title":"Cyclic Refiner: Object-Aware Temporal Representation Learning for Multi-View 3D Detection and Tracking","date":"2024-07-03","arxiv_id":"2407.03240","repositories_listed":0,"syntology":null},{"url":null,"slug":"egoflownet-non-rigid-scene-flow-from-point","title":"EgoFlowNet: Non-Rigid Scene Flow from Point Clouds with Ego-Motion Support","date":"2024-07-03","arxiv_id":"2407.02920","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-disentangled-representation-in","title":"Learning Disentangled Representation in Object-Centric Models for Visual Dynamics Prediction via Transformers","date":"2024-07-03","arxiv_id":"2407.03216","repositories_listed":0,"syntology":null},{"url":null,"slug":"visual-grounding-with-attention-driven","title":"Visual Grounding with Attention-Driven Constraint Balancing","date":"2024-07-03","arxiv_id":"2407.03243","repositories_listed":0,"syntology":null},{"url":null,"slug":"hoimotion-forecasting-human-motion-during","title":"HOIMotion: Forecasting Human Motion During Human-Object Interactions Using Egocentric 3D Object Bounding Boxes","date":"2024-07-02","arxiv_id":"2407.02633","repositories_listed":0,"syntology":null},{"url":null,"slug":"magic-insert-style-aware-drag-and-drop","title":"Magic Insert: Style-Aware Drag-and-Drop","date":"2024-07-02","arxiv_id":"2407.02489","repositories_listed":0,"syntology":null},{"url":null,"slug":"grouped-discrete-representation-guides-object","title":"Grouped Discrete Representation Guides Object-Centric Learning","date":"2024-07-01","arxiv_id":"2407.01726","repositories_listed":0,"syntology":null},{"url":null,"slug":"scarecrow-monitoring-system-employing","title":"Scarecrow monitoring system:employing mobilenet ssd for enhanced animal supervision","date":"2024-07-01","arxiv_id":"2407.01435","repositories_listed":0,"syntology":null},{"url":null,"slug":"droboost-an-intelligent-score-and-model","title":"DroBoost: An Intelligent Score and Model Boosting Method for Drone Detection","date":"2024-06-30","arxiv_id":"2407.00830","repositories_listed":0,"syntology":null},{"url":null,"slug":"basketball-sort-an-association-method-for","title":"Basketball-SORT: An Association Method for Complex Multi-object Occlusion Problems in Basketball Multi-object Tracking","date":"2024-06-28","arxiv_id":"2406.19655","repositories_listed":0,"syntology":null},{"url":null,"slug":"egogaussian-dynamic-scene-understanding-from","title":"EgoGaussian: Dynamic Scene Understanding from Egocentric Video with 3D Gaussian Splatting","date":"2024-06-28","arxiv_id":"2406.19811","repositories_listed":0,"syntology":null},{"url":null,"slug":"object-space-is-embodied","title":"Object Space is Embodied","date":"2024-06-28","arxiv_id":"2406.19659","repositories_listed":0,"syntology":null},{"url":null,"slug":"poliformer-scaling-on-policy-rl-with","title":"PoliFormer: Scaling On-Policy RL with Transformers Results in Masterful Navigators","date":"2024-06-28","arxiv_id":"2406.20083","repositories_listed":0,"syntology":null},{"url":null,"slug":"maniwav-learning-robot-manipulation-from-in","title":"ManiWAV: Learning Robot Manipulation from In-the-Wild Audio-Visual Data","date":"2024-06-27","arxiv_id":"2406.19464","repositories_listed":0,"syntology":null},{"url":null,"slug":"3d-feature-distillation-with-object-centric","title":"3D Feature Distillation with Object-Centric Priors","date":"2024-06-26","arxiv_id":"2406.18742","repositories_listed":0,"syntology":null},{"url":null,"slug":"cts-sim-to-real-unsupervised-domain","title":"CTS: Sim-to-Real Unsupervised Domain Adaptation on 3D Detection","date":"2024-06-26","arxiv_id":"2406.18129","repositories_listed":0,"syntology":null},{"url":null,"slug":"human-aware-3d-scene-generation-with","title":"Human-Aware 3D Scene Generation with Spatially-constrained Diffusion Models","date":"2024-06-26","arxiv_id":"2406.18159","repositories_listed":0,"syntology":null},{"url":null,"slug":"spy-a-context-based-approach-to-spacecraft","title":"SpY: A Context-Based Approach to Spacecraft Component Detection","date":"2024-06-26","arxiv_id":"2406.18709","repositories_listed":0,"syntology":null},{"url":null,"slug":"et-tu-clip-addressing-common-object-errors","title":"ET tu, CLIP? Addressing Common Object Errors for Unseen Environments","date":"2024-06-25","arxiv_id":"2406.17876","repositories_listed":0,"syntology":null},{"url":null,"slug":"human-object-interaction-from-human-level","title":"Human-Object Interaction from Human-Level Instructions","date":"2024-06-25","arxiv_id":"2406.17840","repositories_listed":0,"syntology":null},{"url":null,"slug":"pixel-weighted-multi-pose-fusion-for-metal","title":"Pixel-weighted Multi-pose Fusion for Metal Artifact Reduction in X-ray Computed Tomography","date":"2024-06-25","arxiv_id":"2406.17897","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-open-set-camera-3d-object-detection","title":"Towards Open-set Camera 3D Object Detection","date":"2024-06-25","arxiv_id":"2406.17297","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-test-time-adaptation-for-object","title":"Exploring Test-Time Adaptation for Object Detection in Continually Changing Environments","date":"2024-06-24","arxiv_id":"2406.16439","repositories_listed":0,"syntology":null},{"url":null,"slug":"high-resolution-open-vocabulary-object-6d","title":"High-resolution open-vocabulary object 6D pose estimation","date":"2024-06-24","arxiv_id":"2406.16384","repositories_listed":0,"syntology":null},{"url":null,"slug":"ocalm-object-centric-assessment-with-language","title":"OCALM: Object-Centric Assessment with Language Models","date":"2024-06-24","arxiv_id":"2406.16748","repositories_listed":0,"syntology":null},{"url":null,"slug":"livescene-language-embedding-interactive","title":"LiveScene: Language Embedding Interactive Radiance Fields for Physical Scene Rendering and Control","date":"2024-06-23","arxiv_id":"2406.16038","repositories_listed":0,"syntology":null}],"record_sha256":"c76c76f6351f1ba653983db8fef0da7e55eef2d18676a06b9d930d18cfe982ad","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}