{"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/scene-understanding/papers/13","list_of":"/task/scene-understanding","task":"Scene Understanding","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":13,"pages_in_order":18,"rows_per_page":100,"rows":[1201,1300],"of":1723,"counts":{"archive_papers_tagged":1723,"with_a_code_link":720,"where_syntology_ran_a_sample":208,"not_listed_spam_title":0,"listed":1723,"listed_where_code_ran":208,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":182,"every_run_a_failure_of_syntologys_instrument":26,"listed_with_a_run_with_no_instrument_failure":182,"listed_every_run_a_failure_of_syntologys_instrument":26,"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/scene-understanding","prev":"/task/scene-understanding/papers/12","next":"/task/scene-understanding/papers/14","papers":[{"url":null,"slug":"style-transfer-based-speech-and-audio-visual","title":"Style-transfer based Speech and Audio-visual Scene Understanding for Robot Action Sequence Acquisition from Videos","date":"2023-06-27","arxiv_id":"2306.15644","repositories_listed":0,"syntology":null},{"url":null,"slug":"semantic-aware-transmission-for-robust-point","title":"Semantic-aware Transmission for Robust Point Cloud Classification","date":"2023-06-23","arxiv_id":"2306.13296","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-unseen-triples-effective-text-image","title":"Towards Unseen Triples: Effective Text-Image-joint Learning for Scene Graph Generation","date":"2023-06-23","arxiv_id":"2306.13420","repositories_listed":0,"syntology":null},{"url":null,"slug":"mo-vln-a-multi-task-benchmark-for-open-set","title":"CorNav: Autonomous Agent with Self-Corrected Planning for Zero-Shot Vision-and-Language Navigation","date":"2023-06-17","arxiv_id":"2306.10322","repositories_listed":0,"syntology":null},{"url":null,"slug":"dorsal-diffusion-for-object-centric","title":"DORSal: Diffusion for Object-centric Representations of Scenes et al","date":"2023-06-13","arxiv_id":"2306.08068","repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-projection-mapping-using-reflectance","title":"Neural Projection Mapping Using Reflectance Fields","date":"2023-06-11","arxiv_id":"2306.06595","repositories_listed":0,"syntology":null},{"url":null,"slug":"snel-a-structured-neuro-symbolic-language-for","title":"SNeL: A Structured Neuro-Symbolic Language for Entity-Based Multimodal Scene Understanding","date":"2023-06-09","arxiv_id":"2306.06036","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-dynamic-feature-interaction-framework-for","title":"A Dynamic Feature Interaction Framework for Multi-task Visual Perception","date":"2023-06-08","arxiv_id":"2306.05061","repositories_listed":0,"syntology":null},{"url":"/paper/topomask-instance-mask-based-formulation-for","slug":"topomask-instance-mask-based-formulation-for","title":"TopoMask: Instance-Mask-Based Formulation for the Road Topology Problem via Transformer-Based Architecture","date":"2023-06-08","arxiv_id":"2306.05419","repositories_listed":0,"syntology":null},{"url":null,"slug":"disaster-anomaly-detector-via-deeper-fcdds","title":"Disaster Anomaly Detector via Deeper FCDDs for Explainable Initial Responses","date":"2023-06-05","arxiv_id":"2306.02517","repositories_listed":0,"syntology":null},{"url":null,"slug":"recyclable-semi-supervised-method-based-on","title":"Recyclable Semi-supervised Method Based on Multi-model Ensemble for Video Scene Parsing","date":"2023-06-05","arxiv_id":"2306.02894","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-clip-contrastive-vision-language-pre","title":"Multi-CLIP: Contrastive Vision-Language Pre-training for Question Answering tasks in 3D Scenes","date":"2023-06-04","arxiv_id":"2306.02329","repositories_listed":0,"syntology":null},{"url":null,"slug":"dynamic-clustering-transformer-network-for","title":"Dynamic Clustering Transformer Network for Point Cloud Segmentation","date":"2023-05-30","arxiv_id":"2306.08073","repositories_listed":0,"syntology":null},{"url":null,"slug":"fairness-continual-learning-approach-to","title":"Fairness Continual Learning Approach to Semantic Scene Understanding in Open-World Environments","date":"2023-05-25","arxiv_id":"2305.15700","repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-category-level-3d-pose-estimation-from","title":"Robust Category-Level 3D Pose Estimation from Synthetic Data","date":"2023-05-25","arxiv_id":"2305.16124","repositories_listed":0,"syntology":null},{"url":null,"slug":"panocontext-former-panoramic-total-scene","title":"PanoContext-Former: Panoramic Total Scene Understanding with a Transformer","date":"2023-05-21","arxiv_id":"2305.12497","repositories_listed":0,"syntology":null},{"url":null,"slug":"vision-language-pre-training-with-object","title":"Vision-Language Pre-training with Object Contrastive Learning for 3D Scene Understanding","date":"2023-05-18","arxiv_id":"2305.10714","repositories_listed":0,"syntology":null},{"url":null,"slug":"metamorphosis-task-oriented-privacy-cognizant","title":"MetaMorphosis: Task-oriented Privacy Cognizant Feature Generation for Multi-task Learning","date":"2023-05-13","arxiv_id":"2305.07815","repositories_listed":0,"syntology":null},{"url":null,"slug":"hear-to-segment-unmixing-the-audio-to-guide","title":"Transavs: End-To-End Audio-Visual Segmentation With Transformer","date":"2023-05-12","arxiv_id":"2305.07223","repositories_listed":0,"syntology":null},{"url":"/paper/incorporating-structured-representations-into","slug":"incorporating-structured-representations-into","title":"Incorporating Structured Representations into Pretrained Vision & Language Models Using Scene Graphs","date":"2023-05-10","arxiv_id":"2305.06343","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-supervised-pre-training-with-masked","title":"Self-supervised Pre-training with Masked Shape Prediction for 3D Scene Understanding","date":"2023-05-08","arxiv_id":"2305.05026","repositories_listed":0,"syntology":null},{"url":null,"slug":"living-in-a-material-world-learning-material","title":"Living in a Material World: Learning Material Properties from Full-Waveform Flash Lidar Data for Semantic Segmentation","date":"2023-05-07","arxiv_id":"2305.04334","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-based-relational-object-matching","title":"Learning-based Relational Object Matching Across Views","date":"2023-05-03","arxiv_id":"2305.02398","repositories_listed":0,"syntology":null},{"url":null,"slug":"ark-augmented-reality-with-knowledge","title":"ArK: Augmented Reality with Knowledge Interactive Emergent Ability","date":"2023-05-01","arxiv_id":"2305.00970","repositories_listed":0,"syntology":null},{"url":null,"slug":"compositional-3d-human-object-neural","title":"Compositional 3D Human-Object Neural Animation","date":"2023-04-27","arxiv_id":"2304.14070","repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-implicit-dense-semantic-slam","title":"Neural Implicit Dense Semantic SLAM","date":"2023-04-27","arxiv_id":"2304.14560","repositories_listed":0,"syntology":null},{"url":null,"slug":"zrg-a-high-resolution-3d-residential-rooftop","title":"ZRG: A Dataset for Multimodal 3D Residential Rooftop Understanding","date":"2023-04-26","arxiv_id":"2304.13219","repositories_listed":0,"syntology":null},{"url":null,"slug":"factored-neural-representation-for-scene","title":"Factored Neural Representation for Scene Understanding","date":"2023-04-21","arxiv_id":"2304.10950","repositories_listed":0,"syntology":null},{"url":null,"slug":"360-circ-high-resolution-depth-estimation-via","title":"360$^\\circ$ High-Resolution Depth Estimation via Uncertainty-aware Structural Knowledge Transfer","date":"2023-04-17","arxiv_id":"2304.07967","repositories_listed":0,"syntology":null},{"url":null,"slug":"video-kmax-a-simple-unified-approach-for","title":"Video-kMaX: A Simple Unified Approach for Online and Near-Online Video Panoptic Segmentation","date":"2023-04-10","arxiv_id":"2304.04694","repositories_listed":0,"syntology":null},{"url":null,"slug":"object-agnostic-affordance-categorization-via","title":"Object-agnostic Affordance Categorization via Unsupervised Learning of Graph Embeddings","date":"2023-03-30","arxiv_id":"2304.05989","repositories_listed":0,"syntology":null},{"url":null,"slug":"both-style-and-distortion-matter-dual-path","title":"Both Style and Distortion Matter: Dual-Path Unsupervised Domain Adaptation for Panoramic Semantic Segmentation","date":"2023-03-25","arxiv_id":"2303.14360","repositories_listed":0,"syntology":null},{"url":null,"slug":"uni-fusion-universal-continuous-mapping","title":"Uni-Fusion: Universal Continuous Mapping","date":"2023-03-22","arxiv_id":"2303.12678","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-content-adaptive-learnable-time-frequency","title":"Content Adaptive Front End For Audio Classification","date":"2023-03-18","arxiv_id":"2303.10446","repositories_listed":0,"syntology":null},{"url":null,"slug":"shifted-windows-transformers-for-the","title":"Shifted-Windows Transformers for the Detection of Cerebral Aneurysms in Microsurgery","date":"2023-03-16","arxiv_id":"2303.09648","repositories_listed":0,"syntology":null},{"url":null,"slug":"camera-radar-perception-for-autonomous","title":"Camera-Radar Perception for Autonomous Vehicles and ADAS: Concepts, Datasets and Metrics","date":"2023-03-08","arxiv_id":"2303.04302","repositories_listed":0,"syntology":null},{"url":null,"slug":"clip-fo3d-learning-free-open-world-3d-scene","title":"CLIP-FO3D: Learning Free Open-world 3D Scene Representations from 2D Dense CLIP","date":"2023-03-08","arxiv_id":"2303.04748","repositories_listed":0,"syntology":null},{"url":"/paper/unified-perception-efficient-video-panoptic","slug":"unified-perception-efficient-video-panoptic","title":"Unified Perception: Efficient Depth-Aware Video Panoptic Segmentation with Minimal Annotation Costs","date":"2023-03-03","arxiv_id":"2303.01991","repositories_listed":0,"syntology":null},{"url":null,"slug":"aparate-adaptive-adversarial-patch-for-cnn","title":"APARATE: Adaptive Adversarial Patch for CNN-based Monocular Depth Estimation for Autonomous Navigation","date":"2023-03-02","arxiv_id":"2303.01351","repositories_listed":0,"syntology":null},{"url":null,"slug":"weakly-supervised-hoi-detection-via-prior","title":"Weakly-supervised HOI Detection via Prior-guided Bi-level Representation Learning","date":"2023-03-02","arxiv_id":"2303.01313","repositories_listed":0,"syntology":null},{"url":null,"slug":"mask3d-pre-training-2d-vision-transformers-by","title":"Mask3D: Pre-training 2D Vision Transformers by Learning Masked 3D Priors","date":"2023-02-28","arxiv_id":"2302.14746","repositories_listed":0,"syntology":null},{"url":null,"slug":"uavsnet-an-encoder-decoder-architecture-based","title":"RemoteNet: Remote Sensing Image Segmentation Network based on Global-Local Information","date":"2023-02-25","arxiv_id":"2302.13084","repositories_listed":0,"syntology":null},{"url":null,"slug":"open-challenges-for-monocular-single-shot-6d","title":"Open Challenges for Monocular Single-shot 6D Object Pose Estimation","date":"2023-02-23","arxiv_id":"2302.11827","repositories_listed":0,"syntology":null},{"url":null,"slug":"explicit3d-graph-network-with-spatial","title":"Explicit3D: Graph Network with Spatial Inference for Single Image 3D Object Detection","date":"2023-02-13","arxiv_id":"2302.06494","repositories_listed":0,"syntology":null},{"url":null,"slug":"object-centric-scene-representations-using","title":"Object-Centric Scene Representations using Active Inference","date":"2023-02-07","arxiv_id":"2302.03288","repositories_listed":0,"syntology":null},{"url":null,"slug":"structured-generative-models-for-scene","title":"Structured Generative Models for Scene Understanding","date":"2023-02-07","arxiv_id":"2302.03531","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-flexible-framework-for-virtual","title":"A Flexible Framework for Virtual Omnidirectional Vision to Improve Operator Situation Awareness","date":"2023-02-01","arxiv_id":"2302.00362","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-from-mistakes-self-regularizing","title":"Learning from Mistakes: Self-Regularizing Hierarchical Representations in Point Cloud Semantic Segmentation","date":"2023-01-26","arxiv_id":"2301.11145","repositories_listed":0,"syntology":null},{"url":null,"slug":"long-range-pooling-for-3d-large-scale-scene","title":"Long Range Pooling for 3D Large-Scale Scene Understanding","date":"2023-01-17","arxiv_id":"2301.06962","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-comprehensive-review-of-modern-object","title":"A Comprehensive Review of Modern Object Segmentation Approaches","date":"2023-01-13","arxiv_id":"2301.07499","repositories_listed":0,"syntology":null},{"url":null,"slug":"combining-implicit-explicit-view-correlation","title":"Combining Implicit-Explicit View Correlation for Light Field Semantic Segmentation","date":"2023-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-geometric-aware-properties-in-2d","title":"Learning Geometric-Aware Properties in 2D Representation Using Lightweight CAD Models, or Zero Real 3D Pairs","date":"2023-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"plausible-uncertainties-for-human-pose","title":"Plausible Uncertainties for Human Pose Regression","date":"2023-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"realgraph-a-multiview-dataset-for-4d-real","title":"RealGraph: A Multiview Dataset for 4D Real-world Context Graph Generation","date":"2023-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"seeing-with-sound-long-range-acoustic","title":"Seeing With Sound: Long-range Acoustic Beamforming for Multimodal Scene Understanding","date":"2023-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"self-supervised-object-detection-from","title":"Self-Supervised Object Detection from Egocentric Videos","date":"2023-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"visual-traffic-knowledge-graph-generation","title":"Visual Traffic Knowledge Graph Generation from Scene Images","date":"2023-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"attentional-graph-convolutional-network-for","title":"Attentional Graph Convolutional Network for Structure-aware Audio-Visual Scene Classification","date":"2022-12-31","arxiv_id":"2301.00145","repositories_listed":0,"syntology":null},{"url":null,"slug":"mm-3dscene-3d-scene-understanding-by","title":"MM-3DScene: 3D Scene Understanding by Customizing Masked Modeling with Informative-Preserved Reconstruction and Self-Distilled Consistency","date":"2022-12-20","arxiv_id":"2212.09948","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-deeper-and-better-multi-view-feature","title":"Towards Deeper and Better Multi-view Feature Fusion for 3D Semantic Segmentation","date":"2022-12-13","arxiv_id":"2212.06682","repositories_listed":0,"syntology":null},{"url":null,"slug":"omnihorizon-in-the-wild-outdoors-depth-and","title":"Cross-Domain Synthetic-to-Real In-the-Wild Depth and Normal Estimation for 3D Scene Understanding","date":"2022-12-09","arxiv_id":"2212.05040","repositories_listed":0,"syntology":null},{"url":null,"slug":"gaussian-radar-transformer-for-semantic","title":"Gaussian Radar Transformer for Semantic Segmentation in Noisy Radar Data","date":"2022-12-07","arxiv_id":"2212.03690","repositories_listed":0,"syntology":null},{"url":null,"slug":"framework-for-2d-ad-placements-in-lineartv","title":"Framework for 2D Ad placements in LinearTV","date":"2022-12-05","arxiv_id":"2212.02450","repositories_listed":0,"syntology":null},{"url":null,"slug":"3d-object-aided-self-supervised-monocular","title":"3D Object Aided Self-Supervised Monocular Depth Estimation","date":"2022-12-04","arxiv_id":"2212.01768","repositories_listed":0,"syntology":null},{"url":null,"slug":"review-on-6d-object-pose-estimation-with-the","title":"Review on 6D Object Pose Estimation with the focus on Indoor Scene Understanding","date":"2022-12-04","arxiv_id":"2212.01920","repositories_listed":0,"syntology":null},{"url":null,"slug":"prediction-of-scene-plausibility","title":"Prediction of Scene Plausibility","date":"2022-12-02","arxiv_id":"2212.01470","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-3d-scene-priors-with-2d-supervision","title":"Learning 3D Scene Priors with 2D Supervision","date":"2022-11-25","arxiv_id":"2211.14157","repositories_listed":0,"syntology":null},{"url":null,"slug":"pointca-evaluating-the-robustness-of-3d-point","title":"PointCA: Evaluating the Robustness of 3D Point Cloud Completion Models Against Adversarial Examples","date":"2022-11-22","arxiv_id":"2211.12294","repositories_listed":0,"syntology":null},{"url":null,"slug":"object-level-3d-semantic-mapping-using-a","title":"Object-level 3D Semantic Mapping using a Network of Smart Edge Sensors","date":"2022-11-21","arxiv_id":"2211.11354","repositories_listed":0,"syntology":null},{"url":"/paper/an-enhanced-object-detection-model-for-scene","slug":"an-enhanced-object-detection-model-for-scene","title":"An Enhanced Object Detection Model for Scene Graph Generation","date":"2022-11-18","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"monocular-bev-perception-of-road-scenes-via","title":"Monocular BEV Perception of Road Scenes via Front-to-Top View Projection","date":"2022-11-15","arxiv_id":"2211.08144","repositories_listed":0,"syntology":null},{"url":null,"slug":"user-identification-the-key-enabler-for-multi","title":"User Identification: A Key Enabler for Multi-User Vision-Aided Communications","date":"2022-10-27","arxiv_id":"2210.15652","repositories_listed":0,"syntology":null},{"url":null,"slug":"visual-semantic-parsing-from-images-to","title":"Visual Semantic Parsing: From Images to Abstract Meaning Representation","date":"2022-10-26","arxiv_id":"2210.14862","repositories_listed":0,"syntology":null},{"url":"/paper/number-adaptive-prototype-learning-for-3d","slug":"number-adaptive-prototype-learning-for-3d","title":"Number-Adaptive Prototype Learning for 3D Point Cloud Semantic Segmentation","date":"2022-10-18","arxiv_id":"2210.09948","repositories_listed":0,"syntology":null},{"url":null,"slug":"novel-3d-scene-understanding-applications","title":"Novel 3D Scene Understanding Applications From Recurrence in a Single Image","date":"2022-10-14","arxiv_id":"2210.07991","repositories_listed":0,"syntology":null},{"url":null,"slug":"segmentation-guided-domain-adaptation-for","title":"Segmentation-guided Domain Adaptation for Efficient Depth Completion","date":"2022-10-14","arxiv_id":"2210.09213","repositories_listed":0,"syntology":null},{"url":null,"slug":"earthnets-empowering-ai-in-earth-observation","title":"EarthNets: Empowering AI in Earth Observation","date":"2022-10-10","arxiv_id":"2210.04936","repositories_listed":0,"syntology":null},{"url":null,"slug":"feature-realistic-neural-fusion-for-real-time","title":"Feature-Realistic Neural Fusion for Real-Time, Open Set Scene Understanding","date":"2022-10-06","arxiv_id":"2210.03043","repositories_listed":0,"syntology":null},{"url":null,"slug":"gaia-graphical-information-gain-based","title":"GaIA: Graphical Information Gain based Attention Network for Weakly Supervised Point Cloud Semantic Segmentation","date":"2022-10-02","arxiv_id":"2210.01558","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-on-knowledge-graph-based-methods-for","title":"A Survey on Knowledge Graph-based Methods for Automated Driving","date":"2022-09-30","arxiv_id":"2210.08119","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-multimodal-multitask-scene","title":"Towards Multimodal Multitask Scene Understanding Models for Indoor Mobile Agents","date":"2022-09-27","arxiv_id":"2209.13156","repositories_listed":0,"syntology":null},{"url":null,"slug":"stochastic-future-prediction-in-real-world","title":"Stochastic Future Prediction in Real World Driving Scenarios","date":"2022-09-21","arxiv_id":"2209.10693","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-review-on-visual-slam-advancements-from","title":"A Review on Visual-SLAM: Advancements from Geometric Modelling to Learning-based Semantic Scene Understanding","date":"2022-09-12","arxiv_id":"2209.05222","repositories_listed":0,"syntology":null},{"url":null,"slug":"neuromorphic-visual-scene-understanding-with","title":"Neuromorphic Visual Scene Understanding with Resonator Networks","date":"2022-08-26","arxiv_id":"2208.12880","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-in-audio-visual-context-a-review","title":"Learning in Audio-visual Context: A Review, Analysis, and New Perspective","date":"2022-08-20","arxiv_id":"2208.09579","repositories_listed":0,"syntology":null},{"url":null,"slug":"safety-assessment-for-autonomous-system","title":"Safety Assessment for Autonomous Systems' Perception Capabilities","date":"2022-08-17","arxiv_id":"2208.08237","repositories_listed":0,"syntology":null},{"url":null,"slug":"autolaparo-a-new-dataset-of-integrated-multi","title":"AutoLaparo: A New Dataset of Integrated Multi-tasks for Image-guided Surgical Automation in Laparoscopic Hysterectomy","date":"2022-08-03","arxiv_id":"2208.02049","repositories_listed":0,"syntology":null},{"url":null,"slug":"compnvs-novel-view-synthesis-with-scene","title":"CompNVS: Novel View Synthesis with Scene Completion","date":"2022-07-23","arxiv_id":"2207.11467","repositories_listed":0,"syntology":null},{"url":null,"slug":"seeing-3d-objects-in-a-single-image-via-self","title":"Neural Groundplans: Persistent Neural Scene Representations from a Single Image","date":"2022-07-22","arxiv_id":"2207.11232","repositories_listed":0,"syntology":null},{"url":null,"slug":"seasonet-a-seasonal-scene-classification","title":"SeasoNet: A Seasonal Scene Classification, segmentation and Retrieval dataset for satellite Imagery over Germany","date":"2022-07-19","arxiv_id":"2207.09507","repositories_listed":0,"syntology":null},{"url":null,"slug":"blindspotnet-seeing-where-we-cannot-see","title":"BlindSpotNet: Seeing Where We Cannot See","date":"2022-07-08","arxiv_id":"2207.03870","repositories_listed":0,"syntology":null},{"url":null,"slug":"scene-aware-prompt-for-multi-modal-dialogue","title":"Scene-Aware Prompt for Multi-modal Dialogue Understanding and Generation","date":"2022-07-05","arxiv_id":"2207.01823","repositories_listed":0,"syntology":null},{"url":null,"slug":"toward-explainable-and-fine-grained-3d","title":"Toward Explainable and Fine-Grained 3D Grounding through Referring Textual Phrases","date":"2022-07-05","arxiv_id":"2207.01821","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-dynamic-data-driven-approach-for","title":"A Dynamic Data Driven Approach for Explainable Scene Understanding","date":"2022-06-18","arxiv_id":"2206.09089","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-efficient-real-time-semantic-segmentation","title":"On Efficient Real-Time Semantic Segmentation: A Survey","date":"2022-06-17","arxiv_id":"2206.08605","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-multi-purpose-real-haze-benchmark-with","title":"A Multi-purpose Realistic Haze Benchmark with Quantifiable Haze Levels and Ground Truth","date":"2022-06-13","arxiv_id":"2206.06427","repositories_listed":0,"syntology":null},{"url":null,"slug":"beyond-rgb-scene-property-synthesis-with","title":"Beyond RGB: Scene-Property Synthesis with Neural Radiance Fields","date":"2022-06-09","arxiv_id":"2206.04669","repositories_listed":0,"syntology":null},{"url":null,"slug":"extracting-zero-shot-common-sense-from-large","title":"Extracting Zero-shot Common Sense from Large Language Models for Robot 3D Scene Understanding","date":"2022-06-09","arxiv_id":"2206.04585","repositories_listed":0,"syntology":null},{"url":null,"slug":"scan2part-fine-grained-and-hierarchical-part","title":"Scan2Part: Fine-grained and Hierarchical Part-level Understanding of Real-World 3D Scans","date":"2022-06-06","arxiv_id":"2206.02366","repositories_listed":0,"syntology":null},{"url":null,"slug":"conceptual-design-of-the-memory-system-of-the","title":"A Memory System of a Robot Cognitive Architecture and its Implementation in ArmarX","date":"2022-06-05","arxiv_id":"2206.02241","repositories_listed":0,"syntology":null}],"record_sha256":"ba6b33e10a8d6c693bcd62e725873451183c70339ac03664e783e57bfbaee59f","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}