{"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/14","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":14,"pages_in_order":18,"rows_per_page":100,"rows":[1301,1400],"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/13","next":"/task/scene-understanding/papers/15","papers":[{"url":null,"slug":"sample-hd-simultaneous-action-and-motion","title":"SAMPLE-HD: Simultaneous Action and Motion Planning Learning Environment","date":"2022-06-01","arxiv_id":"2206.10312","repositories_listed":0,"syntology":null},{"url":null,"slug":"review-on-panoramic-imaging-and-its","title":"Review on Panoramic Imaging and Its Applications in Scene Understanding","date":"2022-05-11","arxiv_id":"2205.05570","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-discovery-and-composition-of","title":"Unsupervised Discovery and Composition of Object Light Fields","date":"2022-05-08","arxiv_id":"2205.03923","repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-rendering-in-a-room-amodal-3d","title":"Neural Rendering in a Room: Amodal 3D Understanding and Free-Viewpoint Rendering for the Closed Scene Composed of Pre-Captured Objects","date":"2022-05-05","arxiv_id":"2205.02714","repositories_listed":0,"syntology":null},{"url":null,"slug":"rangeseg-range-aware-real-time-segmentation","title":"RangeSeg: Range-Aware Real Time Segmentation of 3D LiDAR Point Clouds","date":"2022-05-02","arxiv_id":"2205.01570","repositories_listed":0,"syntology":null},{"url":null,"slug":"bbbd-bounding-box-based-detector-for","title":"BBBD: Bounding Box Based Detector for Occlusion Detection and Order Recovery","date":"2022-04-27","arxiv_id":"2204.12841","repositories_listed":0,"syntology":null},{"url":null,"slug":"graph-detr3d-rethinking-overlapping-regions","title":"Graph-DETR3D: Rethinking Overlapping Regions for Multi-View 3D Object Detection","date":"2022-04-25","arxiv_id":"2204.11582","repositories_listed":0,"syntology":null},{"url":null,"slug":"scenetrilogy-on-scene-sketches-and-its","title":"SceneTrilogy: On Human Scene-Sketch and its Complementarity with Photo and Text","date":"2022-04-25","arxiv_id":"2204.11964","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-foundation-models-perform-zero-shot-task","title":"Can Foundation Models Perform Zero-Shot Task Specification For Robot Manipulation?","date":"2022-04-23","arxiv_id":"2204.11134","repositories_listed":0,"syntology":null},{"url":null,"slug":"selma-semantic-large-scale-multimodal","title":"SELMA: SEmantic Large-scale Multimodal Acquisitions in Variable Weather, Daytime and Viewpoints","date":"2022-04-20","arxiv_id":"2204.09788","repositories_listed":0,"syntology":null},{"url":null,"slug":"attention-mechanism-based-cognition-level","title":"Attention Mechanism based Cognition-level Scene Understanding","date":"2022-04-17","arxiv_id":"2204.08027","repositories_listed":0,"syntology":null},{"url":"/paper/mtanet-multitask-aware-network-with","slug":"mtanet-multitask-aware-network-with","title":"MTANet: Multitask-Aware Network With Hierarchical Multimodal Fusion for RGB-T Urban Scene Understanding","date":"2022-04-05","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-task-learning-for-visual-scene","title":"Multi-Task Learning for Visual Scene Understanding","date":"2022-03-28","arxiv_id":"2203.14896","repositories_listed":0,"syntology":null},{"url":null,"slug":"semi-supervised-and-deep-learning-frameworks","title":"Semi-supervised and Deep learning Frameworks for Video Classification and Key-frame Identification","date":"2022-03-25","arxiv_id":"2203.13459","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-escaping-from-language-bias-and-ocr","title":"Towards Escaping from Language Bias and OCR Error: Semantics-Centered Text Visual Question Answering","date":"2022-03-24","arxiv_id":"2203.12929","repositories_listed":0,"syntology":null},{"url":null,"slug":"iwin-human-object-interaction-detection-via","title":"Iwin: Human-Object Interaction Detection via Transformer with Irregular Windows","date":"2022-03-20","arxiv_id":"2203.10537","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-3d-scene-understanding-by-referring","title":"Towards 3D Scene Understanding by Referring Synthetic Models","date":"2022-03-20","arxiv_id":"2203.10546","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-point-cloud-simplification-for-high","title":"Deep Point Cloud Simplification for High-quality Surface Reconstruction","date":"2022-03-17","arxiv_id":"2203.09088","repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-part-priors-learning-to-optimize-part","title":"Neural Part Priors: Learning to Optimize Part-Based Object Completion in RGB-D Scans","date":"2022-03-17","arxiv_id":"2203.09375","repositories_listed":0,"syntology":null},{"url":null,"slug":"raum-vo-rotational-adjusted-unsupervised","title":"RAUM-VO: Rotational Adjusted Unsupervised Monocular Visual Odometry","date":"2022-03-14","arxiv_id":"2203.07162","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-steering-multi-annotations-per-sample-for","title":"On Steering Multi-Annotations per Sample for Multi-Task Learning","date":"2022-03-06","arxiv_id":"2203.02946","repositories_listed":0,"syntology":null},{"url":null,"slug":"fast-neural-architecture-search-for","title":"Fast Neural Architecture Search for Lightweight Dense Prediction Networks","date":"2022-03-03","arxiv_id":"2203.01994","repositories_listed":0,"syntology":null},{"url":null,"slug":"hybrid-optimized-deep-convolution-neural","title":"Hybrid Optimized Deep Convolution Neural Network based Learning Model for Object Detection","date":"2022-03-02","arxiv_id":"2203.00869","repositories_listed":0,"syntology":null},{"url":null,"slug":"movies2scenes-learning-scene-representations","title":"Movies2Scenes: Using Movie Metadata to Learn Scene Representation","date":"2022-02-22","arxiv_id":"2202.10650","repositories_listed":0,"syntology":null},{"url":null,"slug":"catch-me-if-you-can-a-novel-task-for","title":"Catch Me if You Can: A Novel Task for Detection of Covert Geo-Locations (CGL)","date":"2022-02-05","arxiv_id":"2202.02567","repositories_listed":0,"syntology":null},{"url":null,"slug":"standardsim-a-synthetic-dataset-for-retail","title":"StandardSim: A Synthetic Dataset For Retail Environments","date":"2022-02-04","arxiv_id":"2202.02418","repositories_listed":0,"syntology":null},{"url":null,"slug":"moving-beyond-navigation-with-active-neural","title":"Moving Beyond Navigation with Active Neural SLAM","date":"2022-01-17","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-holistic-scene-understanding-semantic","title":"Towards holistic scene understanding: Semantic segmentation and beyond","date":"2022-01-16","arxiv_id":"2201.07734","repositories_listed":0,"syntology":null},{"url":null,"slug":"interactive-attention-ai-to-translate-low","title":"Interactive Attention AI to translate low light photos to captions for night scene understanding in women safety","date":"2022-01-04","arxiv_id":"2201.00969","repositories_listed":0,"syntology":null},{"url":null,"slug":"scene-graph-generation-a-comprehensive-survey","title":"Scene Graph Generation: A Comprehensive Survey","date":"2022-01-03","arxiv_id":"2201.00443","repositories_listed":0,"syntology":null},{"url":"/paper/glass-segmentation-using-intensity-and","slug":"glass-segmentation-using-intensity-and","title":"Glass Segmentation Using Intensity and Spectral Polarization Cues","date":"2022-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"segment-fusion-hierarchical-context-fusion","title":"Segment-Fusion: Hierarchical Context Fusion for Robust 3D Semantic Segmentation","date":"2022-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/hspace-synthetic-parametric-humans-animated","slug":"hspace-synthetic-parametric-humans-animated","title":"HSPACE: Synthetic Parametric Humans Animated in Complex Environments","date":"2021-12-23","arxiv_id":"2112.12867","repositories_listed":0,"syntology":null},{"url":null,"slug":"distillation-of-human-object-interaction","title":"Distillation of Human-Object Interaction Contexts for Action Recognition","date":"2021-12-17","arxiv_id":"2112.09448","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-human-object-interaction-detection","title":"Improving Human-Object Interaction Detection via Phrase Learning and Label Composition","date":"2021-12-14","arxiv_id":"2112.07383","repositories_listed":0,"syntology":null},{"url":null,"slug":"image-to-height-domain-translation-for","title":"Image-to-Height Domain Translation for Synthetic Aperture Sonar","date":"2021-12-12","arxiv_id":"2112.06307","repositories_listed":0,"syntology":null},{"url":null,"slug":"3d-scene-understanding-at-urban-intersection","title":"3D Scene Understanding at Urban Intersection using Stereo Vision and Digital Map","date":"2021-12-10","arxiv_id":"2112.05295","repositories_listed":0,"syntology":null},{"url":null,"slug":"roominoes-generating-novel-3d-floor-plans","title":"Roominoes: Generating Novel 3D Floor Plans From Existing 3D Rooms","date":"2021-12-10","arxiv_id":"2112.05644","repositories_listed":0,"syntology":null},{"url":"/paper/4dcontrast-contrastive-learning-with-dynamic","slug":"4dcontrast-contrastive-learning-with-dynamic","title":"4DContrast: Contrastive Learning with Dynamic Correspondences for 3D Scene Understanding","date":"2021-12-06","arxiv_id":"2112.02990","repositories_listed":0,"syntology":null},{"url":"/paper/both-style-and-fog-matter-cumulative-domain","slug":"both-style-and-fog-matter-cumulative-domain","title":"Both Style and Fog Matter: Cumulative Domain Adaptation for Semantic Foggy Scene Understanding","date":"2021-12-01","arxiv_id":"2112.00484","repositories_listed":0,"syntology":null},{"url":null,"slug":"joint-modeling-of-visual-objects-and","title":"Joint Modeling of Visual Objects and Relations for Scene Graph Generation","date":"2021-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"remips-physically-consistent-3d","title":"REMIPS: Physically Consistent 3D Reconstruction of Multiple Interacting People under Weak Supervision","date":"2021-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"diffsdfsim-differentiable-rigid-body-dynamics","title":"DiffSDFSim: Differentiable Rigid-Body Dynamics With Implicit Shapes","date":"2021-11-30","arxiv_id":"2111.15318","repositories_listed":0,"syntology":null},{"url":null,"slug":"zero-shot-semantic-segmentation-via-spatial","title":"Zero-Shot Semantic Segmentation via Spatial and Multi-Scale Aware Visual Class Embedding","date":"2021-11-30","arxiv_id":"2111.15181","repositories_listed":0,"syntology":null},{"url":null,"slug":"papooling-graph-based-position-adaptive","title":"PAPooling: Graph-based Position Adaptive Aggregation of Local Geometry in Point Clouds","date":"2021-11-28","arxiv_id":"2111.14067","repositories_listed":0,"syntology":null},{"url":null,"slug":"not-all-relations-are-equal-mining","title":"Not All Relations are Equal: Mining Informative Labels for Scene Graph Generation","date":"2021-11-26","arxiv_id":"2111.13517","repositories_listed":0,"syntology":null},{"url":null,"slug":"panoptic-segmentation-meets-remote-sensing","title":"Panoptic Segmentation Meets Remote Sensing","date":"2021-11-23","arxiv_id":"2111.12126","repositories_listed":0,"syntology":null},{"url":null,"slug":"talk-to-resolve-combining-scene-understanding","title":"Talk-to-Resolve: Combining scene understanding and spatial dialogue to resolve granular task ambiguity for a collocated robot","date":"2021-11-22","arxiv_id":"2111.11099","repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-3d-scene-segmentation-through","title":"Robust 3D Scene Segmentation through Hierarchical and Learnable Part-Fusion","date":"2021-11-16","arxiv_id":"2111.08434","repositories_listed":0,"syntology":null},{"url":null,"slug":"driveguard-robustification-of-automated","title":"DriveGuard: Robustification of Automated Driving Systems with Deep Spatio-Temporal Convolutional Autoencoder","date":"2021-11-05","arxiv_id":"2111.03480","repositories_listed":0,"syntology":null},{"url":null,"slug":"when-neural-networks-using-different-sensors","title":"When Neural Networks Using Different Sensors Create Similar Features","date":"2021-11-04","arxiv_id":"2111.02732","repositories_listed":0,"syntology":null},{"url":null,"slug":"semantic-detection-of-potential-wind-borne","title":"Semantic Detection of Potential Wind-borne Debris in Construction Jobsites: Digital Twining for Hurricane Preparedness and Jobsite Safety","date":"2021-10-22","arxiv_id":"2110.12968","repositories_listed":0,"syntology":null},{"url":null,"slug":"adversarial-scene-reconstruction-and-object","title":"Adversarial Scene Reconstruction and Object Detection System for Assisting Autonomous Vehicle","date":"2021-10-13","arxiv_id":"2110.07716","repositories_listed":0,"syntology":null},{"url":null,"slug":"monocular-depth-estimation-with-sharp","title":"Monocular Depth Estimation with Sharp Boundary","date":"2021-10-12","arxiv_id":"2110.05885","repositories_listed":0,"syntology":null},{"url":null,"slug":"semantic-dense-reconstruction-with-consistent","title":"Semantic Dense Reconstruction with Consistent Scene Segments","date":"2021-09-30","arxiv_id":"2109.14821","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-domain-adaptation-for-lidar","title":"Unsupervised Domain Adaptation for LiDAR Panoptic Segmentation","date":"2021-09-30","arxiv_id":"2109.15286","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-point-transformer-for-large-scale","title":"Efficient Point Transformer for Large-scale 3D Scene Understanding","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"referring-self-supervised-learning-on-3d","title":"Referring Self-supervised Learning on 3D Point Cloud","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"bio-inspired-audio-visual-cues-integration","title":"Audio-Visual Collaborative Representation Learning for Dynamic Saliency Prediction","date":"2021-09-17","arxiv_id":"2109.08371","repositories_listed":0,"syntology":null},{"url":null,"slug":"navigation-oriented-scene-understanding-for","title":"Navigation-Oriented Scene Understanding for Robotic Autonomy: Learning to Segment Driveability in Egocentric Images","date":"2021-09-15","arxiv_id":"2109.07245","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-sins-of-image-synthesis-loss-for-self","title":"On the Sins of Image Synthesis Loss for Self-supervised Depth Estimation","date":"2021-09-13","arxiv_id":"2109.06163","repositories_listed":0,"syntology":null},{"url":null,"slug":"residual-3d-scene-flow-learning-with-context","title":"Residual 3D Scene Flow Learning with Context-Aware Feature Extraction","date":"2021-09-10","arxiv_id":"2109.04685","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-building-segmentation-for-off-nadir","title":"Improving Building Segmentation for Off-Nadir Satellite Imagery","date":"2021-09-08","arxiv_id":"2109.03961","repositories_listed":0,"syntology":null},{"url":"/paper/refinecap-concept-aware-refinement-for-image","slug":"refinecap-concept-aware-refinement-for-image","title":"RefineCap: Concept-Aware Refinement for Image Captioning","date":"2021-09-08","arxiv_id":"2109.03529","repositories_listed":0,"syntology":null},{"url":null,"slug":"binaural-soundnet-predicting-semantics-depth","title":"Binaural SoundNet: Predicting Semantics, Depth and Motion with Binaural Sounds","date":"2021-09-06","arxiv_id":"2109.02763","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-task-learning-from-fixed-wing-uav","title":"Multi-task learning from fixed-wing UAV images for 2D/3D city modeling","date":"2021-08-25","arxiv_id":"2109.00918","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-bayesian-image-set-classification-a","title":"Deep Bayesian Image Set Classification: A Defence Approach against Adversarial Attacks","date":"2021-08-23","arxiv_id":"2108.10217","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-multiple-view-geometric-model-for","title":"A Multiple-View Geometric Model for Specularity Prediction on General Curved Surfaces","date":"2021-08-20","arxiv_id":"2108.09378","repositories_listed":0,"syntology":null},{"url":null,"slug":"patch2cad-patchwise-embedding-learning-for-in","title":"Patch2CAD: Patchwise Embedding Learning for In-the-Wild Shape Retrieval from a Single Image","date":"2021-08-20","arxiv_id":"2108.09368","repositories_listed":0,"syntology":null},{"url":null,"slug":"deployment-of-deep-neural-networks-for-object","title":"Deployment of Deep Neural Networks for Object Detection on Edge AI Devices with Runtime Optimization","date":"2021-08-18","arxiv_id":"2108.08166","repositories_listed":0,"syntology":null},{"url":null,"slug":"indoor-semantic-scene-understanding-using","title":"Indoor Semantic Scene Understanding using Multi-modality Fusion","date":"2021-08-17","arxiv_id":"2108.07616","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-supervised-learning-of-occlusion-aware","title":"Self-supervised Learning of Occlusion Aware Flow Guided 3D Geometry Perception with Adaptive Cross Weighted Loss from Monocular Videos","date":"2021-08-09","arxiv_id":"2108.03893","repositories_listed":0,"syntology":null},{"url":"/paper/ci-net-contextual-information-for-joint","slug":"ci-net-contextual-information-for-joint","title":"CI-Net: Contextual Information for Joint Semantic Segmentation and Depth Estimation","date":"2021-07-29","arxiv_id":"2107.13800","repositories_listed":0,"syntology":null},{"url":null,"slug":"dense-supervision-propagation-for-weakly","title":"Dense Supervision Propagation for Weakly Supervised Semantic Segmentation on 3D Point Clouds","date":"2021-07-23","arxiv_id":"2107.11267","repositories_listed":0,"syntology":null},{"url":null,"slug":"generative-video-transformer-can-objects-be","title":"Generative Video Transformer: Can Objects be the Words?","date":"2021-07-20","arxiv_id":"2107.09240","repositories_listed":0,"syntology":null},{"url":null,"slug":"accelerating-deep-neural-networks-for","title":"Accelerating deep neural networks for efficient scene understanding in automotive cyber-physical systems","date":"2021-07-19","arxiv_id":"2107.09101","repositories_listed":0,"syntology":null},{"url":null,"slug":"codemapping-real-time-dense-mapping-for","title":"CodeMapping: Real-Time Dense Mapping for Sparse SLAM using Compact Scene Representations","date":"2021-07-19","arxiv_id":"2107.08994","repositories_listed":0,"syntology":null},{"url":null,"slug":"dance-data-network-co-optimization-for","title":"DANCE: DAta-Network Co-optimization for Efficient Segmentation Model Training and Inference","date":"2021-07-16","arxiv_id":"2107.07706","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-weakly-supervised-depth-estimation-network","title":"A Weakly-Supervised Depth Estimation Network Using Attention Mechanism","date":"2021-07-10","arxiv_id":"2107.04819","repositories_listed":0,"syntology":null},{"url":null,"slug":"empowering-cyberphysical-systems-of-systems","title":"Empowering cyberphysical systems of systems with intelligence","date":"2021-07-05","arxiv_id":"2107.02264","repositories_listed":0,"syntology":null},{"url":null,"slug":"hybrid-memoised-wake-sleep-approximate","title":"Hybrid Memoised Wake-Sleep: Approximate Inference at the Discrete-Continuous Interface","date":"2021-07-04","arxiv_id":"2107.06393","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-analysis-of-state-of-the-art-models-for","title":"An Analysis of State-of-the-Art Models for Situated Interactive MultiModal Conversations (SIMMC)","date":"2021-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"egocentric-image-captioning-for-privacy","title":"Egocentric Image Captioning for Privacy-Preserved Passive Dietary Intake Monitoring","date":"2021-07-01","arxiv_id":"2107.00372","repositories_listed":0,"syntology":null},{"url":"/paper/unsupervised-image-segmentation-by-mutual","slug":"unsupervised-image-segmentation-by-mutual","title":"Unsupervised Image Segmentation by Mutual Information Maximization and Adversarial Regularization","date":"2021-07-01","arxiv_id":"2107.00691","repositories_listed":0,"syntology":null},{"url":null,"slug":"imenet-joint-3d-semantic-scene-completion-and","title":"IMENet: Joint 3D Semantic Scene Completion and 2D Semantic Segmentation through Iterative Mutual Enhancement","date":"2021-06-29","arxiv_id":"2106.15413","repositories_listed":0,"syntology":null},{"url":null,"slug":"offroadtranseg-semi-supervised-segmentation","title":"OffRoadTranSeg: Semi-Supervised Segmentation using Transformers on OffRoad environments","date":"2021-06-26","arxiv_id":"2106.13963","repositories_listed":0,"syntology":null},{"url":null,"slug":"ireason-multimodal-commonsense-reasoning","title":"iReason: Multimodal Commonsense Reasoning using Videos and Natural Language with Interpretability","date":"2021-06-25","arxiv_id":"2107.10300","repositories_listed":0,"syntology":null},{"url":null,"slug":"feature-level-collaboration-joint","title":"Feature-Level Collaboration: Joint Unsupervised Learning of Optical Flow, Stereo Depth and Camera Motion","date":"2021-06-19","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"openrooms-an-open-framework-for","title":"OpenRooms: An Open Framework for Photorealistic Indoor Scene Datasets","date":"2021-06-19","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-urban-scenes-understanding-through","title":"Towards urban scenes understanding through polarization cues","date":"2021-06-03","arxiv_id":"2106.01717","repositories_listed":0,"syntology":null},{"url":null,"slug":"polarimetric-spatio-temporal-light-transport","title":"Polarimetric Spatio-Temporal Light Transport Probing","date":"2021-05-25","arxiv_id":"2105.11609","repositories_listed":0,"syntology":null},{"url":null,"slug":"egocentric-activity-recognition-and","title":"Egocentric Activity Recognition and Localization on a 3D Map","date":"2021-05-20","arxiv_id":"2105.09544","repositories_listed":0,"syntology":null},{"url":null,"slug":"sail-vos-3d-a-synthetic-dataset-and-baselines","title":"SAIL-VOS 3D: A Synthetic Dataset and Baselines for Object Detection and 3D Mesh Reconstruction from Video Data","date":"2021-05-18","arxiv_id":"2105.08612","repositories_listed":0,"syntology":null},{"url":null,"slug":"scene-understanding-for-autonomous-driving","title":"Scene Understanding for Autonomous Driving","date":"2021-05-11","arxiv_id":"2105.04905","repositories_listed":0,"syntology":null},{"url":null,"slug":"acdc-the-adverse-conditions-dataset-with","title":"ACDC: The Adverse Conditions Dataset with Correspondences for Robust Semantic Driving Scene Perception","date":"2021-04-27","arxiv_id":"2104.13395","repositories_listed":0,"syntology":null},{"url":null,"slug":"wireless-sensing-with-deep-spectrogram","title":"Wireless Sensing With Deep Spectrogram Network and Primitive Based Autoregressive Hybrid Channel Model","date":"2021-04-21","arxiv_id":"2104.10378","repositories_listed":0,"syntology":null},{"url":null,"slug":"monogrnet-a-general-framework-for-monocular","title":"MonoGRNet: A General Framework for Monocular 3D Object Detection","date":"2021-04-18","arxiv_id":"2104.08797","repositories_listed":0,"syntology":null},{"url":null,"slug":"single-image-depth-estimation-an-overview","title":"Single Image Depth Estimation: An Overview","date":"2021-04-13","arxiv_id":"2104.06456","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-ensembles-based-on-stochastic-activation","title":"Deep ensembles based on Stochastic Activation Selection for Polyp Segmentation","date":"2021-04-02","arxiv_id":"2104.00850","repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluation-of-multimodal-semantic","title":"Evaluation of Multimodal Semantic Segmentation using RGB-D Data","date":"2021-03-31","arxiv_id":"2103.16758","repositories_listed":0,"syntology":null}],"record_sha256":"d552bfdceca13c937d96aba7bbd33eb7a84060683874b9219f325a15bf242253","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}